CN116718600B - Detection device for intelligent detection of wire harness product - Google Patents
Detection device for intelligent detection of wire harness product Download PDFInfo
- Publication number
- CN116718600B CN116718600B CN202310683214.2A CN202310683214A CN116718600B CN 116718600 B CN116718600 B CN 116718600B CN 202310683214 A CN202310683214 A CN 202310683214A CN 116718600 B CN116718600 B CN 116718600B
- Authority
- CN
- China
- Prior art keywords
- detection
- wire harness
- image
- product
- color
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 250
- 238000000034 method Methods 0.000 claims abstract description 77
- 230000008569 process Effects 0.000 claims abstract description 73
- 230000007547 defect Effects 0.000 claims abstract description 50
- 238000012797 qualification Methods 0.000 claims abstract description 15
- 238000004088 simulation Methods 0.000 claims description 75
- 238000012360 testing method Methods 0.000 claims description 53
- 238000000605 extraction Methods 0.000 claims description 35
- 238000012795 verification Methods 0.000 claims description 26
- 238000005070 sampling Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000013142 basic testing Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000009413 insulation Methods 0.000 abstract description 6
- 230000000007 visual effect Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 230000002950 deficient Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000002893 slag Substances 0.000 description 4
- 238000003466 welding Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical group [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009975 flexible effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method 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
- 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/14—Quality control systems
- G07C3/143—Finished product quality control
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Automation & Control Theory (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a detection device for intelligently detecting wire harness products, which comprises: the wire harness identification tag is arranged on the wire harness product to be tested and used for representing the product batch number of the wire harness product to be tested and the number of the wire harness product in the product batch number; the wire harness identity recognition detection gun is used for carrying out identity recognition on a wire harness identity recognition tag arranged on a wire harness product to be detected and sending a recognition result to the detection table; the detection table can determine a detection data packet matched with the product batch number, generate a corresponding operation process based on the detection data packet, and perform product qualification detection and mechanical arm on the to-be-detected beam product based on the operation process; the invention can not only avoid the defect of leakage error detection caused by manual operation to the maximum extent and reduce the experience requirement for operators, but also can timely find and remove unqualified failure products such as poor contact disconnection, poor instantaneous disconnection insulation short circuit, wrong assembly and wrong wiring.
Description
Technical Field
The invention relates to the technical field of wire harness detection, in particular to an intelligent detection system for wire harness products.
Background
The main function of the wire harness (circuit group) is to connect a series of plug connectors, insulating materials, circuit boards and other electronic elements together to form a complete connecting wire end, and the application of the wire harness product relates to various aspects of daily work and life of people at present, such as manufacturing and using various scenes of automobiles, household appliances, computers and other electronic products, so the quality and reliability of the wire harness also indirectly influence the performance and service life of the product, and the detection and evaluation of the wire harness product are particularly important.
The wire harness test is to test wiring components, insulation wrapping materials and the like for connecting various electrical equipment in a circuit to find out possible problems, so that the wire harness is ensured to be safely and reliably used, strict process screening and supplementary screening are required to be carried out on the wire harness production line or before the wire harness is used by a user according to product standards, so that unqualified and invalid products such as poor contact disconnection, poor instantaneous insulation short circuit, wrong assembly and wrong wiring are timely found out and removed, and further wire harness products meeting design requirements are screened out for application.
However, the existing wire harness detection has the problems of low speed, low efficiency and easy fatigue of workers, and is easy to cause false detection and missing detection, and the main reasons are found out, firstly, because a plurality of units cannot record detection data related to a plurality of detection processes of each wire harness product in time when the wire harness detection is produced or used, and the problems of false recording and missing recording are also easy to occur in the recording process, secondly, the detection is still carried out by using a manual means, besides the inherent problems that the false detection or missing detection is easy to cause due to the fact that the manual means are easy to fatigue, higher requirements are also put forward for manual individuals on the wire harness product types and detection requirements, and new individuals cannot quickly and accurately determine detection procedures and corresponding qualified parameters required by the wire harness of the type.
In summary, the existing detection technology has low accuracy, unreliable quality and high cost, and cannot meet the requirements of high efficiency and instantaneity of mass production and detection of wire harnesses.
Disclosure of Invention
Based on the above, in order to solve the defects existing in the prior art, a detection device for intelligently detecting a wire harness product is specifically provided.
A detection apparatus for intelligent detection of a wire harness product, comprising:
The wire harness identification tag is arranged on the wire harness product to be tested and used for representing the product batch number of the wire harness product to be tested and the number of the wire harness product in the product batch number; the product lot number comprises a total number A of product numbers and a user identification code; the user identification code includes: basic test information of the wire harness type and test information of the wire harness use environment required by a user;
the wire harness identity recognition detection gun is provided with a display screen and is used for carrying out identity recognition on a wire harness identity recognition tag arranged on a wire harness product to be detected, and sending the obtained product batch number and the number of the wire harness product in the product batch number to a detection table;
the detection table can determine a detection data packet matched with the product batch number according to the obtained product batch number, generate a corresponding operation process based on the detection data packet, and perform product qualification detection on the wire harness product to be detected, which is conveyed to the detection area, based on the operation process;
and the manipulator is controlled by the detection table and picks up the test product from the detection area of the detection table and places the test product to a specified position after receiving the pick-up notification.
