CN111830061A - Aeroengine detection system and method based on machine vision - Google Patents
Aeroengine detection system and method based on machine vision Download PDFInfo
- Publication number
- CN111830061A CN111830061A CN202010764138.4A CN202010764138A CN111830061A CN 111830061 A CN111830061 A CN 111830061A CN 202010764138 A CN202010764138 A CN 202010764138A CN 111830061 A CN111830061 A CN 111830061A
- Authority
- CN
- China
- Prior art keywords
- picture
- detection
- unit
- axis robot
- identification result
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 187
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims abstract description 49
- 238000004519 manufacturing process Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 56
- 238000003860 storage Methods 0.000 claims description 33
- 230000005856 abnormality Effects 0.000 claims description 12
- 238000005538 encapsulation Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 14
- 238000009826 distribution Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an aeroengine detection system and method based on machine vision, wherein the system comprises: the system comprises aeroengine equipment, a multi-axis robot system, an AI algorithm server and a service platform server; the method comprises the following steps: the multi-axis robot system collects picture data of different point positions of the aircraft engine equipment and sends the picture data to the AI algorithm server; the AI algorithm server classifies the picture data, intelligently analyzes the picture and outputs an identification result; the service platform server compares the received identification result with pictures in a standard picture library, and if the detection is normal, the point location detection is passed; and if the point location detection is abnormal, giving abnormal classification, and outputting an overall detection report after all point location detection is finished. The aeroengine detection system and method based on machine vision provided by the invention apply the machine vision technology to the factory detection of aeroengine production, thereby not only avoiding false detection and missed detection, but also greatly improving the detection efficiency and reducing the detection cost investment.
Description
Technical Field
The invention relates to the field of industrial detection of aero-engines, in particular to an aero-engine detection system and method based on machine vision.
Background
When the aircraft engine is delivered and inspected to the whole machine, the appearance of the aircraft engine needs to be comprehensively detected, the important point is to detect the positions of a bracket, a hoop, a joint fuse and the like outside the aircraft engine, and whether assembly defects exist is detected, wherein the assembly defects comprise misassembly, neglected assembly, multi-assembly, position mismatching and the like. At present, the detection work is carried out in a manual visual mode, the detection points are multiple, the similarity of the detected points of the same type is high, the manual detection efficiency is low, and the detection personnel are easy to fatigue and negligence due to long-time concentrated work, so that the problems of false detection, missed detection and the like are caused.
Disclosure of Invention
In view of the defects of the implementation mode of the prior art, the aeroengine detection system and method based on machine vision provided by the invention apply the machine vision technology to the factory detection of aeroengine production, thereby not only avoiding false detection and missed detection, but also greatly improving the detection efficiency and reducing the detection cost investment.
The technical scheme provided by the invention is as follows:
a machine vision based aircraft engine inspection system, wherein the system comprises:
the aeroengine equipment is to-be-detected aeroengine equipment after production.
And the multi-axis robot system is used for acquiring the picture data of different point positions of the aircraft engine equipment.
And the AI algorithm server intelligently analyzes the acquired picture data of different point positions of the aircraft engine and provides an intelligent analysis and identification result.
And the service platform server compares the intelligent analysis and identification result with the pictures in the standard picture library and provides a detection report.
Further, the aircraft engine detection system based on machine vision, wherein the multi-axis robot system specifically includes:
and the guide rail is used for providing a track for the movement of the multi-axis robot.
And the 3D industrial camera is used for acquiring the relative position information of the aircraft engine and the multi-axis robot and providing positioning navigation information for the multi-axis robot.
The industrial camera is used for acquiring picture data of different point positions of the aircraft engine.
And the multi-axis robot is used for moving on the guide rail, can rotate at multiple degrees of freedom, moves the position of the industrial camera, and controls the industrial camera to acquire picture data of different point positions of the aircraft engine equipment.
Further, the aircraft engine detection system based on machine vision, wherein the multi-axis robot of the multi-axis robot system specifically includes:
and the motor driving unit is used for driving the multi-axis robot to move on the guide rail.
And the coordinate database unit is used for storing the coordinate position information of all the image acquisition data points.
And the positioning navigation unit is used for acquiring accurate position information of the multi-axis robot in real time.
And the position coarse adjustment unit is used for coarse adjusting the position of the mechanical arm.
And the position fine adjustment unit is used for finely adjusting the position of the mechanical arm.
And the camera shooting control unit is used for controlling the industrial camera to acquire pictures.
And the picture coordinate identification unit is used for providing coordinate identification for the pictures acquired in detail in the industry.
And the picture storage and output unit is used for storing the pictures acquired by the industrial camera and outputting the pictures to the AI algorithm server for intelligent analysis and processing.
Further, the aircraft engine detection system based on machine vision, wherein the AI algorithm server specifically includes:
and the collected picture receiving unit is used for receiving the picture data sent by the multi-axis robot system.
And the acquisition picture classification unit is used for classifying the acquired picture information, and the picture classification is based on the coordinate information corresponding to the picture and the component type of the detection point location.
And the picture identification unit is used for intelligently identifying the picture based on different algorithm detection models and outputting an intelligent analysis identification result.
And the recognition result unit is used for carrying out data encapsulation on the intelligent analysis recognition results of different algorithm detection models.
And the collected picture output unit is used for outputting the picture to the service platform server.
And the recognition result output unit is used for outputting the packaged intelligent analysis recognition result data to the service platform server.
Further, the aircraft engine detection system based on machine vision, wherein the service platform server specifically includes:
and the standard picture library unit is used for storing the part picture information of the normal standard of the aircraft engine equipment.
And the acquisition picture receiving unit is used for receiving the picture data sent by the AI algorithm server.
And the identification result receiving unit is used for receiving the intelligent analysis identification result data sent by the AI algorithm server.
And the identification result comparison unit is used for comparing the received intelligent analysis identification result data with the picture data in the standard picture library and giving comparison result information, wherein the comparison result is normal or abnormal.
And an abnormality classification unit for classifying the detected abnormality.
