CN107389689B - AOI management system and management method for defect detection - Google Patents
AOI management system and management method for defect detection Download PDFInfo
- Publication number
- CN107389689B CN107389689B CN201710618222.3A CN201710618222A CN107389689B CN 107389689 B CN107389689 B CN 107389689B CN 201710618222 A CN201710618222 A CN 201710618222A CN 107389689 B CN107389689 B CN 107389689B
- Authority
- CN
- China
- Prior art keywords
- aoi
- server
- detection
- defect detection
- image
- 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
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
- G01N21/8851—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
- 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
- G06T7/0008—Industrial image inspection checking presence/absence
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biochemistry (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an AOI management system and a management method for defect detection, wherein the management system comprises an AOI defect detection work station, a line image storage library, a line server and a remote AOI server; a user can configure a plurality of AOI defect detection work stations and a linear image storage library on each production line according to requirements; a line server can be communicated with AOI defect detection stations and line image storage libraries on a plurality of production lines; one remote AOI server can communicate with the line servers in a plurality of production factories; the line body server and the remote AOI server can verify the adjusted image processing algorithm under the condition of not influencing the normal production of a production line; the remote AOI server can synchronously update the AOI software version of each AOI defect detection work station and remotely monitor the running state of each AOI defect detection work station. The AOI management system and the management method provided by the invention can avoid the situation of product defect leak detection to the greatest extent and keep good product defect detection rate on the premise of not influencing production line production.
Description
Technical Field
The invention belongs to the technical field of optical automatic defect detection, and particularly relates to an AOI management system and method for defect detection.
Background
The automatic optical inspection (aoi) refers to acquiring an image of an object to be inspected by using an optical imaging technology (usually using a camera and a lens), and acquiring information such as the size, position, direction, spectral characteristics, structure, defects and the like of the object from the captured image by using a certain image processing algorithm, so that tasks such as inspection of products, identification and positioning of parts on an assembly line, measurement in process monitoring, process control feedback, classification, grouping and the like can be performed. At present, AOI is widely applied to various industries such as semiconductors, industrial robots, automobile part manufacturing, printing, steel, medical treatment, medicine and the like.
The AOI system for detecting the defects mainly detects the defects of products and then classifies and judges the defects according to the industry standard. However, the defect detection AOI system widely used at present still has the following defects:
1. for different models of products, different defects of the same product have different image processing algorithms. Aiming at the conditions of missing detection and over-detection of product defects in the production process, the processing algorithm is often required to be adjusted, whether the adjusted image processing algorithm is proper or not can only be verified and readjusted in the subsequent production process at present, the processing efficiency is low, the normal production of the product can be influenced, and the production efficiency is reduced;
2. for some product defects detected through leakage detection, special research and development personnel are often required to analyze and adjust an image processing algorithm according to original product images, and the images obtained from a production field often have the conditions of unclear defect position identification and unclear defect types, so that great influence is caused on defect analysis, and the processing efficiency is further influenced;
3. for the production line leading in the defect detection AOI system, because the number of the production lines and the defect detection work stations is large, when the version of the AOI system is updated in an iteration mode, each device can only be updated manually, manpower is consumed, and the production efficiency of the production line is greatly influenced.
Disclosure of Invention
In view of the above drawbacks or needs for improvement in the prior art, the present invention provides an AOI management system and management method for defect detection, which can synchronously update software versions of all AOI systems; the product image stored at the line body end can be obtained in real time, and the adjusted image processing algorithm is quickly verified and readjusted without influencing the normal production of a production line; the running state of the AOI system and the production condition of a production line can be remotely monitored, and abnormal conditions can be timely found.
To achieve the above object, according to one aspect of the present invention, there is provided an AOI management system for defect inspection, comprising an AOI server, and a line volume image repository and at least one AOI defect inspection station arranged on at least one production line and in communication with the AOI server;
the AOI defect detection work station is used for collecting product images and detecting the defects of the products according to the collected product images;
the line image storage library is connected with the AOI defect detection work stations on the production line where the line image storage library is located and is used for storing product images collected by the AOI defect detection work stations;
the AOI server is used for adjusting the image processing algorithm to carry out defect detection on the products which are subjected to over-detection or missing detection in the AOI defect detection work station, and updating the image processing algorithm when the products are not subjected to over-detection or missing detection to the AOI defect detection work station.