Optionally, in one embodiment, the detection platform includes a workbench assembly, an image acquisition unit, a detection controller, and a display unit;
The workbench assembly is used for providing a detection area for detecting the qualified products of the wire harness products to be detected;
the image acquisition unit is used for sampling image information of the wire harness product to be detected entering the detection area so as to acquire a sampling image of the wire harness product to be detected;
the detection controller is used for determining a detection data packet matched with the product batch number according to the obtained product batch number, and generating a corresponding defect detection operation process based on the detection data packet; meanwhile, the detection controller can also provide a parallel simulation detection environment for the defect detection operation process based on the detection data packet, extract image features and identify defects of the sampling image based on the parallel simulation detection environment so as to complete a product qualification detection process, and output a detection result to a display unit for display.
Optionally, in one embodiment, the detection controller includes: simulating a master controller and a network controller;
the simulation main controller is used for determining a detection data packet matched with the product batch number according to the obtained product batch number, and generating a corresponding defect detection operation process based on the detection data packet; meanwhile, image feature extraction and defect recognition are carried out on the sampling images based on each parallel simulation detection environment so as to finish the product qualification detection process, and detection results are output to a display unit for display; the detection data packet is provided with a detection data type list, the detection data type list is used for representing detection items corresponding to product batch numbers matched with wire harness products to be detected, and each detection item corresponds to one wire harness detection type;
The network controller is configured to configure a required number of parallel simulation detection environments for the defect detection operation process based on the detection data packet, where the number of simulation detection environments is determined according to the number of detection types included in the detection data type list.
Optionally, in one embodiment, the detection item includes, but is not limited to, cable appearance information, cable size information, and wiring information, where the wiring information includes wiring color information and plug connector model information.
Alternatively, in one of the embodiments,
the simulation main controller sets an image processing strategy, and performs image feature extraction and defect recognition on the sampled image based on each parallel simulation detection environment through the image processing strategy to complete a product qualification detection process, wherein the image processing strategy specifically comprises the following steps:
firstly, carrying out image preprocessing on the sampling image;
secondly, carrying out image key region segmentation on the preprocessed image and forming a plurality of key region segmentation patterns, wherein the image key regions are set according to corresponding detection items, and comprise cable appearance image key regions, single cable size image key regions, wiring color image key regions and two-end plug-in connector image key regions;
Thirdly, calling the corresponding simulation verification process packages based on the detection data type list, and extracting image features and identifying defects of the segmentation patterns of each key region in parallel under each simulation detection environment; the simulation verification process packet is preset in a database of the simulation main controller, and the wire harness detection type in the detection data type list is used as a calling query condition.
Optionally, in one embodiment, the list of detection data types further includes environmental test items including, but not limited to, a wire harness temperature resistance test item, a wire harness moisture resistance test item, and a wire harness vibration resistance test item.
Optionally, in one embodiment, the database of the simulation master controller presets an environment test item simulation verification process packet to perform environment test simulation on the to-be-tested cable bundle product under a simulation detection environment configured by the network controller and give an evaluation result.
Optionally, in one embodiment, the simulation verification process packet corresponding to the detection item has a first cis-position execution authority, and the environment test item simulation verification process packet has a second cis-position execution authority, that is, the simulation main controller starts to execute the environment test item simulation verification process after the sampling image is subjected to image feature extraction and defect identification.
Optionally, in one embodiment, the wire harness identification tag is in a two-dimensional code tag form.
The implementation of the embodiment of the invention has the following beneficial effects:
the invention can not only avoid the defect of leakage error detection caused by manual operation to the maximum extent, reduce the experience requirement for operators, and timely find and remove unqualified and invalid products such as bad contact disconnection, bad instantaneous insulation short circuit, wrong assembly and wrong wiring.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Wherein:
FIG. 1 is a block diagram of a module structure according to the present invention;
FIG. 2 is a structural frame diagram of an embodiment of a detection stage according to the present invention;
FIG. 3 is a diagram showing a specific operation execution profile of the inspection station according to the present invention;
in the figure: 1. a wire feed Pi Daizu; 2. a photoelectric sensor; 3. a light source; 4. a camera of an industrial camera; 5. a detection controller; 6. an industrial personal computer; 7. a display unit; 8. a good product placement area; 9. and a manipulator.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. It will be understood that the terms first, second, etc. as used herein may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present application. Both the first element and the second element are elements, but they are not the same element.
In recent years, various novel wire harness detectors are developed in succession abroad, and corresponding detection tools are matched, so that the basic use requirement of wire harness detection can be met, but the product has a defect, the detection of the wire harness product is only based on the basic detection of the existing product, the manual participation degree is high, and the problems described in the prior art are unavoidable, so that a novel intelligent detection system is required to be designed.
In this embodiment, as shown in fig. 1 to 3, a detection device for performing intelligent detection on a wire harness product is specifically provided, and the detection device is characterized by comprising:
the wire harness identification tag is arranged on the wire harness product to be tested and used for representing the product batch number of the wire harness product to be tested and the number of the wire harness product in the product batch number; the product lot number comprises a total number A of product numbers and a user identification code; the user identification code includes: the basic test information of the wire harness type required by the user can be added with the test information of the wire harness use environment according to the use test requirement;
the wire harness identity recognition detection gun is provided with a display screen for displaying recognition information in real time, is arranged on the inspector side (or can be arranged on the scanning gun at the inlet formed at the feeding end side of the detection table for automatic scanning) and is used for carrying out identity recognition on a wire harness identity recognition tag arranged on a wire harness product to be detected and sending the obtained product batch number and the number of the wire harness product in the product batch number to the detection table;
the detection table can determine a detection data packet matched with the product batch number according to the obtained product batch number, generate a corresponding operation process based on the detection data packet, and perform product qualification detection on the wire harness product to be detected, which is conveyed to the detection area, based on the operation process;
And the manipulator 9 is controlled by the detection table, and picks up the test product from the detection area of the detection table and places the test product to a specified position after receiving the pick-up notification.