And the detection report unit is used for summarizing all detected result information and outputting a detection report.
And the detection report storage unit is used for storing the detection report.
And the detection report presenting unit is used for displaying the content information of the detection report.
And the picture storage unit is used for storing the received picture data.
And the identification result storage unit is used for storing the received intelligent analysis identification result data.
Further, the invention also provides an aircraft engine detection method based on machine vision, wherein the method comprises the following steps:
the multi-axis robot system collects picture data of different point positions of the aircraft engine equipment and sends the picture data to the AI algorithm server.
And the AI algorithm server classifies the picture data, intelligently analyzes the picture and outputs an identification result.
The service platform server compares the received identification result with pictures in a standard picture library, and if the detection is normal, the point location detection is passed; and if the point location detection is abnormal, giving abnormal classification, and outputting an overall detection report after all point location detection is finished.
Further, the method for detecting the aircraft engine based on the machine vision, wherein the multi-axis robot system collects picture data of different point locations of the aircraft engine equipment and sends the picture data to the AI algorithm server, specifically comprises:
a multi-axis robot of the multi-axis robot system moves on a guide rail of the multi-axis robot system.
The 3D industrial camera of the multi-axis robot system collects the relative position information of the aero-engine and the multi-axis robot in real time and provides positioning navigation information for the multi-axis robot.
And the multi-axis robot adjusts the position of the multi-axis robot according to the positioning navigation information.
And when the position information of the multi-axis robot is matched with one coordinate position information in the coordinate database unit of the multi-axis robot, the camera shooting control unit of the multi-axis robot controls the industrial camera to acquire the picture data of the corresponding point of the aircraft engine.
And the picture storage and output unit of the multi-axis robot stores the pictures acquired by the industrial camera and outputs the pictures to the AI algorithm server for intelligent analysis and processing.
Further, the method for detecting an aircraft engine based on machine vision, wherein the AI algorithm server classifies picture data, intelligently identifies pictures, and outputs identification results, specifically includes:
and the acquisition picture receiving unit of the AI algorithm server receives the picture data sent by the multi-axis robot system.
And the acquired picture classifying unit of the AI algorithm server classifies the acquired picture information, and the picture classification is based on the coordinate information corresponding to the picture and the component type of the detection point location.
And the picture identification unit of the AI algorithm server intelligently identifies the picture based on different algorithm detection models and outputs an intelligent analysis identification result.
And the identification result unit of the AI algorithm server performs data encapsulation on the intelligent analysis identification results of different algorithm detection models.
And the acquired picture output unit of the AI algorithm server outputs the picture to the service platform server.
And the identification result output unit of the AI algorithm server outputs the packaged intelligent analysis identification result data to the service platform server.
Further, the method for detecting an aircraft engine based on machine vision, wherein the service platform server compares the received identification result with pictures in a standard picture library, and if the detection is normal, the point location detection is passed, specifically comprising:
and the identification result receiving unit of the service platform server receives the intelligent analysis identification result data sent by the AI algorithm server.
And the identification result comparison unit of the service platform server compares the received intelligent analysis identification result data with the picture data in the standard picture library and provides comparison result information, wherein the comparison result is normal or abnormal.
And the comparison result is normal, which indicates that the detection is normal, and the point location detection is passed.
Further, the method for detecting an aircraft engine based on machine vision, wherein the service platform server compares the received identification result with pictures in a standard picture library, if there is an abnormality, an abnormality classification is given, and after all point locations are detected, an overall detection report is output, specifically including:
and the identification result comparison unit of the service platform server compares the received intelligent analysis identification result data with the picture data in the standard picture library and provides comparison result information, wherein the comparison result is normal or abnormal.
And the comparison result is abnormal, and the point detection is not passed.
And the abnormity classification unit of the service platform server classifies the detected abnormity.
And the detection report unit of the service platform server summarizes all detected result information and outputs a detection report.
And the detection report storage unit of the service platform server stores the detection report.
And the detection report presenting unit of the service platform server displays the content information of the detection report.
And the picture storage unit of the service platform server stores the picture data received by the collected picture receiving unit.
And the identification result storage unit of the service platform server stores the intelligent analysis identification result data received by the identification result receiving unit.
The aircraft engine detection system and method based on machine vision provided by the invention apply the machine vision technology to the delivery detection of aircraft engine production, thereby not only avoiding false detection and missed detection, but also greatly improving the detection efficiency and reducing the detection cost input.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments are briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a block diagram of a system architecture of a machine vision based aircraft engine inspection system of the present invention.
Fig. 2 is a functional structure block diagram of a multi-axis robot system in the system architecture of the machine vision-based aircraft engine detection system according to the present invention.
Fig. 3 is a functional structure block diagram of a multi-axis robot in the functional structure of a multi-axis robot system in the system architecture of the machine vision-based aircraft engine detection system according to the present invention.
Fig. 4 is a functional structure block diagram of an AI algorithm server in the system architecture of the machine vision-based aircraft engine detection system according to the present invention.
Fig. 5 is a functional structure block diagram of a service platform server in the system architecture of the machine vision-based aircraft engine detection system according to the present invention.
FIG. 6 is a flow chart of a preferred embodiment of a machine vision based aircraft engine inspection method of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is described in further detail below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a system architecture block diagram of an aircraft engine detection system based on machine vision, which is shown in fig. 1. The method specifically comprises the following steps:
the aircraft engine device 100, the multi-axis robot system 200, the AI algorithm server 300, and the service platform server 400.
The aircraft engine equipment 100 is aircraft engine equipment to be detected after production is finished; the to-be-detected method is detection of appearance parts; the appearance parts include but are not limited to: brackets, clamps, joint safeties, etc.; the detection means detecting whether the appearance parts have assembly defects such as misassembly, neglected assembly, multiple assembly, position mismatching and the like.