Preferably, in the AOI management system, the AOI server includes line servers respectively installed in a plurality of production plants, and one line server can communicate with at least one line image repository and at least one AOI defect detection station on at least one production line in the production plant; and a remote AOI server in communication with each of the linear servers;
the line body server is used for adjusting an image processing algorithm to carry out defect detection on products which are subjected to over-detection or missing detection in the AOI defect detection work station, and updating the image processing algorithm when no over-detection or missing detection exists to the AOI defect detection work station;
the remote AOI server is used for adjusting an image processing algorithm to carry out defect detection on products which are subjected to over-detection or under-detection by the line body server, and updating the image processing algorithm when the products are not subjected to over-detection or under-detection to the line body server and the AOI defect detection work station.
Preferably, in the AOI management system, the AOI defect inspection station includes an external device control unit, an image acquisition unit, a first image processing unit, and a first inspection result output unit, which are connected in sequence;
the external equipment control unit is connected with the line body server and used for controlling production line equipment enabling the AOI defect detection station to normally operate; the online server updates the AOI software version of the AOI defect detection station through an external equipment control unit;
the first image processing unit is used for carrying out image processing on the acquired product image according to a preset image processing algorithm so as to detect the product defect; the defect detection result is output through the first detection result output unit.
Preferably, in the AOI management system, the line server includes an image uploading unit, a line server management unit, and a first image reading unit, a second image processing unit, and a second detection result output unit, which are connected in sequence;
the first image reading unit is connected with the line body image storage bank and used for reading product images in the line body image storage bank, the second image processing unit carries out image processing on the read product images according to a preset image processing algorithm so as to detect product defects, and the second image processing unit of the line body server integrates the image processing algorithms of the first image processing units of all AOI defect detection stations in a factory area where the line body server is located; outputting the defect detection result through a second detection result output unit;
the image uploading unit is used for uploading the product images in the line body image storage to a remote AOI server;
and the line body server management unit is used for synchronously updating the AOI software version sent by the remote AOI server to each AOI defect detection work station.
Preferably, in the AOI management system, the remote AOI server includes a linear management unit, and an image server, a remote image repository, a second image reading unit, a third image processing unit, and a third detection result output unit, which are sequentially connected to each other;
the image server is connected with the image uploading unit of the line body server and used for receiving the product images uploaded by the line body server and storing the product images in the remote image storage library, the second image reading unit is used for reading the product images in the remote image storage library, the third image processing unit carries out image processing on the read product images according to a preset image processing algorithm so as to detect product defects, and the third image processing unit of the remote AOI server integrates the image processing algorithms of the second image processing units of all line body servers; outputting the defect detection result through a third detection result output unit;
and the line body management unit is connected with a line body server management unit of the line body server and is used for sending the AOI software version to be updated to the line body server.
Preferably, in the AOI management system, the remote AOI server further includes a line monitoring unit, and the line monitoring unit is connected to the line management unit and to a line server management unit of the line server; and the line body server management unit sends the running state of each AOI defect detection work station to the line body monitoring unit, and the remote AOI server remotely monitors the running state of each AOI defect detection work station through the line body monitoring unit.
According to another aspect of the present invention, there is provided a management method of an AOI management system for defect detection, including the steps of:
(1) performing defect detection on the product by the AOI defect detection station according to the acquired product image, and storing the product image to a line image repository;
(2) comparing the defect detection result with the result of the pre-detection, and judging whether over-detection and missing-detection exist; if no over-detection and no missing detection exist, judging that the image processing algorithm of the AOI defect detection station is optimal; if the over-detection or the omission detection exists, entering the step (3);
(3) adjusting an image processing algorithm of an AOI server, carrying out defect detection on a product by the AOI server according to a product image in a linear image storage bank, comparing a defect detection result with a defect detection result of an AOI defect detection station, and judging whether over-detection and missing-detection exist or not; if the product is over-inspected or under-inspected, adjusting an image processing algorithm of the AOI server and carrying out defect detection on the product again by the AOI server until no over-inspection or under-inspection exists;
(4) and judging that the image processing algorithm of the AOI server is optimal when no over-inspection and missing inspection exist, and updating the image processing algorithm to the AOI defect detection work station.
