CN111915604A - Internet artificial intelligence electron accessories discernment and detecting system - Google Patents
Internet artificial intelligence electron accessories discernment and detecting system Download PDFInfo
- Publication number
- CN111915604A CN111915604A CN202010840947.9A CN202010840947A CN111915604A CN 111915604 A CN111915604 A CN 111915604A CN 202010840947 A CN202010840947 A CN 202010840947A CN 111915604 A CN111915604 A CN 111915604A
- Authority
- CN
- China
- Prior art keywords
- electronic
- detection
- model
- identification
- electronic accessory
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 210
- 238000013500 data storage Methods 0.000 claims abstract description 52
- 230000003287 optical effect Effects 0.000 claims abstract description 52
- 230000007547 defect Effects 0.000 claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims description 93
- 238000012360 testing method Methods 0.000 claims description 14
- 238000005520 cutting process Methods 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000003466 welding Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 description 9
- 238000000034 method Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000275 quality assurance Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 229910000679 solder Inorganic materials 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/955—Hardware or software architectures specially adapted for image or video understanding using specific electronic processors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses an internet artificial intelligence electronic accessory identification and detection system, which comprises automatic optical detection equipment, a picture acquisition device, an input device, a display device and an image receiving and processing terminal machine, wherein the picture acquisition device is arranged on the automatic optical detection equipment, an Ethernet interface is arranged on the automatic optical detection equipment, the image processing terminal machine comprises an image receiving module, a microprocessor, a data storage module, an electronic accessory AI identification processor and an electronic accessory AI detection processor, and the microprocessor is coupled with the image receiving module, the data storage module, the electronic accessory AI identification processor and the electronic accessory AI detection processor. The invention belongs to the technical field of electronic product detection, and particularly provides an internet artificial intelligence electronic part identification and detection system capable of quickly and accurately detecting defects and errors of processing and assembling of an object to be detected.
Description
Technical Field
The invention belongs to the technical field of electronic product detection, and particularly relates to an internet artificial intelligence electronic accessory identification and detection system.
Background
Automatic optical inspection equipment (AOI) is widely used in the production line with Surface Mount Technology (SMT) and in the inspection of the internal structure of electronic products or equipment before assembly is completed, in order to find defects in advance, improve quality and reduce cost.
Before the existing AOI equipment is used, templates and configuration related parameters need to be established on the AOI equipment, different templates and parameters need to be established for different objects to be tested, and a large amount of manpower is spent on configuration and setting. The comparison program is also required to be rewritten according to different objects to be tested, and the preparation and maintenance before use require time and labor input, so that the cost is high. In addition, the existing AOI equipment needs a high-precision camera and a fast comparison operation and determination module, so that the equipment cost is high.
Disclosure of Invention
In order to solve the existing problems, the invention provides an internet artificial intelligence electronic accessory identification and detection system which can quickly and accurately detect the defects and errors of processing and assembling of an object to be detected.
The technical scheme adopted by the invention is as follows: the invention relates to an internet artificial intelligent electronic accessory identification and detection system, which comprises automatic optical detection equipment, a picture acquisition device, an input device, a display device and an image receiving and processing terminal, wherein the picture acquisition device is arranged on the automatic optical detection equipment, a circuit board to be detected is arranged on the automatic optical detection equipment, an electronic accessory to be detected is arranged on the circuit board to be detected, the circuit board to be detected is arranged right below the picture acquisition device, the picture acquisition device acquires an image of the circuit board to be detected, an Ethernet interface is arranged on the automatic optical detection equipment, the automatic optical detection equipment is connected with the image receiving and processing terminal through Ethernet, the automatic optical detection equipment transmits a detection picture acquired by the picture acquisition device to the image receiving and processing terminal through the Ethernet interface, the image processing terminal receives information provided by the automatic optical detection equipment, and the image receiving and processing terminal receives, The image processing terminal comprises an image receiving module, a microprocessor, a data storage module, an electronic accessory AI identification processor and an electronic accessory AI detection processor, wherein the microprocessor is coupled with the image receiving module, the data storage module, the electronic accessory AI identification processor and the electronic accessory AI detection processor, the image receiving module is coupled with the data storage module, the image receiving module receives a detection picture sent by the automatic optical detection equipment and sends the detection picture to the microprocessor, the data storage module stores the electronic accessory information, the microprocessor transmits the detection picture to the electronic accessory AI identification processor and the electronic accessory AI detection processor and controls the electronic accessory AI identification processor and the electronic accessory AI detection processor to identify and