The multi-axis robot system 200 is used for acquiring picture data of different point positions of the aircraft engine equipment; more specifically, the multi-axis robot system 200 moves the multi-axis robot to a corresponding point location according to coordinate information of a detection point location preset by the system, and controls the industrial camera to acquire image data of the corresponding point location of the aircraft engine device; the multi-axis robot system 200 is further configured to add a point location identifier to the acquired picture data, where the point location identifier corresponds to coordinate information of a point location; the multi-axis robot system 200 is further configured to send the acquired picture information to the AI algorithm server 300.
The AI algorithm server 300 intelligently analyzes the acquired picture data of different point positions of the aircraft engine and provides an intelligent analysis and identification result; the AI algorithm server 300 trains algorithm models according to the characteristics of different parts of the aircraft engine, so as to intelligently analyze the picture data and provide an intelligent analysis result; the AI algorithm server 300 is further configured to send the picture data and the intelligent analysis recognition result to the service platform server 400.
The service platform server 400 compares the intelligent analysis recognition result with the pictures in the standard picture library and gives a detection report; the detection report comprises detection result information of each point location; the service platform server 400 presents the detection report, including the passing condition of the detection point location, the distribution of the abnormal point location, the abnormal details, and the like; the service platform server 400 is further configured to store the picture data, the identification result data, and the detection report.
The invention provides a functional structure block diagram of a multi-axis robot system in a system architecture of an aircraft engine detection system based on machine vision, which is shown in fig. 2. The method specifically comprises the following steps:
a rail 210, a 3D industrial camera 220, an industrial camera 230, a multi-axis robot 240.
The guide rail 210 of the multi-axis robot system 200 is used for providing a track for movement of the multi-axis robot, and the multi-axis robot 240 of the multi-axis robot system 200 moves on the guide rail, so as to move the industrial camera to different positions to acquire picture data of different detection point positions.
The 3D industrial camera 220 of the multi-axis robot system 200 is configured to collect relative position information of the aircraft engine and the multi-axis robot 240, and provide positioning navigation information for the multi-axis robot 240; the 3D industrial camera 220 needs to give specific position reference information so that the multi-axis robot 240 collects picture information of different point locations of the aircraft engine apparatus 100; a certain point location on the aircraft engine equipment 100 is an origin of coordinates for data acquisition, and the position system information of other point locations is uniquely represented by (x, y, z) coordinates; the distribution of aeroengine equipment 100 according to different position, can divide into 5 detection areas, is respectively: the aeroengine comprises an aeroengine front area, an aeroengine hanger coverage area (left along the course), a transport vehicle coverage area, an aeroengine hanger coverage area (right along the course) and an aeroengine rear area.
The industrial camera 230 of the multi-axis robot system 200 is configured to acquire image data of different point locations of the aircraft engine; the industrial camera 230 selects different camera specifications according to different detection specification requirements, and the industrial camera 230 with more than 2500 ten thousand pixels is suggested to be adopted in practical application; the industrial camera 230 is mounted on the multi-axis robot 240, and the multi-axis robot 240 moves the industrial camera 230 to a specific spot location to acquire picture data.
The multi-axis robot 240 of the multi-axis robot system 200 is configured to move on the guide rail, rotate in multiple degrees of freedom, move the position of the industrial camera, and control the industrial camera to acquire image data of different point locations of the aircraft engine device; the multi-axis robot 240 is further configured to add a point location identifier to the acquired picture data, where the point location identifier corresponds to coordinate information of a point location; the multi-axis robot 240 is also configured to send the acquired picture information to the AI algorithm server 300.
The invention provides a functional structure block diagram of a multi-axis robot in a functional structure of a multi-axis robot system in a system architecture of an aircraft engine detection system based on machine vision, which is shown in fig. 3. The method specifically comprises the following steps:
a motor driving unit 241, a coordinate database unit 242, a positioning navigation unit 243, a coarse position adjusting unit 244, a fine position adjusting unit 245, a camera shooting control unit 246, a picture coordinate identification unit 247, and a picture storage and output unit 248.
The motor driving unit 241 of the multi-axis robot 240 is configured to drive the multi-axis robot to move on a guide rail; the motor driving unit 241 moves the multi-axis robot 240 to a corresponding position of the positioning point based on the coordinate position information of the positioning point provided by the coordinate database unit 242 and the positioning navigation unit 243 and the coordinate position information of the current multi-axis robot 240, and the position coarse adjustment unit 244 and the position fine adjustment unit 245 adjust the driving parameter information of the motor driving unit 241; more specifically, the multi-axis robot 240 drives the industrial camera 230 to a positioning point specified by the coordinate database unit 242 to acquire image data.
The coordinate database unit 242 of the multi-axis robot 240 is configured to store coordinate position information of all image acquisition data points; more specifically, the coordinate position information stored in the coordinate database unit 242 is coordinate position information of a point location to be detected, which is acquired in advance; the detected point location is represented by the coordinate origin of the first point location, and the position information of other point locations relative to the coordinate origin is uniquely represented by (x, y, z) coordinates; the point location information is uniquely identified by area identification, point location identification, component type identification and (x, y, z) coordinate information; the region identification is used for identifying different regions, and the regions comprise: the aeroengine comprises an aeroengine front area, an aeroengine hanger coverage area (left side along the course), a transport vehicle coverage area, an aeroengine hanger coverage area (right side along the course) and an aeroengine rear area; the point location identification is used for identifying different point locations and is a serial number of the different point locations; the component type identifier is used for identifying different types of components, and specifically includes but is not limited to: brackets, clamps, joint safeties, etc.; the (x, y, z) coordinate information is used to give position information of the point location with respect to the origin of coordinates.
The positioning navigation unit 243 of the multi-axis robot 240 is configured to obtain accurate position information of the multi-axis robot in real time; the position information of the positioning navigation unit 243 is provided by the 3D industrial camera 220; the 3D industrial camera 220 is configured to acquire relative position information of the aircraft engine and the multi-axis robot 240, and provide positioning navigation information for the multi-axis robot 240; the 3D industrial camera 220 needs to give specific position reference information.