Based on the above technical content, the system described in this document firstly configures a wire harness identification tag for the wire harness product to be tested to describe the corresponding user product test requirement, the detection station uses the information recorded by the wire harness identification tag to form the relevant process and test information of the test, the machine is used as an active information release main body, the manual participation is changed into a passive execution main body, and the defects of manual participation (such as omission problem and experience requirement problem) are eliminated; secondly, besides the conventional test steps, the system also carries out a parallel synchronous defect detection process of a plurality of detection items through a simulation verification process of setting line parallelism, and the detection efficiency and the detection precision are submitted. And finally, notifying the manipulator to execute the pick-up operation, so as to realize the full-automatic test process.
In some specific embodiments, the wire harness identification tag is disposed on the wire harness product to be tested and is used for representing a product batch number of the wire harness product to be tested and a number of the wire harness product in the product batch number; preferably, the wire harness identification tag is in a two-dimensional code tag form, and an identification code endowed to each product in a two-dimensional code tag form is used for realizing the correspondence of one article and one code, each product can be endowed with unique identification information through coding software to represent the test requirement required by a user, and meanwhile, after detection is finished, the wire harness identification tag can also be subjected to secondary verification or rechecking at any time, so that the possibility of scurrying is effectively prevented. Optionally, the harness identification tag may also be in the form of a bar code tag.
In a more specific embodiment, the two-dimensional code tag records the product lot number of the wire harness product to be tested and the number I (I&1 ～ 100 The product lot number comprising a total number of product numbers a (this lot amounts to 100 products being detected) and a user identification code (9501234); the user identification code is an automobile wire harness product produced by a certain user B company in the systemCode information of the batch corresponding to the wire harness for the main power line, the code information is taken as an identification symbol, and the code is taken as an identification mark to call, extract and record the basic test information of the wire harness type of the wire harness (and/or the wire harness use environment test information), namely 9501234 actually represents a user name B company, a wire harness code for the wire harness use-the main power line, a wire harness type basic test information code required by a user, a wire harness use environment test information code and the like, wherein the code information comprises but is not limited to single cable appearance information (such as breakage and stain or not), single cable size information (such as the model corresponding to the wire harness for the main power line, namely the wire specification-the nominal section and the like), the total number of cables and wiring information; preferably, the wiring information includes wiring color information (such as black is dedicated to the bonding wire, red is used for the power wire, and whether a misconnection problem exists is primarily judged through color) and plug connector model information (whether the installed plug connector has a misconnection problem is determined according to the wire harness application corresponding to the user identification code, if the plug connector is used for connecting the wire harnesses, the plug connector needs to be connected by adopting a connector, and a connecting connector or a wire lug is used for connecting the wire harnesses and the electrical components);
In some specific embodiments, the wire harness identification detection gun is arranged on the inspector side and is provided with a color display screen, the wire harness identification detection gun is used for identifying the wire harness identification label arranged on the wire harness product to be detected, and the obtained product batch number and the number (the configuration number can be used for better automatic statistics of the detection progress, the statistical product qualification rate and the like) of the wire harness product in the product batch number are sent to the holder server (real-time communication is carried out with the detection controller) so that the holder server can conveniently carry out subsequent analysis and statistics operations. In a more specific embodiment, the two-dimensional code and the bar code intelligent detection software are preset in the wire harness identity recognition detection gun so as to accurately recognize, record and display detection results of the wire harness identity recognition tag, and log-in registration management can be performed at the same time, so that the identity of a inspector currently performing detection operation can be conveniently recognized; and the result of each detection is recorded in a table.
In some specific embodiments, the detection platform mainly includes a hardware module and a software system design, where the hardware module is mainly responsible for collecting images, the software system is mounted on a high-performance control chip and is mainly responsible for image processing, and the two are mutually matched to cooperatively complete a defect vision detection task, that is, the main functions of the detection platform are three basic functions of image acquisition, image processing and defective product classification, as shown in fig. 3, the image acquisition unit acquires a detected image, and the image processing acquires detected image features by a specific processing model of multiple parallel operations of the detection controller to determine whether a product is qualified; sorting operation is completed by the manipulator in the classification of defective products.
Specific:
the detection platform comprises a workbench assembly, an image acquisition unit, a detection controller and a display unit;
the workbench assembly is used for providing a detection area for detecting the qualified products of the wire harness products to be detected;
the image acquisition unit is used for sampling image information of the wire harness product to be detected entering the detection area so as to acquire a sampling image of the wire harness product to be detected;
the detection controller is used for determining a detection data packet matched with the product batch number according to the obtained product batch number, and generating a corresponding defect detection operation process based on the detection data packet; meanwhile, the detection controller can also provide a parallel simulation detection environment for the defect detection operation process based on the detection data packet, extract image features and identify defects of the sampling image based on the parallel simulation detection environment so as to complete a product qualification detection process, and output a detection result to the display unit 7 for display.
In some specific embodiments, the table assembly comprises a wire feeding belt set 1, a table; the wire feeding belt group 1 is provided with a plurality of wire feeding belts so as to convey each wire harness product to be tested to a detection area one by one; the workbench is provided with 3 areas, mainly comprising a detection area, a good product area, namely a good product placement area 8 and a defective product area, and the manipulator 9 is used for completing the selecting operation.