detect the detection picture, the electronic accessory part AI identification processor and the electronic accessory part AI detection processor are respectively coupled with the data storage module, an electronic accessory part identification AI model is arranged in the electronic accessory part AI identification processor, an electronic accessory part detection AI model is arranged in the electronic accessory part AI detection processor, the electronic accessory part AI identification processor and the electronic accessory part AI detection processor respectively provide storage and operation capabilities for the electronic accessory part identification AI model and the electronic accessory part identification AI model, the electronic accessory part identification AI model receives a detection picture transmitted by the microprocessor and identifies whether the electronic accessory part in the detection picture belongs to the electronic accessory part stored in the data storage module and the category and the specification thereof according to the detection picture and the electronic accessory part information stored in the data storage module, the display device and the input device are arranged on the automatic optical detection equipment, and the microprocessor and the display device, The input device is coupled, the display device displays a prompt instruction sent by the microprocessor, an electronic accessory identification AI model judgment result, an electronic accessory detection AI model judgment result and electronic accessory information, when the electronic accessory identification AI model identifies that the electronic accessories existing on the detection picture do not belong to the electronic accessories stored in the data storage module, the electronic accessory identification AI model sends the picture of the electronic accessories which are not stored to the microprocessor, the microprocessor controls the display device to display the detection picture of the electronic accessories which are not stored and displays that the electronic accessories do not have the prompt instruction for establishing the relevant information of the electronic accessories in the system, the input device inputs the electronic accessory information and picture labels, and a user inputs the information of the electronic accessories which are not stored and labels the picture of the electronic accessories on the input device,
the microprocessor is internally provided with a model training module, the data storage module is internally provided with a model base, an electronic accessory identification AI model and an electronic accessory detection AI model mark a large number of electronic accessory pictures through the model training module and establish a training set, test set data are generated through artificial intelligence model training, the electronic accessory detection AI model judges whether the processing technology of the electronic accessories in the detection pictures is good or not according to the detection pictures and the model base and judges whether defects and defect reasons exist in the electronic accessories according to the electronic accessory pictures, the model training module makes the training set and the test set required by model training for the electronic accessory information which is input at the input end and needs model training, carries out model parameter setting and model training, the model base stores and updates the model trained by the model training module and provides a model for the electronic accessory identification AI model and the electronic accessory detection AI model, the microprocessor sends the electronic accessory information input by the input end to the electronic accessory AI recognition processor to judge whether the electronic accessory which needs model training and is not stored is stored in the data storage module, when the electronic accessory AI recognition processor judges that the electronic accessory information which needs model training and is not stored in the data storage module, the model training module adds the electronic accessory information which needs model training to the data storage module and labels the electronic accessory information which needs model training, after the labeling of the electronic accessory information which needs model training is finished, the model training module makes a training set and a testing set which are needed by model training and then carries out model parameter setting and model training, after the model parameter setting and the model training are finished, the model training module updates the model to the model base, and the model base stores the updated model, when the electronic accessory AI identification processor judges that the electronic accessory information required to be subjected to model training is stored in the data storage module, the model training module performs model parameter setting and model training after manufacturing a training set and a test set required by the model training, the model training module updates the model into the model base after the model parameter setting and the model training are finished, the microprocessor controls the electronic accessory identification AI model to detect and compare the detection picture with the electronic accessory picture in the data storage module again to judge whether all the electronic accessory information on the detection picture belongs to the electronic accessories stored in the data storage module, and when the electronic accessory identification AI model detects that all the electronic accessory information on the detection picture belongs to the electronic accessories stored in the data storage module, the electronic accessory identification AI model sends the detection picture to the electronic accessory detection AI model, the electronic spare and accessory part detection AI model detects the electronic spare and accessory parts and returns the judgment result to the microprocessor, and the microprocessor controls the display device to display the judgment result of the electronic spare and accessory part detection AI model.
Furthermore, the electronic spare and accessory part information comprises pictures, categories, specifications, functions and manufacturer models, and the electronic spare and accessory part detection AI model and the electronic spare and accessory part identification AI model are convenient to accurately identify and detect the electronic spare and accessory parts.