The position rough adjustment unit 244 of the multi-axis robot 240 for rough adjustment of the position of the robot arm; the position rough adjusting unit 244 provides driving parameter information for the motor driving unit 241 according to the coordinate position information of the positioning point provided by the coordinate database unit 242 and the coordinate position information of the current multi-axis robot 240 provided by the positioning navigation unit 243; the driving parameter information is coarse adjustment driving parameter information, and the accuracy which can be achieved by the coarse adjustment driving parameter information is centimeter level.
The position fine adjustment unit 245 of the multi-axis robot 240 for fine adjusting the position of the robot arm; the position fine adjustment unit 245 provides driving parameter information for the motor driving unit 241 according to the coordinate position information of the positioning point provided by the coordinate database unit 242 and the coordinate position information of the current multi-axis robot 240 provided by the positioning navigation unit 243; the driving parameter information is fine adjustment driving parameter information, and the precision which can be achieved by the fine adjustment driving parameter information is 0.1 millimeter level.
The camera photographing control unit 246 of the multi-axis robot 240 for controlling the industrial camera 230 to perform picture taking; when the position of the multi-axis robot 240 reaches the point where the picture is taken, the camera photographing control unit 246 controls the industrial camera 230 to take the picture data of the aero-engine.
The picture coordinate identification unit 247 of the multi-axis robot 240 is configured to provide a coordinate identification for a picture acquired by an industrial camera; more specifically, the coordinate identification information provided by the picture coordinate identification unit 247 for the collected picture is actually point location identification information, and the point location identification information is specifically uniquely identified by an area identification, a point location identification, a component type identification, and (x, y, z) coordinate information.
The picture storage and output unit 248 of the multi-axis robot 240 is configured to store pictures acquired by the industrial camera and output the pictures to the AI algorithm server for intelligent analysis and processing; the collected picture information is stored on the SD card and/or the TF card by the picture storage and output unit 248; the acquired picture information is sent to an AI algorithm server by the picture storage and output unit 248 for intelligent analysis processing.
The invention provides a functional structure block diagram of an AI algorithm server in a system architecture of an aircraft engine detection system based on machine vision, which is shown in FIG. 4. The method specifically comprises the following steps:
a collected picture receiving unit 301, a collected picture classifying unit 302, a picture identifying unit 303, an identification result unit 304, a collected picture output unit 305, and an identification result output unit 306.
The collected picture receiving unit 301 of the AI algorithm server 300 is configured to receive picture data sent by the multi-axis robot system; the picture data comprises point location identification information; the point location identification information is specifically identified by an area identification, a point location identification, a component type identification and (x, y, z) coordinate information.
The collected picture classifying unit 302 of the AI algorithm server 300 is configured to classify the obtained picture information, where the picture classification is based on the coordinate information corresponding to the picture and the component type of the detection point location; more specifically, the classification of the pictures is based on point location identification information; the point location identification information is specifically identified by an area identification, a point location identification, a component type identification and (x, y, z) coordinate information.
The picture recognition unit 303 of the AI algorithm server 300 intelligently recognizes the picture based on different algorithm detection models, and outputs an intelligent analysis recognition result; the algorithm detection model is used for training the algorithm model based on parts of different types and different specifications; the different types of components include, but are not limited to: brackets, clamps, joint safeties, etc.; the different specifications include, but are not limited to: type, size, shape, material, etc.; the algorithmic detection model includes, but is not limited to: a support algorithm detection model, a hoop algorithm detection model, a joint insurance algorithm detection model and the like; the algorithm detection model calls different algorithm detection models according to the pictures at different point positions, so that intelligent analysis and identification result data are given; the recognition result data includes, but is not limited to: bracket identification result data, clamp identification result data, and joint insurance identification result data.
The recognition result unit 304 of the AI algorithm server 300 is configured to perform data encapsulation on the intelligent analysis recognition results of different algorithm detection models; the recognition result data includes, but is not limited to: bracket identification result data, clamp identification result data and joint insurance identification result data; the step of carrying out data encapsulation on the intelligent analysis recognition result refers to the step of associating the recognition result data with specific pictures and point identification information; the pictures refer to the collected pictures of different detection points of the original aircraft engine; the point location identification information is specifically identified by an area identification, a point location identification, a component type identification and (x, y, z) coordinate information.
The collected picture output unit 305 of the AI algorithm server 300 is configured to output picture data to the service platform server; the picture data comprises coded data of the picture and point location identification information of the picture.
The recognition result output unit 306 of the AI algorithm server 300 is configured to output the encapsulated intelligent analysis recognition result data to the service platform server.
The invention provides a functional structure block diagram of a service platform server in a system architecture of an aircraft engine detection system based on machine vision, which is shown in fig. 5. The method specifically comprises the following steps:
a standard picture library unit 401, a collected picture receiving unit 402, an identification result receiving unit 403, an identification result comparing unit 404, an abnormality classifying unit 405, a detection report unit 406, a detection report storage unit 407, a detection report presenting unit 408, a picture storage unit 409, and an identification result storage unit 410.
The standard picture library unit 401 of the service platform server 400 is configured to store component picture information of a normal standard of an aircraft engine device; the normal standard component picture information comprises picture coding data, point location identification information of a picture and a characteristic value of the picture; the point location identification information is specifically a unique identification consisting of an area identification, a point location identification, a component type identification and (x, y, z) coordinate information; the region identification is used for identifying region information, and the region refers to a region in front of the aircraft engine, a region covered by a lifting appliance of the aircraft engine (left side along the course), a region covered by a transport vehicle, a region covered by the lifting appliance of the aircraft engine (right side along the course) and a region behind the aircraft engine; the component types include, but are not limited to: brackets, clips, joint safeties, etc. The standard picture library unit 401 may be classified into a standard rack picture library, a standard hoop picture library, and a standard joint insurance picture library, distinguished by the type of component.
Taking a certain type of aircraft engine as an example, the standard stent picture library is used for storing stent picture information of the normal standard of the aircraft engine, and specifically comprises stent picture identification, stent picture data and coordinate information of stent pictures. The first bracket comprises 210 parts, specifically: 80 pieces in the front area of the aircraft engine, 10 pieces in the coverage area (left heading) of the aircraft engine lifting appliance, 70 pieces in the coverage area of the transport vehicle, 20 pieces in the coverage area (right heading) of the aircraft engine lifting appliance and 30 pieces in the rear area of the aircraft engine. Each coordinate position at least comprises a normal standard picture.