Preferably, step (3) in the above management method includes the following substeps:
(3.1) adjusting an image processing algorithm of a line body server in the AOI server, carrying out defect detection on a product by the line body server according to a product image in a line body image storage bank, comparing a defect detection result with a detection result of an AOI defect detection station, and judging whether over-detection and missing-detection exist or not; if no over-detection and no missing detection exist, entering the step (4); if the over-detection or the omission detection exists, the step (3.2) is carried out;
(3.2) generating a defect report containing information of the defect position and the defect type of the product according to the over-inspected or the missed-inspected product image, and uploading and storing the over-inspected or missed-inspected product image to a remote AOI server;
(3.3) adjusting an image processing algorithm of a remote AOI server in the AOI server, carrying out defect detection on the product by the remote AOI server according to the stored product image, and comparing the defect detection result with the defect report in the step (3.2) to judge whether over-detection and missing detection exist;
and (3.4) repeating the step (3.3) until no overdetection or omission occurs.
Preferably, step (2) in the management method further includes the following steps: and uploading the result of the pre-detection to an AOI defect detection work station, and automatically comparing the defect detection result with the result of the pre-detection by the AOI defect detection work station to judge whether the leak detection exists or not.
Preferably, in the step (3.2) of the management method, the product images are classified according to the product category, the production line, the station and the defect type, and then stored in the remote image repository of the remote AOI server.
Preferably, the management method further includes the steps that the remote AOI server sends the AOI software version to be updated to the line body server, and the line body server synchronously updates the AOI software versions of the AOI defect detection stations.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
(1) according to the AOI management system and method for defect detection, provided by the invention, aiming at the leakage detection in the product defect detection, the image processing algorithm can be adjusted in real time through the line body server under the condition of not influencing the normal production of a production line, and the adjusted image processing algorithm is verified efficiently;
(2) the invention provides an AOI management system and method for defect detection.A remote AOI server acquires a product image stored at a line body end in real time through a line body server, and stores the product image subjected to leak detection in a remote image storage library after marking the position and type of a defect; the image processing algorithm can be adjusted and quickly verified by the remote AOI server under the condition of not influencing production line production; the remote image repository is convenient for research personnel to further analyze and perfect the image processing algorithm;
(3) according to the AOI management system and method for defect detection, provided by the invention, the software versions of all AOI systems can be synchronously updated through the remote AOI server, so that repeated and inefficient work of personnel is reduced;
(4) the AOI management system and the AOI management method for defect detection provided by the invention can remotely monitor the running state of the AOI defect detection work station and the production condition of a production line through the remote AOI server and find abnormal conditions in time.
Drawings
FIG. 1 is a schematic diagram of a component structure of an AOI management system for defect detection according to an embodiment of the present invention;
fig. 2 is a connection block diagram of an AOI management system for defect detection according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1, an embodiment of the present invention provides an AOI management system for defect detection, including: the system comprises an AOI defect detection station, a line body image storage library, a line body server and a remote AOI server.
A user configures N (N is a natural number greater than 1) production lines according to production requirements, each production line is configured with a plurality of AOI defect detection stations and a line body image storage library according to product defect detection requirements, one line body server can match the AOI defect detection stations and the line body image storage libraries on the N production lines, and one remote AOI server can match N (N is a natural number greater than 1) line body servers in a production plant area;
the AOI defect detection work station collects product images, carries out defect detection on the products according to the collected product images and outputs a product defect detection result; wherein; the AOI defect detection station 1, the AOI defect detection station 2 and the AOI defect detection station … can be respectively used for detecting the same type or different types of defects of products;
the line body image storage library is used for storing product images acquired by all AOI defect detection work stations on the production line where the line body image storage library is located;
the line body server reads a product image in the line body image storage bank to perform defect detection on an inspected or missed product of the AOI defect detection station; uploading the over-inspected or missed-inspected product images in the linear image repository to a remote AOI server, and updating the AOI software versions of all AOI defect inspection work stations synchronously;
the remote AOI server receives the product images uploaded by the line server and stores the product images in a remote image storage library, and the product images in the remote image storage library are read to perform defect detection on products which are over-inspected or under-inspected by the line server; and the AOI software version to be updated is sent to the online server.