Furthermore, an image cutting module is arranged in the microprocessor, and the image cutting module performs image cutting on the detection image provided by the automatic optical detection equipment to obtain an independent detection image of each electronic spare and accessory part, so as to obtain the image of each electronic spare and accessory part for identification and detection and marking the result.
Preferably, the labeling includes labeling the type of the electronic parts to the independent detection image and labeling the defect reason to the independent detection image of the electronic parts with defects, the model training module makes different defect training sets and test set data of each type according to the labeling, generates an electronic part detection AI model of each type through model training, and the electronic part detection AI model judges whether the electronic parts have defects and defect reasons through the electronic part picture and continuously improves the detection accuracy through repetitive recognition and deep learning.
Preferably, the defects include, but are not limited to, poor assembly of the component, poor solder joint, offset, missing component, pin warp, side standing, reverse, pin imperfection.
Furthermore, the automatic optical detection device and the image receiving and processing terminal machine are respectively provided with a WiFi transmission module, so that the automatic optical detection device and the image receiving and processing terminal machine can conveniently perform data interaction through WiFi.
Furthermore, the image processing terminal machine and the automatic optical detection equipment are connected in a plurality of ways, and the image processing terminal machine simultaneously serves the plurality of automatic optical detection equipment through the Ethernet to provide identification and detection results.
Further, the input device includes but is not limited to a keyboard, a mouse, a touch screen, a voice recognition module, and a text recognition module.
The invention with the structure has the following beneficial effects: according to the internet artificial intelligence electronic spare part identification and detection system, the electronic spare part internet data center is built by collecting the electronic spare part information provided by the automatic optical detection equipment, the manual investment of early-stage preparation and later-stage maintenance is avoided, the information service of intelligent manufacturing is provided, and the equipment cost required by a detection module can be saved by the required automatic optical detection equipment from the viewpoint of saving the cost; in the aspect of efficiency, the artificial intelligence is adopted to carry out identification, detection and judgment on the electronic spare and accessory parts, so that the accuracy and the reliability are improved; in view of quality assurance, the technology and the equipment can identify the defects in advance for later assembly processes with higher and higher precision, and detect the defects before the assembly of the product, so that the defects can be avoided being found after the assembly is finished, and the waste of disassembling the machine is reduced; the electronic spare and accessory part internet data center provides an information platform to serve a large number of users to quickly improve the manufacturing level
Drawings
FIG. 1 is a schematic structural diagram of an Internet artificial intelligence electronic accessory identification and detection system of the present invention;
FIG. 2 is a schematic block diagram of an Internet artificial intelligence electronic accessory identification and detection system of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in figures 1 and 2, the internet artificial intelligence electronic accessory identification and detection system comprises an automatic optical detection device, a picture acquisition device, an input device, a display device and an image receiving and processing terminal, wherein the picture acquisition device is arranged on the automatic optical detection device, a circuit board to be detected is arranged on the automatic optical detection device, an electronic accessory to be detected is arranged on the circuit board to be detected, the circuit board to be detected is arranged right below the picture acquisition device, the picture acquisition device acquires an image of the circuit board to be detected, an Ethernet interface is arranged on the automatic optical detection device, the automatic optical detection device is connected with the image receiving and processing terminal through Ethernet, a detection picture acquired by the picture acquisition device is transmitted to the image receiving and processing terminal through the Ethernet interface by the automatic optical detection device, the image processing terminal receives information provided by the automatic optical detection device, and the image processing terminal receives the information, The image processing terminal comprises an image receiving module, a microprocessor, a data storage module, an electronic accessory AI identification processor and an electronic accessory AI detection processor, wherein the microprocessor is coupled with the image receiving module, the data storage module, the electronic accessory AI identification processor and the electronic accessory AI detection processor, the image receiving module is coupled with the data storage module, the image receiving module receives a detection picture sent by the automatic optical detection equipment and sends the detection picture to the microprocessor, the data storage module stores the electronic accessory information, the microprocessor transmits the detection picture to the electronic accessory AI identification processor and the electronic accessory AI detection processor and controls the electronic accessory AI identification processor and the electronic accessory AI detection processor to identify and detect the detection picture, the electronic accessory part AI identification processor and the electronic accessory part AI detection processor are respectively coupled with the data storage module, an electronic accessory part identification AI model is arranged in the electronic accessory part AI identification processor, an electronic accessory part detection AI model is arranged in the electronic accessory part AI detection processor, the electronic accessory part AI identification processor and the electronic accessory part AI detection processor respectively provide storage and operation capabilities for the electronic accessory part identification AI model and the electronic accessory part identification AI model, the electronic accessory part identification AI model receives