Taking a certain type of aircraft engine as an example, the standard hoop picture library is used for storing hoop picture information of the normal standard of the aircraft engine, and specifically comprises hoop picture identification, hoop picture data and coordinate information of hoop pictures. The first hoop has 530 groups, specifically: group 180 of front regions of the aero-engine, group 50 of spreader coverage regions (left heading), group 180 of transporter coverage regions, group 60 of spreader coverage regions (right heading), group 60 of rear regions of the aero-engine. Each coordinate position at least comprises a normal standard picture.
Taking a certain type of aircraft engine as an example, the standard joint insurance picture library is used for storing joint insurance picture information of the normal standard of the aircraft engine, and specifically comprises joint insurance picture identification, joint insurance picture data and coordinate information of a joint insurance picture. The joint insurance is 220 in total, and specifically comprises the following steps: an aircraft engine forward area 50, an aircraft engine spreader footprint area (forward left) 20, a transporter footprint area 90, an aircraft engine spreader footprint area (forward right) 20, and an aircraft engine aft area 40. Each coordinate position at least comprises a normal standard picture.
The collected picture receiving unit 402 of the service platform server 400 is configured to receive picture data sent by an AI algorithm server; the received picture data comprises coded data of the picture and point location identification information of the picture; the point location identification information of the picture is specifically identified by an area identification, a point location identification, a component type identification and (x, y, z) coordinate information.
The identification result receiving unit 403 of the service platform server 400 is configured to receive intelligent analysis identification result data sent by an AI algorithm server; the recognition result data includes: bracket identification result data, clamp identification result data and joint insurance identification result data; the identification result data also comprises information which is associated with the identification result data and the specific picture and the point identification information; the pictures refer to the collected pictures of different detection points of the original aircraft engine; the point location identification information is specifically identified by an area identification, a point location identification, a component type identification and (x, y, z) coordinate information.
The identification result comparing unit 404 of the service platform server 400 is configured to compare the received intelligent analysis identification result data with picture data in a standard picture library, and provide comparison result information, where the comparison result is normal or abnormal; the recognition result comprises: bracket identification result data, clamp identification result data and joint insurance identification result data; the standard picture library includes: a standard bracket picture library, a standard hoop picture library and a standard joint insurance picture library; the identification result comparing unit 404 finds corresponding pictures in the standard picture library according to the point location identification information in the identification result data and compares the pictures with the feature values of the pictures to obtain comparison results, where the comparison results include two types, one type is normal and the other type is abnormal.
The anomaly classification unit 405 of the service platform server 400 is configured to classify the detected anomalies; when the detection result of a certain point location by the identification result comparison unit 404 is abnormal, the abnormality classification unit 405 needs to classify the abnormality; the abnormality classification information includes: abnormal point location identification information, a point location acquisition picture, a point location standard picture, an abnormal grade and an abnormal point location component type.
The detection report unit 406 of the service platform server 400 is configured to summarize all detected result information and output a detection report; the detection report contains detection result information of all detection point locations, normal or abnormal, abnormal point location distribution, abnormal quantity, quantity of different abnormal severity grades and quantity of different types of abnormal, and can show detailed abnormal information about a specific point location: the method comprises the following steps of abnormal pictures, difference comparison between the abnormal pictures and the normal pictures, abnormal description, abnormal classification, abnormal severity grade, abnormal point location number, abnormal point location coordinate information and the like.
The detection report storage unit 407 of the service platform server 400 is configured to store a detection report; the storage refers to storing the detection report in a nonvolatile storage medium.
The detection report presenting unit 408 of the service platform server 400 is configured to display content information of a detection report; the method specifically comprises the following steps: detecting the overall detection condition of the point locations, namely normal point location distribution and abnormal point location distribution; the abnormal point location further includes detailed information of the abnormal point location, specifically: the method comprises the following steps of abnormal pictures, difference comparison between the abnormal pictures and the normal pictures, abnormal description, abnormal classification, abnormal severity grade, abnormal point location number, abnormal point location coordinate information and the like.
The picture storage unit 409 of the service platform server 400 is configured to store the received picture data; the picture data comprises coded data of the picture and point location identification information of the picture; the bit identification information is specifically identified by an area identification, a point location identification, a component type identification and (x, y, z) coordinate information.
The identification result storage unit 410 of the service platform server 400 is configured to store the received intelligent analysis identification result data; the intelligent analysis recognition result data comprises: bracket identification result data, clamp identification result data and joint insurance identification result data; the identification result data also comprises information which is associated with the identification result data and the specific picture and the point identification information; the pictures refer to the collected pictures of different detection points of the original aircraft engine; the point location identification information is specifically identified by an area identification, a point location identification, a component type identification and (x, y, z) coordinate information.
The invention provides a flow chart of a preferred embodiment of the aircraft engine detection method based on machine vision, which is shown in fig. 6. The method comprises the following specific steps:
step S100: the multi-axis robot system 200 collects picture data of different point locations of the aircraft engine apparatus 100, and sends the picture data to the AI algorithm server 300.
The multi-axis robot 240 of the multi-axis robot system 200 moves on the guide rail 210 of the multi-axis robot system.
The 3D industrial camera 220 of the multi-axis robot system 200 collects the relative position information of the aero-engine and the multi-axis robot in real time, and provides the multi-axis robot 240 with positioning navigation information.
And the multi-axis robot 240 adjusts the position of the multi-axis robot according to the positioning navigation information.
When the position information of the multi-axis robot 240 matches with one coordinate position information in the coordinate database unit 242 of the multi-axis robot 240, the camera shooting control unit 246 of the multi-axis robot 240 controls the industrial camera 230 to collect the picture data of the corresponding point of the aircraft engine.
The picture coordinate identification unit 247 of the multi-axis robot 240 provides coordinate identification to the picture collected by the industrial camera 230.