In some specific embodiments, the image acquisition unit comprises a light source 3 and an industrial camera; the camera 4 of the industrial camera can be used for clearly imaging by a 300-ten-thousand-pixel camera with macro magnification shooting, and the automatic recognition time is less than 0.5S. Meanwhile, a voice alarm module can be arranged to automatically report the recognition result through voice. In order to highlight key characteristics such as cable edges, boundaries and flaws of the wire harness to be tested, the light source adopts an annular light source lamp band to avoid noise influence on image sampling as much as possible because of uneven light distribution, and the annular light source has the advantages of stable performance and long service life, and the annular light source is used for irradiating an object to be tested to avoid dark shadows in an irradiation area, so that the imaging characteristics can be better highlighted, and the imaging can be uniform and soft by matching with a proper color plate.
Preferably, the photoelectric sensor 2 can be used for accurately sensing whether the wire harness product to be measured reaches a specified detection area or not, if the photoelectric sensor detects that the wire harness product to be measured reaches a preset position, station information is sent to a camera controller of the industrial camera, the camera controller forms a control signal, and the camera is controlled to acquire an image of the wire harness product to be measured.
In some specific embodiments, the detection controller 5 includes: simulating a master controller and a network controller;
the simulation main controller is used for determining a detection data packet matched with the product batch number according to the obtained product batch number, and generating a corresponding defect detection operation process based on the detection data packet; meanwhile, image feature extraction and defect recognition are carried out on the sampling images based on each parallel simulation detection environment so as to finish the product qualification detection process, and detection results are output to a display unit for display; the detection data packet is provided with a detection data type list, the detection data type list is used for representing detection items corresponding to product batch numbers matched with wire harness products to be detected, and each detection item corresponds to one wire harness detection type; the detection items comprise, but are not limited to, cable appearance information, cable size information and wiring information, wherein the wiring information comprises wiring color information and plug connector model information;
the network controller is configured to configure a required number of parallel simulation detection environments for the defect detection operation process based on the detection data packet, where the number of simulation detection environments is determined according to the number of detection types included in the detection data type list.
Based on the above scheme, the simulation main controller should set an image processing policy, and perform image feature extraction and defect recognition on the sampled image based on each parallel simulation detection environment through the image processing policy to complete a product qualification detection process, where the image processing policy specifically includes:
firstly, carrying out image preprocessing on the sampling image; because of the influence of external environmental factors such as industrial environment, image transmission and the like, the acquired image is inevitably noisy, and image preprocessing such as filtering (image median filtering) is needed to reduce interference and highlight image characteristics, so that the edge information of each key area is better acquired for edge segmentation, and the edge profile of the target is more prominent.
Secondly, carrying out image key region segmentation on the preprocessed image and forming a plurality of key region segmentation patterns, wherein the image key regions are set according to corresponding detection items, and comprise cable appearance image key regions, single cable size image key regions, wiring color image key regions and two-end plug-in connector image key regions; preferentially, for the same frame of sampled image, the same image segmentation algorithm can be used for acquiring a key region segmentation pattern, such as an ROI extraction algorithm, and an interested target (such as the appearance of a plug-in connector) is separated from a background block (other region) to generate the key region segmentation pattern, or different algorithms can be selected for different key region types, such as an edge detection algorithm is adopted for a cable size image, and the ROI extraction algorithm is adopted for a cable appearance image key region; setting according to specific use scenes;
Thirdly, calling the corresponding simulation verification process packages based on the detection data type list, and extracting image features and identifying defects of the segmentation patterns of each key region in parallel under each simulation detection environment; the simulation verification process packet is preset in a database of the simulation main controller, and the wire harness detection type in the detection data type list is used as a calling query condition.
Preferably, the image feature extraction and identification of the cable appearance image, the image feature extraction and identification of the single cable size image, the image feature extraction and identification of the wiring color image and the image feature extraction and identification of the appearance of the two-end connectors are all performed by adopting a machine vision algorithm.
Preferably, the image feature extraction and recognition processing of the cable appearance image is carried out by presetting a cluster recognition model in a simulation verification process packet corresponding to the image feature extraction and recognition processing, and the specific process is that the defect edge of the cable appearance image or the area with unclean foreign matters exist and the surrounding non-defect cable surface have larger gray level difference, so that the defect feature is more effectively highlighted in the image processing process, the self-adaptive filtering processing is carried out by the following formula, namely, firstly, the variation coefficient CV (i) is set, and the structural area and the flat area of the cable appearance image are divided by the constant variation coefficient CV (i);
Wherein Ω i Represents a square neighborhood of fixed size centered on i, SD (Ω i )、Ave(Ω i ) Respectively representing standard deviation and mean value of pixel gray scale in the adjacent domain; the structural region here is a defective region including local features such as a large number of textures, and has a sharp change in pixel gradation, SD (Ω) i ) The CV (i) is larger, whereas the flat area is a non-defective cable surface area, the gray distribution is relatively uniform, SD (Ω) i ) Smaller CV (i) is also smaller;
setting a corresponding adaptive filter window N, and correspondingly setting as
Wherein SR is the structural area of the image; USR is the flat region; finally, subtracting the image processed by the adaptive filter window from the background image to obtain a differential image F (in the differential image F, almost all high gray level parts are structural areas, namely defect areas, and the low gray level parts are flat areas, namely non-defect areas)
F＝|P-Q|
Therefore, the self-adaptive threshold value is set, so that the position of the suspected defect can be determined from the obtained differential image, and the identification result of whether the defect exists in the appearance or not can be given.