a detection picture transmitted by the microprocessor and identifies whether the electronic accessory part in the detection picture belongs to the electronic accessory part stored in the data storage module and the category and the specification thereof according to the detection picture and the electronic accessory part information stored in the data storage module, the display device and the input device are arranged on the automatic optical detection equipment, and the microprocessor is respectively coupled with the display device, The input device is coupled, the display device displays a prompt instruction sent by the microprocessor, an electronic accessory identification AI model judgment result, an electronic accessory detection AI model judgment result and electronic accessory information, when the electronic accessory identification AI model identifies that the electronic accessories existing on the detection picture do not belong to the electronic accessories stored in the data storage module, the electronic accessory identification AI model sends the picture of the electronic accessories which are not stored to the microprocessor, the microprocessor controls the display device to display the independent detection picture of the electronic accessories which are not stored and displays the prompt instruction that the electronic accessories do not have related information to be established in the system, the input device inputs the electronic accessory information and picture labels, a user inputs the information of the electronic accessories which are not stored and labels the picture of the electronic accessories on the input device, and the microprocessor is internally provided with a model training module, a model base is arranged in the data storage module, an electronic accessory identification AI model and an electronic accessory detection AI model are used as model training modules to mark a large number of electronic accessory pictures and establish a training set, test set data is generated through artificial intelligence model training, the electronic accessory detection AI model judges whether the processing technology of the electronic accessories in the detection pictures is good or not according to the detection pictures and the model base and judges whether defects and defect reasons exist in the electronic accessories according to the electronic accessory pictures, the model training module makes the training set and the test set required by model training for the electronic accessory information input by the input end and required by model training, carries out model parameter setting and model training, the model base stores and updates the models trained by the model training module and provides models for the electronic accessory identification AI model and the electronic accessory detection AI model, and the microprocessor sends the electronic accessory information input by the input end to the electronic accessory AI identification processor to judge whether the electronic accessory identification processor or not Whether the electronic parts needing model training and not stored are stored in the data storage module, when the electronic parts AI identification processor judges that the electronic parts information needing model training is not stored in the data storage module, the model training module adds the electronic parts information needing model training to the data storage module and labels the electronic parts information needing model training, after the electronic parts information needing model training is labeled, the model training module carries out model parameter setting and model training after manufacturing a training set and a testing set required by model training, the model training module updates the model to the model base after the model parameter setting and model training is finished, the model base stores the updated model, when the electronic parts AI identification processor judges that the electronic parts information needing model training is stored in the data storage module, the model training module makes a training set and a test set required by model training and then carries out model parameter setting and model training, the model training module updates the model into the model base after the model parameter setting and the model training are finished, after the model updating is finished, the microprocessor controls the electronic accessory identification AI model to detect and compare the independent detection picture with the electronic accessory picture in the data storage module again to judge whether all the electronic accessory information on the detection picture belongs to the electronic accessories stored in the data storage module, when the electronic accessory identification AI model detects that all the electronic accessory information on the detection picture belongs to the electronic accessories stored in the data storage module, the electronic accessory identification AI model sends the independent detection picture to the electronic accessory detection AI model, the electronic accessory detection AI model detects the electronic accessories and returns the judgment result to the microprocessor, and the microprocessor controls the display device to display the judgment result of the AI model detected by the electronic spare and accessory parts.
The electronic spare and accessory part information comprises pictures, categories, specifications, functions and manufacturer models, and the electronic spare and accessory part information is convenient for detecting the AI model and accurately identifying and detecting the electronic spare and accessory part by identifying the AI model.
And an image cutting module is arranged in the microprocessor, and the image cutting module performs image cutting on the detection image provided by the automatic optical detection equipment to obtain an independent detection image of each electronic part, so as to obtain the image of each electronic part for identification, detection and result marking.
The marking comprises marking the categories of the electronic accessories on the independent detection images and marking the reasons of the defects on the independent detection images of the electronic accessories with the defects, the model training module is used for manufacturing different defect training sets and test set data of each category according to the marking, the respective electronic accessory detection AI model of each category is generated through model training, the electronic accessory detection AI model judges whether the electronic accessories have the defects and the reasons of the defects through the electronic accessory pictures, and the detection accuracy is continuously improved through repeated identification and deep learning.