The accurate positioning of the multi-axis robot 240 for the acquisition point is cooperatively processed by the 3D industrial camera 220, the motor driving unit 241, the positioning navigation unit 243, the coordinate database unit 242, the coarse position adjusting unit 244 and the fine position adjusting unit 245, so that the accurate positioning is realized.
The picture storage and output unit 248 of the multi-axis robot 240 stores the pictures collected by the industrial camera 230 and outputs the pictures to the AI algorithm server 300 for intelligent analysis and processing.
More specifically, the guide rail 210, the 3D industrial camera 220, the industrial camera 230, and the multi-axis robot 240 of the multi-axis robot system 200 are already described in detail in the functional block diagram of the multi-axis robot system in the system architecture of the aircraft engine detection system based on machine vision provided in fig. 2, and are not repeated herein.
More specifically, the motor driving unit 241, the coordinate database unit 242, the positioning navigation unit 243, the coarse position adjustment unit 244, the fine position adjustment unit 245, the camera shooting control unit 246, the picture coordinate identification unit 247, and the picture storage and output unit 248 of the multi-axis robot 240 are already described in detail in the functional block diagram of the multi-axis robot system in the system architecture of the machine vision based aircraft engine detection system provided in fig. 3, and therefore, no further description is given here.
Step S200: and the AI algorithm server classifies the picture data, intelligently analyzes the picture and outputs an identification result.
The collected picture receiving unit 301 of the AI algorithm server 300 receives picture data sent by the multi-axis robot system.
The collected picture classification unit 302 of the AI algorithm server 300 classifies the acquired picture information, and the picture classification is based on the coordinate information corresponding to the picture and the type of the component of the detection point location.
The picture recognition unit 303 of the AI algorithm server 300 intelligently recognizes the picture based on different algorithm detection models, and outputs an intelligent analysis recognition result.
The recognition result unit 304 of the AI algorithm server 300 performs data encapsulation on the intelligent analysis recognition results of different algorithm detection models.
The collected picture output unit 305 of the AI algorithm server 300 outputs a picture to the service platform server.
The recognition result output unit 306 of the AI algorithm server 300 outputs the encapsulated intelligent analysis recognition result data to the service platform server.
More specifically, the collected picture receiving unit 301, the collected picture classifying unit 302, the picture identifying unit 303, the identification result unit 304, the collected picture output unit 305, and the identification result output unit 306 of the AI algorithm server 300 have already been described in detail in the functional block diagram of the AI algorithm server in the system architecture of the machine vision-based aeroengine detection system provided in fig. 4, and are not described herein again.
Step S300: the service platform server compares the received identification result with pictures in a standard picture library, and if the detection is normal, the point location detection is passed; and if the point location detection is abnormal, giving abnormal classification, and outputting an overall detection report after all point location detection is finished.
The identification result receiving unit 403 of the service platform server 400 receives the intelligent analysis identification result data sent by the AI algorithm server 300.
The identification result comparing unit 404 of the service platform server 400 compares the received intelligent analysis identification result data with the picture data in the standard picture library unit 401, and provides comparison result information, where the comparison result is normal or abnormal.
And the comparison result is normal, which indicates that the detection is normal, and the point location detection is passed.
And the comparison result is abnormal, and the point detection is not passed.
The anomaly classification unit 405 of the service platform server 400 classifies the detected anomalies.
The detection report unit 406 of the service platform server 400 summarizes all the detected result information and outputs a detection report.
The detection report storage unit 407 of the service platform server 400 stores the detection report.
The detection report presenting unit 408 of the service platform server 400 displays the content information of the detection report.
The picture storage unit 409 of the service platform server 400 stores the picture data received by the collected picture receiving unit 402.
The identification result storage unit 410 of the service platform server 400 stores the intelligent analysis identification result data received by the identification result receiving unit 403.
The standard picture library unit 401, the collected picture receiving unit 402, the identification result receiving unit 403, the identification result comparing unit 404, the exception classifying unit 405, the detection reporting unit 406, the detection report storing unit 407, the detection report presenting unit 408, the picture storing unit 409, and the identification result storing unit 410 of the service platform server 400 are described in detail in the functional structure block diagram of the service platform server in the system architecture of the aircraft engine detection system based on machine vision, which is provided in fig. 5, and are not described herein again.
The aircraft engine detection system and method based on machine vision provided by the invention apply the machine vision technology to the delivery detection of aircraft engine production, thereby not only avoiding false detection and missed detection, but also greatly improving the detection efficiency and reducing the detection cost input.
It should be understood that the invention is not limited to the embodiments described above, but that modifications and variations can be made by one skilled in the art in light of the above teachings, and all such modifications and variations are intended to be within the scope of the invention as defined by the appended claims.
Claims (10)
1. A machine vision based aircraft engine inspection system, the system comprising:
the aeroengine equipment is aeroengine equipment to be detected after production;
the multi-axis robot system is used for acquiring picture data of different point positions of the aircraft engine equipment;
the AI algorithm server is used for intelligently analyzing the acquired picture data of different point positions of the aircraft engine and giving an intelligent analysis and identification result;
and the service platform server compares the intelligent analysis and identification result with the pictures in the standard picture library and provides a detection report.
2. The machine-vision-based aeroengine detection system of claim 1, wherein the multi-axis robot system specifically comprises:
a guide rail for providing a track for the multi-axis robot to move;
the 3D industrial camera is used for acquiring relative position information of the aircraft engine and the multi-axis robot and providing positioning navigation information for the multi-axis robot;
the industrial camera is used for acquiring picture data of different point positions of the aircraft engine;
and the multi-axis robot is used for moving on the guide rail, can rotate at multiple degrees of freedom, moves the position of the industrial camera, and controls the industrial camera to acquire picture data of different point positions of the aircraft engine equipment.