Preferably, the image feature extraction and recognition processing of the cable size image is carried out by a preset size recognition model in a corresponding simulation verification process packet, and the specific process is that the model can adopt the existing SOBEL edge detection model or the Hough transformation circle detection model to carry out size recognition and compare and analyze with a set threshold.
Preferably, the method comprises extracting and identifying image features of the wiring color image, and carrying out image feature extraction and identification processing on the wiring color image by a preset color identification model in a corresponding simulation verification process packet
The basic principle of wiring color identification is to compare the RGB average of the colors of the cable under test with the reference color values of the various cables in the standard color library. However, due to the reasons of non-absolute uniformity of ambient illumination, differences of reflected light rays at different positions of the cable, and the like, imaging at different positions of the same color cable is obviously different, and therefore, the recognition process of the color recognition model is as follows:
converting the color image of the key region division pattern (denoted as f (x, y)) into a gray scale image denoted as g (x, y), and obtaining a binary image g b (x,y)；
T is a given threshold, such as 240;
for binary image g b (x, y) performing connected domain analysis (such as reserving connected region with area larger than threshold to remove small noise) to obtain binary image g C (x, y); mask areas identified by the colors of the wires at the corresponding positions of the subsequent images;
for binary image g C (x, y) performing expansion treatment (adopting rectangular structural elements), and obtaining a graph g according to the standard number N of cables of the wire harness to be tested and N communicating areas with the largest reserved area N (x,y)；g N Each communicating region of (x, y) is the position of each wire;
for g N Each of the connected domains of (x, y) is determined g C An average value of R, G, B three channels of corresponding pixels in f (x, y) for all pixels in (x, y) that are foreground; and comparing the color values with reference color values of various cables in a preset standard color library, wherein if the color value of any cable exceeds a threshold value, the defect exists.
Preferably, the standard color library has a corresponding standard color threshold data set for each wire harness model, and the creating process includes:
creating a plurality of color sample data sets for the cable color picture of each wire harness model, wherein the color samples are the cable color pictures of each wire harness model which are shot in a certain time period; converting each cable color picture into a gray image; feature extraction is carried out according to feature information contained in the gray level image:
creating and training a feature extractor;
the feature extractor formula is:
wherein F is ij Representing the extraction result of the jth color feature in the ith gray-scale image pattern, I ij (t) represents the value of the jth feature in the gray image pattern at time t, μ ij Sum sigma ij Respectively represent theMean and standard deviation, k, of features in the critical region ij Is a preset chromaticity parameter value;
such as characteristic value sequence I ij (T) a time range of 0 to T, the feature having an average value of μ in the gray scale image ij =10, standard deviation σ ij =2, shape parameter k ij =3, the formula changes to
The identification performance evaluation of the feature extractor can be performed by reserving the extractor if the feature extractor is qualified, otherwise, the sample selection and the model creation are performed again, wherein the evaluation formula is that
Wherein D is ij A defect recognition result indicating a j-th color feature in the i-th pattern,representing the corresponding color feature extraction result in the nth detected data type, < >>A pass threshold representing the color feature, +.>N is the number of color types, which is the weight. Let us assume that we have two color types red and blue, corresponding feature extraction results +.>And->Qualification threshold->And->Weight->And->Let->
Through D ij The current recognition effect may be determined.
Preferably, the image feature extraction and recognition processing are respectively carried out on the image of the plug-in connector appearance by the preset recognition model in the corresponding simulation verification process packet, and the specific process is that
Because of the flexible effect of the cable and because the color of the core wire is similar to the possible color of the connector terminal, the image sample image of the connector at two ends (the image is not distinguished from the target image and the background image when being segmented at the previous stage, namely the background image is possibly included), the image can not be directly subjected to feature extraction, and the image is required to be preprocessed again, and the specific flow steps comprise:
S1, extracting a region of interest: since the gray level of the image is already finished (the data amount of the original image is reduced) and the filtering treatment, such as median filtering (the image noise is effectively removed and the image edge of the plug-in unit is protected) is carried out in the previous stage of segmentation, the process mainly involves the edge detection and contour extraction process, preferably, the Canny operator is adopted to carry out edge detection and contour extraction on the image so as to extract all the contour areas possibly being plug-in units, namely plug-in units, the key of the step is to set proper threshold values, and experiments find that the upper limit and the lower limit of the threshold values are preferably between 0.2 and 0.5 respectively;
s2, a first feature extraction process: because Hough detection has the characteristics of insensitivity to noise, high algorithm efficiency and the like, the connectors with different shapes can be quickly and effectively subjected to preliminary classification, and therefore, the electric connector images are subjected to geometric pre-classification by combining a Hough transformation method;
s3, a second feature extraction process: because the core problem of image feature extraction is robustness and distinguishability, and the characteristics of various plug-in connector models and similar appearance are combined, the SIFT feature extraction method is adopted to extract the features of the image processed by the S2 so as to obtain corresponding SIFT features and cluster the SIFT features into corresponding feature matrixes, namely, a visual feature word bag model is constructed by adopting a clustering method, and the features of the image are converted into visual words so as to facilitate the following specific steps of classifying and identifying the image, wherein the specific steps comprise:
Constructing a pre-classified image set;
extracting SIFT features of all images, determining the number S of visual words, and constructing a vocabulary table based on a K-means clustering algorithm; the extracted N plug-in component image features form visual words through clustering and construct a vocabulary containing K words, and each image is described by the K visual words;
the SIFT feature points are replaced by word approximation in a vocabulary table, namely, each image is expressed as a numerical vector of K dimensions;
constructing a visual vocabulary histogram based on each image and normalizing to obtain an image feature matrix M1, and carrying out classification recognition through an SVM model to output classification results, so that model recognition of the plug-in connector is automatically completed by using a computer instead of an assembly worker; the number of times of each word in each image is counted, a visual vocabulary histogram is built and normalized, the numerical vectors of all the images form a characteristic matrix M of the images, the matrix is a matrix of N rows and K columns, the rows of the matrix represent plug-in connector images, and the columns represent corresponding characteristic vectors.