The defects include but not limited to poor assembly of the spare and accessory parts, poor welding spots, deviation, missing parts, pin warping, side standing, reverse direction and incomplete pin of the electronic spare and accessory parts.
The automatic optical detection equipment and the image receiving and processing terminal are respectively provided with a WiFi transmission module, so that the automatic optical detection equipment and the image receiving and processing terminal can conveniently perform data interaction through WiFi.
The image processing terminal machine and the automatic optical detection equipment are connected in a plurality of ways, and the image processing terminal machine simultaneously serves the automatic optical detection equipment through the Ethernet to provide identification and detection results.
The input device comprises but not limited to a keyboard, a mouse, a touch screen, a voice recognition module and a character recognition module.
When the device is used specifically, after a circuit board to be detected enters the automatic optical detection device, the picture acquisition device acquires an image of the circuit board to be detected, the automatic optical detection device transmits a detection picture acquired by the picture acquisition device to the image receiving and processing terminal machine through the Ethernet interface, the image processing terminal machine receives information provided by the automatic optical detection device, stores a large amount of electronic spare and accessory part information and provides storage and operation capabilities required by detection and identification, the image receiving module receives the detection picture sent by the automatic optical detection device and sends the detection picture to the microprocessor, the data storage module stores the electronic spare and accessory part information, the microprocessor transmits the detection picture to the electronic spare and accessory part AI identification processor and controls the electronic spare and accessory part AI identification processor and the electronic spare and accessory part AI detection processor to identify and detect the detection picture, and the electronic spare and accessory part AI identification processor and the electronic spare and accessory part AI detection processor respectively identify and detect the electronic spare and accessory part The AI model and the electronic accessory identification AI model provide storage and operation capabilities, the electronic accessory identification AI model receives a detection picture transmitted by the microprocessor and identifies whether the electronic accessories in the detection picture belong to the electronic accessories stored in the data storage module and the categories and specifications of the electronic accessories according to the detection picture and the electronic accessory information stored in the data storage module, when the electronic accessory identification AI model identifies that the electronic accessories existing on the detection picture do not belong to the electronic accessories stored in the data storage module, namely unidentifiable electronic accessories exist, the microprocessor informs the electronic accessory information unidentifiable to the automatic optical detection equipment through the Internet and displays the electronic accessory information on the display device, and displays a prompt instruction for establishing related information of the electronic accessory in the system, and prompts personnel to manually maintain the picture of the unidentifiable electronic accessories, The method comprises the steps that information such as types, specifications, functions, manufacturers and models is input by a user on an input device, electronic spare and accessory part information which is not stored and an electronic spare and accessory part picture is labeled, when an electronic spare and accessory part AI identification processor judges that the electronic spare and accessory part information which needs model training is not stored in a data storage module, the model training module adds the electronic spare and accessory part information which needs model training to the data storage module and labels the electronic spare and accessory part information which needs model training, the labeling comprises labeling the electronic spare and accessory part types of an independent detection image and labeling defect reasons of the independent detection image of the electronic spare and accessory part with defects, the defects comprise incomplete spare and accessory part assembling, bad welding points, deviation, missing parts, warped feet, side standing, reverse feet and pin feet, after the labeling of the electronic spare and accessory part information which needs model training is completed, the model training module makes different defect training sets and test set data of each category according to labels, carries out model parameter setting and model training, generates an electronic accessory detection AI model of each category through model training, the electronic accessory detection AI model judges whether the electronic accessories have defects and defect reasons through electronic accessory pictures, and continuously improves detection accuracy through repeated recognition and deep learning, the model training module updates the model into the model base after the model parameter setting and model training are finished, the model base stores the updated model, when the electronic accessory identification processor judges that the electronic accessory information needing model training is stored in the data storage module, the model training module makes the training sets and test sets needed by the model training and carries out the model training, the model training module updates the model into the model base after the model parameter setting and model training are finished, after the model is updated, the microprocessor controls the electronic part identification AI model to detect and compare the independent detection picture with the electronic part pictures in the data storage module again to judge whether all the electronic part information on the detection picture belongs to the electronic parts stored in the data storage module, when the electronic part identification AI model detects that all the electronic part information on the detection picture belongs to the electronic parts stored in the data storage module, the electronic part identification AI model returns the judgment