3. The machine-vision-based aircraft engine detection system as claimed in claims 1 and 2, wherein the multi-axis robot of the multi-axis robot system specifically comprises:
the motor driving unit is used for driving the multi-axis robot to move on the guide rail;
the coordinate database unit is used for storing coordinate position information of all the image acquisition data points;
the positioning navigation unit is used for acquiring accurate position information of the multi-axis robot in real time;
the position coarse adjustment unit is used for coarse adjusting the position of the mechanical arm;
the position fine adjustment unit is used for finely adjusting the position of the mechanical arm;
the camera shooting control unit is used for controlling the industrial camera to acquire pictures;
the picture coordinate identification unit is used for providing a coordinate identification for the pictures collected in detail in the industry;
and the picture storage and output unit is used for storing the pictures acquired by the industrial camera and outputting the pictures to the AI algorithm server for intelligent analysis and processing.
4. The machine-vision-based aeroengine detection system of claim 1, wherein the AI algorithm server specifically comprises:
the acquisition picture receiving unit is used for receiving picture data sent by the multi-axis robot system;
the acquisition picture classification unit is used for classifying the acquired picture information, and the classification of the picture is classified based on the coordinate information corresponding to the picture and the component types of the detection points;
the picture identification unit is used for intelligently identifying the picture based on different algorithm detection models and outputting an intelligent analysis identification result;
the recognition result unit is used for carrying out data encapsulation on the intelligent analysis recognition results of different algorithm detection models;
the acquisition picture output unit is used for outputting pictures to the service platform server;
and the recognition result output unit is used for outputting the packaged intelligent analysis recognition result data to the service platform server.
5. The machine-vision-based aeroengine detection system of claim 1, wherein the service platform server specifically comprises:
the standard picture library unit is used for storing the normal standard component picture information of the aircraft engine equipment;
the acquisition picture receiving unit is used for receiving picture data sent by the AI algorithm server;
the identification result receiving unit is used for receiving the intelligent analysis identification result data sent by the AI algorithm server;
the identification result comparison unit is used for comparing the received intelligent analysis identification result data with the picture data in the standard picture library and giving comparison result information, wherein the comparison result is normal or abnormal;
an abnormality classification unit for classifying the detected abnormality;
the detection report unit is used for summarizing all detected result information and outputting a detection report;
a detection report storage unit for storing a detection report;
the detection report presenting unit is used for displaying the content information of the detection report;
the picture storage unit is used for storing the received picture data;
and the identification result storage unit is used for storing the received intelligent analysis identification result data.
6. A machine vision based aircraft engine inspection method, the method comprising the steps of:
the multi-axis robot system collects picture data of different point positions of the aircraft engine equipment and sends the picture data to the AI algorithm server;
the AI algorithm server classifies the picture data, intelligently analyzes the picture and outputs an identification result;
the service platform server compares the received identification result with pictures in a standard picture library, and if the detection is normal, the point location detection is passed; and if the point location detection is abnormal, giving abnormal classification, and outputting an overall detection report after all point location detection is finished.
7. The aircraft engine detection method based on machine vision according to claim 6, wherein the multi-axis robot system collects picture data of different point locations of the aircraft engine equipment and sends the picture data to the AI algorithm server, and specifically comprises:
a multi-axis robot of the multi-axis robot system moves on a guide rail of the multi-axis robot system;
the 3D industrial camera of the multi-axis robot system collects the relative position information of the aero-engine and the multi-axis robot in real time and provides positioning navigation information for the multi-axis robot;
the multi-axis robot adjusts the position of the multi-axis robot according to the positioning navigation information;
when the position information of the multi-axis robot is matched with one coordinate position information in a coordinate database unit of the multi-axis robot, the camera shooting control unit of the multi-axis robot controls the industrial camera to acquire picture data of corresponding point positions of the aircraft engine;
and the picture storage and output unit of the multi-axis robot stores the pictures acquired by the industrial camera and outputs the pictures to the AI algorithm server for intelligent analysis and processing.
8. The machine-vision-based aircraft engine detection method according to claim 6, wherein the AI algorithm server classifies picture data and performs intelligent picture recognition, and outputs a recognition result, specifically comprising:
the acquisition picture receiving unit of the AI algorithm server receives picture data sent by the multi-axis robot system;
the image acquisition and classification unit of the AI algorithm server classifies the acquired image information, and the image classification is based on the coordinate information corresponding to the image and the component types of the detection points;
the picture identification unit of the AI algorithm server intelligently identifies the picture based on different algorithm detection models and outputs an intelligent analysis identification result;
the identification result unit of the AI algorithm server performs data encapsulation on the intelligent analysis identification results of different algorithm detection models;
the acquired picture output unit of the AI algorithm server outputs the picture to the service platform server;
and the identification result output unit of the AI algorithm server outputs the packaged intelligent analysis identification result data to the service platform server.
9. The aircraft engine detection method based on machine vision according to claim 6, wherein the service platform server compares the received recognition result with pictures in a standard picture library, and if the detection is normal, the point location detection is passed, specifically comprising:
the identification result receiving unit of the service platform server receives intelligent analysis identification result data sent by the AI algorithm server;
the identification result comparison unit of the service platform server compares the received intelligent analysis identification result data with the picture data in the standard picture library and provides comparison result information, wherein the comparison result is normal or abnormal;
and the comparison result is normal, which indicates that the detection is normal, and the point location detection is passed.