FIG. 2 is a connection block diagram of an AOI management system for defect detection according to an embodiment of the present invention;
in this embodiment, the AOI defect detection station includes an external device control unit, an image acquisition unit, a first image processing unit, and a first detection result output unit, which are connected in sequence;
the external equipment control unit is connected with the line body server and used for controlling production line equipment, such as a Programmable Logic Controller (PLC), a motor, a light source, a mechanical arm and the like, which enables the AOI defect detection station to normally operate; the external equipment control unit sends the AOI software version and the running state of the AOI defect detection work station to a remote AOI server through a line body server, and the line body server updates the AOI software version of the AOI defect detection work station through the external equipment control unit;
the image acquisition unit is connected with the line body image storage library, is used for acquiring a product image and storing the product image in the line body image storage library, and mainly shoots the product image through a camera and a lens; the first image processing unit carries out image processing on the acquired product image according to a preset image processing algorithm so as to detect the product defects; aiming at different types of defects of different products, different image processing algorithms need to be preset by a worker; the first detection result output unit outputs an excel report of the product defect detection result;
the line server comprises an image uploading unit, a line server management unit, a first image reading unit, a second image processing unit and a second detection result output unit which are sequentially connected;
the first image reading unit is connected with the line body image storage, and is used for reading the product images in the line body image storage and reading the product images in the time period according to the time period set by a user; the second image processing unit carries out image processing on the read product image according to a preset image processing algorithm to detect the product defects, and the second image processing unit of the line server integrates the image processing algorithms of the first image processing units of all AOI defect detection work stations in the factory area where the second image processing unit is located; the second detection result output unit is the same as the first detection result output unit of the AOI defect detection work station and is used for outputting an excel report of the product defect detection result;
the first end of the image uploading unit is connected with the linear image repository, the second end of the image uploading unit is connected with the remote AOI server, and the image uploading unit is used for uploading the over-inspected or under-inspected product images in the linear image repository to the remote AOI server;
the first end of the line server management unit is connected with an external equipment control unit of the AOI defect detection work station, the second end of the line server management unit is connected with the remote AOI server, and the line server management unit is used for sending the AOI software version and the running state of the AOI defect detection work station to the remote AOI server and synchronously updating the AOI software version sent by the remote AOI server to each AOI defect detection work station.
The remote AOI server comprises a line management unit and a line monitoring unit which are connected with each other, and an image server, a remote image storage library, a second image reading unit, a third image processing unit and a third detection result output unit which are connected with each other in sequence;
the image server is connected with the image uploading unit of the line server and used for receiving the product image which is uploaded by the line server and subjected to leak detection, classifying the product image according to the product type, the production line, the station and the defect type and storing the product image in the remote image storage library; the second image reading unit reads the product image in the remote image repository, and the third image processing unit performs image processing on the read product image according to a preset image processing algorithm to detect the product defect; the third image processing unit of the remote AOI server integrates the image processing algorithm of the second image processing unit of each linear server; the third detection result output unit is the same as the second detection result output unit of the line body server and is used for outputting an excel report of the product defect detection result;
and the line body management unit is connected with a line body server management unit of the line body server and is used for sending the AOI software version to be updated to the line body server.
The line body monitoring unit is connected with a line body server management unit of the line body server, the line body server management unit sends the running state of each AOI defect detection work station to the line body monitoring unit, and the remote AOI server remotely monitors the running state of each AOI defect detection work station through the line body monitoring unit.