result to the microprocessor, the microprocessor controls the picture cutting module to cut the detection picture into independent detection pictures of each electronic part, the electronic part identification AI model sends the independent detection pictures to the electronic part detection AI model, and the electronic part detection AI model judges whether the processing technology of the electronic parts in the detection picture is good according to the detection pictures and the model library and judges the electronic parts according to the electronic part pictures Whether the accessories have defects or not and the defect reasons comprise defect positions, the electronic accessory detection AI model collects the judgment results of the electronic accessories and returns the judgment results to the microprocessor, the microprocessor controls the display device to display the judgment results of the electronic accessory detection AI model and collects user supplement data and feedback opinions, a user inputs the user supplement data and the feedback opinions through the input device, and the automatic optical detection equipment uploads the user supplement data and the feedback opinions to the microprocessor and the model training module through the Internet for model training.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The utility model provides an internet artificial intelligence electron accessories discernment and detecting system which characterized in that: the system comprises an automatic optical detection device, a picture acquisition device, an input device, a display device and an image receiving and processing terminal, wherein the picture acquisition device is arranged on the automatic optical detection device, a circuit board to be detected is arranged on the automatic optical detection device, an electronic part to be detected is arranged on the circuit board to be detected, the circuit board to be detected is arranged right below the picture acquisition device, the picture acquisition device acquires an image of the circuit board to be detected, an Ethernet interface is arranged on the automatic optical detection device, the automatic optical detection device is connected with the image receiving and processing terminal through the Ethernet, a detection picture acquired by the picture acquisition device is transmitted to the image receiving and processing terminal through the Ethernet interface by the automatic optical detection device, the image processing terminal receives information provided by the automatic optical detection device, stores a large amount of electronic part information and provides storage and operation capacity required by detection and identification, the image processing terminal comprises an image receiving module, a microprocessor, a data storage module, an electronic spare part AI identification processor and an electronic spare part AI detection processor, wherein the microprocessor is coupled with the image receiving module, the data storage module, the electronic spare part AI identification processor and the electronic spare part AI detection processor, the image receiving module is coupled with the data storage module, the image receiving module receives a detection picture sent by an automatic optical detection device and sends the detection picture to the microprocessor, the data storage module stores information of electronic spare parts, the microprocessor transmits the detection picture to the electronic spare part AI identification processor and the electronic spare part AI detection processor and controls the electronic spare part AI identification processor and the electronic spare part AI detection processor to identify and detect the detection picture, and the electronic spare part AI identification processor and the electronic spare part AI detection processor are respectively coupled with the data storage module, an electronic accessory identification AI model is arranged in the electronic accessory AI identification processor, an electronic accessory detection AI model is arranged in the electronic accessory AI detection processor, the electronic accessory identification AI model receives a detection picture transmitted by the microprocessor and identifies whether the electronic accessories in the detection picture belong to the electronic accessories stored in the data storage module and the categories and specifications thereof according to the detection picture and the electronic accessory information stored in the data storage module, the display device and the input device are arranged on the automatic optical detection equipment, the microprocessor is respectively coupled with the display device and the input device, the display device displays a prompt instruction transmitted by the microprocessor, an electronic accessory identification AI model judgment result, an electronic accessory detection AI model judgment result and the electronic accessory information, the input device inputs the electronic accessory information and picture marks, and the microprocessor is internally provided with a model training module, the data storage module is internally provided with a model base, the electronic accessory detection AI model judges whether the processing technology of the electronic accessories in the detection picture is good or not according to the detection picture and the model base and judges whether the electronic accessories have defects and defect reasons or not according to the electronic accessory picture, the model training module makes a training set and a testing set required by model training for the electronic accessory information input by the input end and needing model training, sets model parameters and trains a model, and the model base stores and updates the model trained by the model training module and provides a model for the electronic accessory identification AI model and the electronic accessory detection AI model.
2. The internet artificial intelligence electronic accessory part identification and detection system of claim 1, wherein: the electronic accessory information comprises pictures, categories, specifications, functions and manufacturer models.
3. The internet artificial intelligence electronic accessory part identification and detection system of claim 1, wherein: an image cutting module is arranged in the microprocessor and is used for carrying out image cutting on the detection image provided by the automatic optical detection equipment to obtain an independent detection image of each electronic spare and accessory part.