10. The aircraft engine detection method based on machine vision according to claim 6, wherein the service platform server compares the received recognition result with pictures in a standard picture library, if there is an abnormality, an abnormality classification is given, and after all point locations are detected, an overall detection report is output, specifically comprising:
the identification result comparison unit of the service platform server compares the received intelligent analysis identification result data with the picture data in the standard picture library and provides comparison result information, wherein the comparison result is normal or abnormal;
the comparison result is abnormal, and the point location detection is not passed;
the abnormity classification unit of the service platform server classifies the detected abnormity;
the detection report unit of the service platform server summarizes all detected result information and outputs a detection report;
the detection report storage unit of the service platform server stores the detection report;
the detection report presenting unit of the service platform server displays the content information of the detection report;
the picture storage unit of the service platform server stores and collects the picture data received by the picture receiving unit;
and the identification result storage unit of the service platform server stores the intelligent analysis identification result data received by the identification result receiving unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010764138.4A CN111830061A (en) | 2020-08-01 | 2020-08-01 | Aeroengine detection system and method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010764138.4A CN111830061A (en) | 2020-08-01 | 2020-08-01 | Aeroengine detection system and method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111830061A true CN111830061A (en) | 2020-10-27 |
Family
ID=72919274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010764138.4A Pending CN111830061A (en) | 2020-08-01 | 2020-08-01 | Aeroengine detection system and method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111830061A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113049600A (en) * | 2021-03-31 | 2021-06-29 | 上汽通用五菱汽车股份有限公司 | Engine part wrong and neglected loading detection method and system based on visual detection |
| CN113192134A (en) * | 2021-04-16 | 2021-07-30 | 北京航空航天大学 | Method for positioning and detecting deviation of clamp of aircraft engine |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104655643A (en) * | 2015-02-12 | 2015-05-27 | 天津理工大学 | Quality detection system for surface welding process of electronic devices |
| CN204924181U (en) * | 2015-08-21 | 2015-12-30 | 中国第一汽车股份有限公司 | Engine main shaft tile assembly quality check out test set |
| CN106226325A (en) * | 2016-07-22 | 2016-12-14 | 广东工业大学 | A kind of seat surface defect detecting system based on machine vision and method thereof |
| CN107389686A (en) * | 2017-06-08 | 2017-11-24 | 深圳市智能机器人研究院 | A kind of detection robot system and its detection method for locomotive bottom |
| CN107478205A (en) * | 2017-09-01 | 2017-12-15 | 西北工业大学 | Aero-engine high accuracy assembly quality detector device people's system |
| CN107576503A (en) * | 2017-09-01 | 2018-01-12 | 西北工业大学 | Aero-engine high accuracy assembly quality detector device people's system |
| CN107677678A (en) * | 2017-09-20 | 2018-02-09 | 广州视源电子科技股份有限公司 | appearance detection method and device based on automatic path planning |
| CN209296602U (en) * | 2018-12-21 | 2019-08-23 | 成都云之澳科技有限公司 | Aeroengine Smart detection system |
-
2020
- 2020-08-01 CN CN202010764138.4A patent/CN111830061A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104655643A (en) * | 2015-02-12 | 2015-05-27 | 天津理工大学 | Quality detection system for surface welding process of electronic devices |
| CN204924181U (en) * | 2015-08-21 | 2015-12-30 | 中国第一汽车股份有限公司 | Engine main shaft tile assembly quality check out test set |
| CN106226325A (en) * | 2016-07-22 | 2016-12-14 | 广东工业大学 | A kind of seat surface defect detecting system based on machine vision and method thereof |
| CN107389686A (en) * | 2017-06-08 | 2017-11-24 | 深圳市智能机器人研究院 | A kind of detection robot system and its detection method for locomotive bottom |
| CN107478205A (en) * | 2017-09-01 | 2017-12-15 | 西北工业大学 | Aero-engine high accuracy assembly quality detector device people's system |
| CN107576503A (en) * | 2017-09-01 | 2018-01-12 | 西北工业大学 | Aero-engine high accuracy assembly quality detector device people's system |
| CN107677678A (en) * | 2017-09-20 | 2018-02-09 | 广州视源电子科技股份有限公司 | appearance detection method and device based on automatic path planning |
| CN209296602U (en) * | 2018-12-21 | 2019-08-23 | 成都云之澳科技有限公司 | Aeroengine Smart detection system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113049600A (en) * | 2021-03-31 | 2021-06-29 | 上汽通用五菱汽车股份有限公司 | Engine part wrong and neglected loading detection method and system based on visual detection |
| CN113192134A (en) * | 2021-04-16 | 2021-07-30 | 北京航空航天大学 | Method for positioning and detecting deviation of clamp of aircraft engine |
| CN113192134B (en) * | 2021-04-16 | 2022-11-22 | 北京航空航天大学 | Method for positioning and detecting deviation of clamp of aircraft engine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102579783B1 (en) | Vision inspection system by using remote learning of product defects image | |
| US20210390678A1 (en) | Method for monitoring manufacture of assembly units | |
| US6266138B1 (en) | System and method for detecting defects in a surface of a workpiece | |
| Chauhan et al. | Fault detection and classification in automated assembly machines using machine vision | |
| US20130057678A1 (en) | Inspection system and method of defect detection on specular surfaces | |
| CN111830061A (en) | Aeroengine detection system and method based on machine vision | |
| CN113822840A (en) | Vehicle bottom inspection system and method | |
| CN115290668B (en) | System and method for detecting defects of finish paint of coated car body | |
| CN113361539A (en) | Instrument reading method and device of underground inspection robot and electronic equipment | |
| US20230053085A1 (en) | Part inspection system having generative training model | |
| WO2021151412A1 (en) | Apparatus and method for automatically detecting damage to vehicles | |
| CN113504239B (en) | Quality control data analysis method | |
| WO1999016010A1 (en) | Automated visual inspection system and process for detecting and classifying defects | |
| KR102523195B1 (en) | Fusion vision inspection system for applied automobile sealer inspection | |
| US11378520B2 (en) | Auto focus function for vision inspection system | |
| CN113240798B (en) | Intelligent material integrity detection and configuration method based on digital twinning and AR | |
| CN116678348B (en) | Method and device for detecting missing parts of whole diesel engine | |
| CN111389750B (en) | Vision measurement system and measurement method | |
| CN113758926A (en) | Product assembling machine with vision inspection station | |
| US20230237636A1 (en) | Vision inspection system for defect detection | |
| KR102527061B1 (en) | Manufacturing intelligence service system connected to MES in smart factory | |
| CN113927217A (en) | Intelligent welding system | |
| JP2018105728A (en) | Device and method for visually inspecting harness holding member | |
| CN112601007A (en) | Image acquisition method and device for characteristic region | |
| CN112444283A (en) | Detection apparatus for vehicle assembly and vehicle assembly production system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201027 |
|
| WD01 | Invention patent application deemed withdrawn after publication |