In some specific embodiments, the detection controller further includes an industrial personal computer 6, where the industrial personal computer is used to control and adjust the sampling position and the sampling angle of the camera in real time; meanwhile, the camera is arranged on the annular track, and the small turntable controlled by the industrial personal computer drives the camera to change the sampling position.
In some specific embodiments, the list of detection data types further includes environmental test items including, but not limited to, a wire harness temperature resistance test item, a wire harness moisture resistance test item, and a wire harness vibration resistance test item; the wire harness use environment test information belongs to user customization information, and the same wire harness product has different environment conditions when facing different user use demands, so that the wire harness use environment test needs to be different from person to person, including but not limited to wire harness temperature resistance information, wire harness humidity resistance information and wire harness vibration resistance information. Meanwhile, heat aging resistance information of the wire harness, oil resistance information of the wire harness and the like can be considered.
In some specific embodiments, the database of the simulation master controller presets an environment test item simulation verification process packet to perform environment test simulation on the to-be-tested cable bundle product under the simulation detection environment configured by the network controller and give an evaluation result. Namely, the detection platform can also provide independent simulation test environments for the environment simulation test subprocesses generated by the simulation verification process based on the digital twin technology, so that the detection period is shortened; the simulation test subprocess at least comprises a wire harness temperature resistance simulation test program, a wire harness moisture resistance simulation test program and a wire harness vibration resistance simulation test program. Historical data in the wire harness experiment process is analyzed through a cloud twin system, a plurality of twin simulation models capable of judging the real state of the wire harness physical model are generated, synchronous classification simulation of wire harnesses in different running states is rapidly achieved, and defects in wire harness materials, structures and the like under the environment given by a user are timely found.
In some specific embodiments, the simulation verification process packet corresponding to the detection item has a first order execution authority, and the environment test item simulation verification process packet has a second order execution authority, that is, the simulation main controller starts to execute the environment test item simulation verification process after the sampling image is subjected to image feature extraction and defect identification.
In some specific embodiments, the wire harness is subject to breaking if the connection between the power transmission line of the wire harness and the wire harness terminal is not tight enough, and the wire harness is subject to performance test because the wire harness is subject to functional failure due to poor contact of tin slag or wire harness caused by tin slag or connector in the process of disconnection of an internal copper core from the wire connection terminal or the wire harness in spite of the intact appearance of the power transmission line of the wire harness; namely, the basic test information of the wire harness type required by a user also comprises performance information, wherein the performance information comprises but is not limited to wire harness tension information (if the connection between a transmission line and a wire harness terminal is not tight enough, the phenomenon of wire harness breakage occurs, meanwhile, the appearance of the transmission line of the wire harness is good, but an internal copper core is disconnected from a wiring terminal, and both the situations can lead to the functional failure of an automobile line), wire harness internal defect information (the process defect of a welding spot in the wire harness, such as missing welding, the short circuit of the wire harness can be directly caused by the defect of tin slag and the like) and wire harness electrical performance information (rated voltage, rated current, temperature rise, contact resistance, insulation resistance, electric resistance strength, current circulation resistance and the like are selected according to actual requirements); the corresponding device can be integrated with a plurality of detection instruments, and the detection instruments can be an automobile wire harness tensile force tester, an automobile wire harness X-ray detector and an automobile wire harness touch tester or a comprehensive wire harness detection instrument so as to obtain wire harness performance information. Preferably, the wire harness tensile tester can be used for configuring measuring devices such as a digital display industrial personal computer, a dial push-pull gauge, a clamp and the like. The automobile wire harness X-ray detector and the automobile wire harness touch tester can use a wire harness conduction test board, are provided with a data comparison analysis program, an automatic recording test report, intelligent test software (an automobile wire harness touch test and wire harness X-ray detection program), a large database and other programs, and visually observe the process defects of welding spots inside the wire harness such as missing welding, tin slag and the like through wire harness X-ray detection. In addition to the above detection, the harness continuity test stand can also detect internal electrical properties of the harness, and general detection items include continuity, resistance, insulation, withstand voltage, and the like.