4. The internet artificial intelligence electronic accessory part identification and detection system of claim 1, wherein: the marking comprises marking the categories of the electronic accessories on the independent detection images and marking the reasons of the defects on the independent detection images of the electronic accessories with the defects, the model training module is used for manufacturing different defect training sets and test set data of each category according to the marking, the respective electronic accessory detection AI model of each category is generated through model training, the electronic accessory detection AI model judges whether the electronic accessories have the defects and the reasons of the defects through the electronic accessory pictures, and the detection accuracy is continuously improved through repeated identification and deep learning.
5. The internet artificial intelligence electronic accessory part identification and detection system of claim 1, wherein: the defects include but are not limited to poor assembly of the parts, poor welding spots, offset, missing parts, pin warping, side standing, reverse direction and incomplete pin.
6. The internet artificial intelligence electronic accessory part identification and detection system of claim 1, wherein: the automatic optical detection equipment and the image receiving and processing terminal are respectively provided with a WiFi transmission module.
7. The internet artificial intelligence electronic accessory part identification and detection system of claim 1, wherein: the image processing terminal machine and the automatic optical detection equipment are connected in a plurality of ways.
8. The internet artificial intelligence electronic accessory part identification and detection system of claim 1, wherein: the input device comprises but not limited to a keyboard, a mouse, a touch screen, a voice recognition module and a character recognition module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010840947.9A CN111915604A (en) | 2020-08-20 | 2020-08-20 | Internet artificial intelligence electron accessories discernment and detecting system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010840947.9A CN111915604A (en) | 2020-08-20 | 2020-08-20 | Internet artificial intelligence electron accessories discernment and detecting system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111915604A true CN111915604A (en) | 2020-11-10 |
Family
ID=73278437
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010840947.9A Pending CN111915604A (en) | 2020-08-20 | 2020-08-20 | Internet artificial intelligence electron accessories discernment and detecting system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111915604A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112711603A (en) * | 2020-12-30 | 2021-04-27 | 广东粤云工业互联网创新科技有限公司 | Workpiece detection method and system based on cloud and computer-readable storage medium |
CN113066087A (en) * | 2021-04-29 | 2021-07-02 | 中奥智能工业研究院(南京)有限公司 | Intelligent detection and labeling system and method for parts |
CN113312969A (en) * | 2021-04-23 | 2021-08-27 | 浙江省机电设计研究院有限公司 | Part identification and positioning method and system based on three-dimensional vision |
CN113359453A (en) * | 2021-06-11 | 2021-09-07 | 刘颖妮 | Part machining device based on artificial intelligence and intelligent workshop system thereof |
CN113433128A (en) * | 2021-07-02 | 2021-09-24 | 南通海舟电子科技有限公司 | Intelligent display screen system based on circuit board automated production |
TWI752846B (en) * | 2021-03-15 | 2022-01-11 | 英業達股份有限公司 | Secondary detection system for integrating automated optical inspection and neural network and method thereof |
WO2022141958A1 (en) * | 2020-12-29 | 2022-07-07 | 南京灵雀智能制造有限公司 | Nut stereoscopic imaging detection apparatus and detection method |
CN115016420A (en) * | 2022-06-28 | 2022-09-06 | 池州市明坤电子科技有限公司 | Intelligent processing system for aluminum parts |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104316033A (en) * | 2014-11-04 | 2015-01-28 | 无锡港湾网络科技有限公司 | Visual inspection system for automobile parts |
RU2548693C1 (en) * | 2013-11-12 | 2015-04-20 | Акционерное общество "Головное производственно-техническое предприятие "Гранит" | Multifunctional maintenance and repair centre (mmrc) |
CN108872247A (en) * | 2018-06-15 | 2018-11-23 | 南京吉目希自动化科技有限公司 | A kind of product automatic checkout system and detection method based on machine vision and RFID |
CN110567974A (en) * | 2019-09-30 | 2019-12-13 | 华中科技大学 | Cloud artificial intelligence based surface defect detection system |