The embodiment of the invention provides a management method of an AOI management system for defect detection, which comprises the following steps:
(1) the AOI defect detection work station acquires a product image, performs defect detection on the product by using a preset image processing algorithm, and outputs a defect detection result; and the collected product image is stored in a line body image storage bank on the line body,
(2) the AOI defect detection station automatically compares the defect detection result with the manual detection result to judge whether over-detection and missing-detection occur; if no over-inspection and no missing inspection exist, determining that the image processing algorithm of the AOI defect detection work station is optimal; if the over-detection or the omission detection exists, entering the step (3);
(3) adjusting an image processing algorithm in a line body server, reading an over-inspected or missing-inspected product image in a line body image storage bank by the line body server, carrying out defect detection on the product by using the adjusted image processing algorithm, and comparing a defect detection result with a defect detection result of an AOI defect detection station to judge whether the over-inspection or the missing-inspection exists; if no over-inspection and no missing inspection exist, the adjusted image processing algorithm is judged to be optimal, and the image processing algorithm is updated to the corresponding AOI defect detection work station through the line body server; if the over-detection or the omission detection exists, entering the step (4);
(4) establishing an excel defect report containing information such as product defect positions, defect types and the like according to the over-inspected or under-inspected product images, uploading the over-inspected or under-inspected product images to a remote AOI server through an image uploading unit of a linear server, receiving and classifying the product images according to the product types, the production lines, the stations and the defect types by an image server in the remote AOI server, and storing the product images in a remote image storage library;
(5) the research and development personnel analyze the over-inspected or missed-inspected product images at the remote AOI server side, adjust the image processing algorithm of the remote AOI server, read the corresponding product images in the remote image storage library by the remote AOI server, detect the defects of the products, and compare the defect detection results with the excel defect report form in the step (4) to judge whether the over-inspected or missed-inspected product still exists;
(6) and (5) repeating the step (5) until no detection and missing detection condition occurs, determining that the adjusted image processing algorithm is optimal, sending the image processing algorithm to the line body server through the remote AOI server, and updating the image processing algorithm to the corresponding AOI defect detection work station through the line body server.
The AOI management method for defect detection provided by the embodiment of the invention further comprises the following steps in the step (2): and uploading the result of manual detection to an AOI defect detection work station in advance, automatically comparing the result of defect detection output by a first detection result output unit of the AOI defect detection work station with the result of manual detection, and judging whether over-detection and missing detection exist.
The AOI management method for defect detection further comprises the steps of sending the AOI software version to be updated to the line body server through the remote AOI server, and synchronously updating the AOI software version of each AOI defect detection work station through the line body server.
The remote AOI server remotely monitors the software version, the production running state and the faults of each AOI defect detection station of each wire body in real time through the wire body monitoring unit.
Compared with the existing AOI system, the AOI management system for defect detection provided by the invention can adjust the image processing algorithm aiming at the defects of the over-detected or missed-detected product in real time, verify and readjust the adjusted image processing algorithm under the condition of not influencing the normal production of a production line, and optimize the image processing algorithm; the software version of the AOI system of each AOI defect detection work station can be updated remotely and synchronously, and repeated inefficient work of personnel is reduced; the running state of each AOI defect detection work station can be remotely monitored, and abnormal conditions can be timely found.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. An AOI management system for defect detection is characterized by comprising an AOI server, a line image storage library and at least one AOI defect detection station, wherein the line image storage library and the AOI defect detection station are arranged on at least one production line and are in communication with the AOI server;
the AOI defect detection work station is used for collecting product images and detecting the defects of the products according to the collected product images;
the line image storage library is connected with the AOI defect detection work stations on the production line where the line image storage library is located and is used for storing product images collected by the AOI defect detection work stations;
the AOI server is used for adjusting the image processing algorithm to carry out defect detection on the products which are subjected to over-detection or under-detection in the AOI defect detection work station, and updating the image processing algorithm when the products are not subjected to over-detection or under-detection to the AOI defect detection work station in real time.