Furthermore, the detection instrument can be used for carrying out complete production detection network with the controller of the detection platform, such as combining field bus industrial Ethernet technology and IO hard contact signal interaction, so as to realize the control of each controller/detection instrument. If the industrial RJ45 interface network cable is used for connecting all communication devices in the whole network through the switch, the IP address is set, all the communication devices are set to be the same network segment, and full online is realized.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (5)
1. A detection apparatus for intelligent detection of a wire harness product, comprising:
the wire harness identification tag is arranged on the wire harness product to be tested and used for representing the product batch number of the wire harness product to be tested and the number of the wire harness product in the product batch number; the product lot number comprises a total number A of product numbers and a user identification code; the user identification code includes: basic test information of the wire harness type required by a user;
The wire harness identity recognition detection gun is provided with a display screen and is used for carrying out identity recognition on a wire harness identity recognition tag arranged on a wire harness product to be detected, and sending the obtained product batch number and the number of the wire harness product in the product batch number to a detection table;
the detection table can determine a detection data packet matched with the product batch number according to the obtained product batch number, generate a corresponding operation process based on the detection data packet, and perform product qualification detection on the wire harness product to be detected, which is conveyed to the detection area, based on the operation process;
the manipulator is controlled by the detection table, and picks up the test product from the detection area of the detection table and places the test product to a designated position after receiving a pick-up notification;
the detection platform comprises a workbench assembly, an image acquisition unit, a detection controller and a display unit;
the workbench assembly is used for providing a detection area for detecting the qualified products of the wire harness products to be detected;
the image acquisition unit is used for sampling image information of the wire harness product to be detected entering the detection area so as to acquire a sampling image of the wire harness product to be detected;
the detection controller is used for determining a detection data packet matched with the product batch number according to the obtained product batch number, and generating a corresponding defect detection operation process based on the detection data packet; meanwhile, the detection controller can also provide a parallel simulation detection environment for the defect detection operation process based on the detection data packet, extract image features and identify defects of the sampling image based on the parallel simulation detection environment so as to complete a product qualification detection process, and output a detection result to a display unit for display;
The detection controller includes: simulating a master controller and a network controller;
the simulation main controller is used for determining a detection data packet matched with the product batch number according to the obtained product batch number, and generating a corresponding defect detection operation process based on the detection data packet; meanwhile, image feature extraction and defect recognition are carried out on the sampling images based on each parallel simulation detection environment so as to finish the product qualification detection process, and detection results are output to a display unit for display; the detection data packet is provided with a detection data type list, the detection data type list is used for representing detection items corresponding to product batch numbers matched with wire harness products to be detected, and each detection item corresponds to one wire harness detection type;
the network controller is used for configuring the required number of parallel simulation detection environments for the defect detection operation process based on the detection data packet, and the number of the simulation detection environments is determined according to the number of detection types contained in the detection data type list;
the detection items comprise, but are not limited to, cable appearance information, cable size information and wiring information, wherein the wiring information comprises wiring color information and plug connector model information;
The simulation main controller sets an image processing strategy, and performs image feature extraction and defect recognition on the sampled image based on each parallel simulation detection environment through the image processing strategy to complete a product qualification detection process, wherein the image processing strategy specifically comprises the following steps:
firstly, carrying out image preprocessing on the sampling image;
secondly, carrying out image key region segmentation on the preprocessed image and forming a plurality of key region segmentation patterns, wherein the image key regions are set according to corresponding detection items, and comprise cable appearance image key regions, single cable size image key regions, wiring color image key regions and two-end plug-in connector image key regions;
thirdly, calling the corresponding simulation verification process packages based on the detection data type list, and extracting image features and identifying defects of the segmentation patterns of each key region in parallel under each simulation detection environment; the simulation verification process packet is preset in a database of the simulation main controller, and the wire harness detection type in the detection data type list is used as a calling query condition; the method comprises the steps of extracting image features of a wiring color image, identifying a preset color identification model in a corresponding simulation verification process packet, and carrying out image feature extraction and identification processing on the wiring color image, wherein the specific process is as follows
Converting the color image f (x, y) of the key region division pattern into a gray scale image, denoted as g (x, y), and obtaining a binary image g b (x,y)；
T is a given threshold;
for binary image g b (x, y) performing connected domain analysis to obtain a binary image g C (x,y)；
For binary image g C (x, y) performing expansion treatment, and obtaining a graph g according to the standard number N of cables of the wire harness to be tested and N communicating areas with the largest reserved area N (x,y)；g N Each communicating region of (x, y) is the position of each wire;
for g N Each of the connected domains of (x, y) is determined g C An average value of R, G, B three channels of corresponding pixels in f (x, y) for all pixels in (x, y) that are foreground; comparing the color values with reference color values of various cables in a preset standard color library, wherein if the color value of any cable exceeds a threshold value, the defect exists; the standard color library is provided with corresponding standard color threshold data sets for each wire harness model, and the creation process comprises the following steps:
creating a plurality of color sample data sets for the cable color picture of each wire harness model, wherein the color samples are the cable color pictures of each wire harness model which are shot in a certain time period; converting each cable color picture into a gray image; feature extraction is carried out according to feature information contained in the gray level image: creating and training a feature extractor;
The feature extractor formula is:
wherein F is ij Representing the extraction result of the jth color feature in the ith gray-scale image pattern, feature value sequence I ij (t) represents the value of the jth feature in the gray image pattern at time t, μ ij Sum sigma ij Respectively represent the mean and standard deviation, k, of the feature in the critical region ij Is a preset chromaticity parameter value; the time range is from 0 to T,
the identification performance evaluation of the feature extractor is carried out by the following formula, if the feature extractor is qualified, the extractor is reserved, otherwise, the sample selection and the model creation are carried out again, and the evaluation formula is that
Wherein D is ij A defect recognition result indicating a j-th color feature in the i-th pattern,representing the corresponding color feature extraction result in the nth detected data type, < >>A pass threshold representing the color feature, +.>N is the number of color types and is the weight; i.e. through D ij The current recognition effect is determined.