CN212322301U (en) * | 2020-08-20 | 2021-01-08 | 魏小燕 | Internet artificial intelligence electron accessories discernment and detecting system |
-
2020
- 2020-08-20 CN CN202010840947.9A patent/CN111915604A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
RU2548693C1 (en) * | 2013-11-12 | 2015-04-20 | Акционерное общество "Головное производственно-техническое предприятие "Гранит" | Multifunctional maintenance and repair centre (mmrc) |
CN104316033A (en) * | 2014-11-04 | 2015-01-28 | 无锡港湾网络科技有限公司 | Visual inspection system for automobile parts |
CN108872247A (en) * | 2018-06-15 | 2018-11-23 | 南京吉目希自动化科技有限公司 | A kind of product automatic checkout system and detection method based on machine vision and RFID |
CN110567974A (en) * | 2019-09-30 | 2019-12-13 | 华中科技大学 | Cloud artificial intelligence based surface defect detection system |
CN212322301U (en) * | 2020-08-20 | 2021-01-08 | 魏小燕 | Internet artificial intelligence electron accessories discernment and detecting system |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022141958A1 (en) * | 2020-12-29 | 2022-07-07 | 南京灵雀智能制造有限公司 | Nut stereoscopic imaging detection apparatus and detection method |
CN112711603A (en) * | 2020-12-30 | 2021-04-27 | 广东粤云工业互联网创新科技有限公司 | Workpiece detection method and system based on cloud and computer-readable storage medium |
TWI752846B (en) * | 2021-03-15 | 2022-01-11 | 英業達股份有限公司 | Secondary detection system for integrating automated optical inspection and neural network and method thereof |
CN113312969A (en) * | 2021-04-23 | 2021-08-27 | 浙江省机电设计研究院有限公司 | Part identification and positioning method and system based on three-dimensional vision |
CN113066087A (en) * | 2021-04-29 | 2021-07-02 | 中奥智能工业研究院(南京)有限公司 | Intelligent detection and labeling system and method for parts |
CN113066087B (en) * | 2021-04-29 | 2022-08-05 | 中奥智能工业研究院(南京)有限公司 | Intelligent detection and labeling system and method for parts |
CN113359453A (en) * | 2021-06-11 | 2021-09-07 | 刘颖妮 | Part machining device based on artificial intelligence and intelligent workshop system thereof |
CN113433128A (en) * | 2021-07-02 | 2021-09-24 | 南通海舟电子科技有限公司 | Intelligent display screen system based on circuit board automated production |
CN115016420A (en) * | 2022-06-28 | 2022-09-06 | 池州市明坤电子科技有限公司 | Intelligent processing system for aluminum parts |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111915604A (en) | Internet artificial intelligence electron accessories discernment and detecting system | |
CN1318839C (en) | Automatic optical detecting system for blemish assembly on printed circuit board | |
CN112053318A (en) | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning | |
US20230262903A1 (en) | Inspection and production of printed circuit board assemblies | |
TWI755953B (en) | Automatic detection system and operation method thereof | |
CN107133725A (en) | A kind of automated production management system of circuit board | |
CN212322301U (en) | Internet artificial intelligence electron accessories discernment and detecting system | |
CN110865087A (en) | PCBA quality detection method based on artificial intelligence | |
CN106556794A (en) | Method and device for realizing PCBA board detection | |
CN114022436B (en) | Detection method, device and detection equipment for printed circuit board | |
TW202230281A (en) | Image reinspection method, computer device, and storage medium | |
CN117589770A (en) | PCB patch board detection method, device, equipment and medium | |
US7134599B2 (en) | Circuit board inspection apparatus | |
CN110006903A (en) | Printed circuit board rechecks system, marker method and reinspection method | |
CN207717640U (en) | Printed circuit board rechecks system | |
CN111343798B (en) | Manual chip mounter auxiliary system and method based on machine vision recognition | |
TW200842346A (en) | Detection method of printed circuit boards and the system thereof | |
CN111542218B (en) | Electric energy meter credible production patch link acquisition verification method and system | |
CN114459350B (en) | PCB board intellectual detection system | |
CN118549435A (en) | Automatic optical detection process | |
CN217586984U (en) | Automatic optical detection device | |
CN112286972B (en) | AOI tracing system | |
CN114820412A (en) | Automatic detection system and operation method thereof | |
CN114328760A (en) | Method for collecting sequence number before wave soldering when sequence number is at bottom of PCBA | |
Chung et al. | DVQI: A Multi-task, Hardware-integrated Artificial Intelligence System for Automated Visual Inspection in Electronics Manufacturing |
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 |