2. The AOI management system of claim 1, wherein the AOI servers comprise a linellae server respectively disposed within a plurality of production plants, one linellae server being in communication with a linellae image repository and at least one AOI defect detection station on at least one production line within the production plant; and a remote AOI server in communication with each of the linear servers;
the line body server is used for adjusting an image processing algorithm to carry out defect detection on products which are subjected to over-detection or missing detection in the AOI defect detection work station, and updating the image processing algorithm when no over-detection or missing detection exists to the AOI defect detection work station;
the remote AOI server is used for adjusting an image processing algorithm to carry out defect detection on products which are subjected to over-detection or under-detection by the line body server, and updating the image processing algorithm when the products are not subjected to over-detection or under-detection to the line body server and the AOI defect detection work station.
3. The AOI management system according to claim 2, wherein the linear server includes an image uploading unit, a linear server management unit, and a first image reading unit, a second image processing unit, and a second detection result output unit connected in sequence;
the first image reading unit is connected with the line body image storage bank and used for reading the product images in the line body image storage bank, and the second image processing unit carries out image processing on the read product images according to a preset image processing algorithm so as to detect product defects; the second image processing unit of the line body server integrates the image processing algorithm of the first image processing unit of each AOI defect detection station in the factory area where the second image processing unit is located; the defect detection result is output through the second detection result output unit;
the image uploading unit is used for uploading the product images in the line body image storage to a remote AOI server;
and the line body server management unit is used for synchronously updating the AOI software version sent by the remote AOI server to each AOI defect detection work station.
4. The AOI management system according to claim 3, wherein the remote AOI server includes a wire management unit, and an image server, a remote image repository, a second image reading unit, a third image processing unit and a third detection result output unit, which are connected in sequence;
the image server is connected with the image uploading unit of the line server and used for receiving the product images uploaded by the line server and storing the product images in the remote image repository, the second image reading unit is used for reading the product images in the remote image repository, and the third image processing unit is used for carrying out image processing on the read product images according to a preset image processing algorithm so as to detect product defects; the third image processing unit of the remote AOI server integrates the image processing algorithm of the second image processing unit of each linear server; the defect detection result is output through the third detection result output unit;
and the line body management unit is connected with a line body server management unit of the line body server and is used for sending the AOI software version to the line body server.
5. The AOI management system of claim 4, wherein the remote AOI server further comprises a wire-tie monitoring unit connected to the wire-tie management unit and to a wire-tie server management unit of a wire-tie server; and the line body server management unit sends the running state of each AOI defect detection work station to the line body monitoring unit, and the remote AOI server remotely monitors the running state of each AOI defect detection work station through the line body monitoring unit.
6. A management method of an AOI management system for defect inspection according to any of claims 1 to 5, comprising the steps of:
(1) performing defect detection on the product by the AOI defect detection station according to the acquired product image, and storing the product image to a line image repository;
(2) comparing the defect detection result with the result of the pre-detection, and judging whether over-detection and missing-detection exist; if no over-detection and no missing detection exist, judging that the image processing algorithm of the AOI defect detection station is optimal; if the over-detection or the omission detection exists, entering the step (3);
(3) adjusting an image processing algorithm of an AOI server, carrying out defect detection on a product by the AOI server according to a product image in a linear image storage bank, comparing a defect detection result with a defect detection result of an AOI defect detection station, and judging whether over-detection and missing-detection exist or not; if the product is over-inspected or under-inspected, adjusting an image processing algorithm of the AOI server and carrying out defect detection on the product again by the AOI server until no over-inspection or under-inspection exists;
(4) and judging that the image processing algorithm of the AOI server is optimal when no over-inspection and missing inspection exist, and updating the optimal image processing algorithm to the AOI defect detection work station in real time.