2. The detecting device for intelligent detection of wire harness products according to claim 1, wherein,
the list of detection data types also includes environmental test items including, but not limited to, a wire harness temperature resistance test item, a wire harness moisture resistance test item, and a wire harness vibration resistance test item.
3. The detecting device for intelligent detection of wire harness products according to claim 2, wherein,
and presetting an environment test item simulation verification process package in a database of the simulation main controller so as to perform environment test simulation on the to-be-tested cable bundle product under a simulation detection environment configured by the network controller and give an evaluation result.
4. The detecting device for intelligent detection of a wire harness product according to claim 3, wherein,
the simulation verification process package corresponding to the detection item has a first order execution authority, and the environment test item simulation verification process package has a second order execution authority, namely, the simulation main controller starts to execute the environment test item simulation verification process after the sampling image is subjected to image feature extraction and defect identification.
5. The detecting device for intelligent detection of wire harness products according to claim 1, wherein,
the wire harness identification tag is in a two-dimensional code tag form.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310683214.2A CN116718600B (en) | 2023-06-09 | 2023-06-09 | Detection device for intelligent detection of wire harness product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310683214.2A CN116718600B (en) | 2023-06-09 | 2023-06-09 | Detection device for intelligent detection of wire harness product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116718600A CN116718600A (en) | 2023-09-08 |
| CN116718600B true CN116718600B (en) | 2024-03-29 |
Family
ID=87865472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310683214.2A Active CN116718600B (en) | 2023-06-09 | 2023-06-09 | Detection device for intelligent detection of wire harness product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116718600B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117368223B (en) * | 2023-10-10 | 2024-04-26 | 广州君华检测认证有限公司 | Machine vision-based automobile wire harness quality detection method and system |
| CN117665221B (en) * | 2024-02-01 | 2024-05-24 | 江苏镨赛精工科技有限公司 | Performance detection method and system for composite material product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007144986A1 (en) * | 2006-06-12 | 2007-12-21 | Sumitomo Wiring Systems, Ltd. | Device and method for inspecting external appearance of wire harness |
| CN102297867A (en) * | 2011-07-20 | 2011-12-28 | 上海元一电子有限公司 | Detection system for assembly quality of wiring harness |
| CN112964723A (en) * | 2021-02-01 | 2021-06-15 | 苏州百迈半导体技术有限公司 | Double-sided multi-target equal-spacing array visual detection method and detection system |
| CN214334702U (en) * | 2020-12-23 | 2021-10-01 | 苏州斯穹精密科技有限公司 | Intelligent wire harness appearance recognition device based on visual detection |
-
2023
- 2023-06-09 CN CN202310683214.2A patent/CN116718600B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007144986A1 (en) * | 2006-06-12 | 2007-12-21 | Sumitomo Wiring Systems, Ltd. | Device and method for inspecting external appearance of wire harness |
| CN102297867A (en) * | 2011-07-20 | 2011-12-28 | 上海元一电子有限公司 | Detection system for assembly quality of wiring harness |
| CN214334702U (en) * | 2020-12-23 | 2021-10-01 | 苏州斯穹精密科技有限公司 | Intelligent wire harness appearance recognition device based on visual detection |
| CN112964723A (en) * | 2021-02-01 | 2021-06-15 | 苏州百迈半导体技术有限公司 | Double-sided multi-target equal-spacing array visual detection method and detection system |
Non-Patent Citations (1)
| Title |
|---|
| 张相胜等.基于机器视觉的汽车线束压接缺陷检测系统.仪表技术与传感器.2020,(第3期),第73-77页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116718600A (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116718600B (en) | Detection device for intelligent detection of wire harness product | |
| US7127099B2 (en) | Image searching defect detector | |
| US11657599B2 (en) | Method for detecting appearance of six sides of chip multi-layer ceramic capacitor based on artificial intelligence | |
| KR102378186B1 (en) | Artificial intelligence vision inspection system for wiring harness | |
| JP5168215B2 (en) | Appearance inspection device | |
| CN117172624B (en) | Intelligent monitoring management system of wire harness production line | |
| CN109870463B (en) | Electronic chip fault detection device | |
| CN107895362A (en) | A kind of machine vision method of miniature binding post quality testing | |
| CN113996556B (en) | Cloud-integrated product sorting system and method | |
| CN115170497A (en) | PCBA online detection platform based on AI visual detection technology | |
| CN116626542B (en) | Intelligent detection system of wire harness product | |
| Londe et al. | Automatic PCB defects detection and classification using MATLAB | |
| CN111307817B (en) | Online detection method and system for PCB production process of intelligent production line | |
| Suhasini et al. | PCB defect detection using image subtraction algorithm | |
| Jarvis | Visual inspection automation | |
| CN116993725B (en) | Intelligent patch information processing system of flexible circuit board | |
| CN113327237A (en) | Visual detection system suitable for power supply circuit board | |
| CN105548210B (en) | The detection method of American Standard power extending line based on machine vision | |
| CN116993654B (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN114782431B (en) | Printed circuit board defect detection model training method and defect detection method | |
| CN116245810A (en) | Flat cable welding point defect detection method, equipment, storage medium and device | |
| CN112598632B (en) | Appearance detection method and device for contact piece of crimping connector | |
| Supriya et al. | Automatic Optical Inspection System for wiring harness using Computer Vision | |
| JP7423368B2 (en) | Defect detection device and method | |
| CN213749668U (en) | Appearance testing device for flexible circuit board |
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 |