7. The management method according to claim 6, wherein the step (3) comprises the sub-steps of:
(3.1) adjusting an image processing algorithm of a line body server in the AOI server, carrying out defect detection on a product by the line body server according to a product image in a line body image storage bank, comparing a defect detection result with a detection result of an AOI defect detection station, and judging whether over-detection and missing-detection exist or not; if no over-detection and no missing detection exist, entering the step (4); if the over-detection or the omission detection exists, the step (3.2) is carried out;
(3.2) generating a defect report containing information of the defect position and the defect type of the product according to the over-inspected or the missed-inspected product image, and uploading and storing the over-inspected or missed-inspected product image to a remote AOI server;
(3.3) adjusting an image processing algorithm of a remote AOI server in the AOI server, carrying out defect detection on the product by the remote AOI server according to the stored product image, and comparing the defect detection result with the defect report in the step (3.2) to judge whether over-detection and missing detection exist;
and (3.4) repeating the step (3.3) until no overdetection or omission occurs.
8. The management method according to claim 7, wherein the step (2) further comprises the steps of: and uploading the result of the pre-detection to an AOI defect detection work station, and automatically comparing the defect detection result with the result of the pre-detection by the AOI defect detection work station so as to judge whether the over-detection and the omission detection exist.
9. The management method according to claim 8, wherein in step (3.2), the product images are sorted according to product category, production line, station and defect type and then stored in a remote image repository of the remote AOI server.
10. The management method according to claim 9, further comprising the steps that the remote AOI server sends the AOI software version to be updated to the wire body server, and the AOI software version of each AOI defect detection station is updated synchronously through the wire body server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710618222.3A CN107389689B (en) | 2017-07-26 | 2017-07-26 | AOI management system and management method for defect detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710618222.3A CN107389689B (en) | 2017-07-26 | 2017-07-26 | AOI management system and management method for defect detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107389689A CN107389689A (en) | 2017-11-24 |
| CN107389689B true CN107389689B (en) | 2020-05-22 |
Family
ID=60341674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710618222.3A Active CN107389689B (en) | 2017-07-26 | 2017-07-26 | AOI management system and management method for defect detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107389689B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107979649B (en) * | 2017-12-15 | 2021-01-12 | 武汉精测电子集团股份有限公司 | AOI multi-line multi-station system and method based on Inline server |
| CN108827970B (en) * | 2018-03-28 | 2021-09-03 | 武汉精测电子集团股份有限公司 | AOI system-based method and system for automatically judging defects of different panels |
| CN108594484B (en) * | 2018-04-19 | 2022-11-11 | 武汉精测电子集团股份有限公司 | Panel detection and repair integrated system |
| CN108710655A (en) * | 2018-05-10 | 2018-10-26 | 武汉精测电子集团股份有限公司 | A kind of AOI based on database crosses missing inspection information analysis method and system |
| CN108931529B (en) * | 2018-05-10 | 2020-12-22 | 深圳市盛波光电科技有限公司 | Yield estimation method for continuously producing roll-shaped materials |
| CN109101398A (en) * | 2018-08-10 | 2018-12-28 | 武汉精测电子集团股份有限公司 | AOI wire body monitoring method and system |
| CN109633937A (en) * | 2018-12-10 | 2019-04-16 | 武汉精立电子技术有限公司 | It is a kind of to sentence system again online |
| CN110597198B (en) * | 2019-08-30 | 2023-12-01 | 彩虹显示器件股份有限公司 | Quality control device, quality control system and quality control method for TFT substrate glass |
| CN110458840B (en) * | 2019-10-12 | 2020-01-14 | 武汉精立电子技术有限公司 | Method, system and terminal equipment for reducing panel defect over-detection rate |
| CN110767564A (en) * | 2019-10-28 | 2020-02-07 | 苏师大半导体材料与设备研究院(邳州)有限公司 | Wafer detection method |
| CN110989422A (en) * | 2019-11-13 | 2020-04-10 | 深圳市盛波光电科技有限公司 | Management system and management method for AOI (automated optical inspection) over-inspection parameters based on serial number code spraying |
| CN112730434B (en) * | 2020-12-26 | 2021-10-29 | 深圳市磐锋精密技术有限公司 | Data monitoring method applied to AOI detection |
| CN113591589B (en) * | 2021-07-02 | 2022-09-27 | 北京百度网讯科技有限公司 | Product missing detection identification method and device, electronic equipment and storage medium |
| CN117576102A (en) * | 2024-01-17 | 2024-02-20 | 长春汽车工业高等专科学校 | Automobile defect detection method and system based on reflection spectrum |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005079154A2 (en) * | 2004-02-19 | 2005-09-01 | Camtek Ltd. | A method and a system for real-time defects verification |
| CN101461063A (en) * | 2006-08-01 | 2009-06-17 | 株式会社岛津制作所 | Substrate inspection and repair device, and substrate evaluation system |
| CN101477066A (en) * | 2009-01-09 | 2009-07-08 | 华南理工大学 | Circuit board element mounting/welding quality detection method and system based on super-resolution image reconstruction |
| CN103411974A (en) * | 2013-07-10 | 2013-11-27 | 杭州赤霄科技有限公司 | Cloud big data-based planar material detection remote system and cloud big data-based planar material detection method |
-
2017
- 2017-07-26 CN CN201710618222.3A patent/CN107389689B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005079154A2 (en) * | 2004-02-19 | 2005-09-01 | Camtek Ltd. | A method and a system for real-time defects verification |
| CN101461063A (en) * | 2006-08-01 | 2009-06-17 | 株式会社岛津制作所 | Substrate inspection and repair device, and substrate evaluation system |
| CN101477066A (en) * | 2009-01-09 | 2009-07-08 | 华南理工大学 | Circuit board element mounting/welding quality detection method and system based on super-resolution image reconstruction |
| CN103411974A (en) * | 2013-07-10 | 2013-11-27 | 杭州赤霄科技有限公司 | Cloud big data-based planar material detection remote system and cloud big data-based planar material detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107389689A (en) | 2017-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107389689B (en) | AOI management system and management method for defect detection | |
| US11722642B2 (en) | Machine-vision system and method for remote quality inspection of a product | |
| US20210390678A1 (en) | Method for monitoring manufacture of assembly units | |
| US11449980B2 (en) | System and method for combined automatic and manual inspection | |
| CN111542791B (en) | Facility diagnosis method using facility diagnosis system | |
| CN111507147A (en) | Intelligent inspection method and device, computer equipment and storage medium | |
| US20210398267A1 (en) | Centralized analytics of multiple visual inspection appliances | |
| CN112712504B (en) | Cloud-based workpiece detection method and system and computer-readable storage medium | |
| CN102353683A (en) | Detection device and method for appearance and assembly of electric paper book based on machine vision | |
| CN109002021A (en) | Semiconductor production remote monitoring system based on OCR image processing techniques | |
| CN113888480A (en) | MES-based quality tracing method and system | |
| CN104931505A (en) | Machine visual surface detection system | |
| CN114895634A (en) | Product production line automatic control system based on machine vision | |
| CN116560326B (en) | Intelligent factory management platform | |
| US20220284699A1 (en) | System and method of object detection using ai deep learning models | |
| US20200073973A1 (en) | Digitalizing system and method | |
| CN113927217A (en) | Intelligent welding system | |
| CN109254009B (en) | Real-time detection processing system for embossing of nailing section | |
| KR102201303B1 (en) | Method of Acquiring Plant Logic Model Using Visual Device | |
| KR102623979B1 (en) | Masking-based deep learning image classification system and method therefor | |
| EP4202765A1 (en) | Method and system for counting bakeable food products | |
| CN111366580A (en) | Automatic optical detection method | |
| KR20230099223A (en) | Artificial intelligence image analysis method of cloud server-linked product assembly process using operator's motion recognition | |
| CN116563194A (en) | Visual inspection system for defect detection | |
| KR20240031018A (en) | Abnormality diagnosis method based on artificial intelligence model, abnormality diagnosis device and factory monitoring system using the same |
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 | ||
| CB02 | Change of applicant information |
Address after: 430070 Hubei City, Hongshan Province, South Lake Road, No. 53, Hongshan Venture Center, building on the four floor, No. Applicant after: Wuhan fine test electronics group Limited by Share Ltd Address before: 430070 Hubei City, Hongshan Province, South Lake Road, No. 53, Hongshan Venture Center, building on the four floor, No. Applicant before: Wuhan Jingce Electronic Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |