CN115266744A - Detection system and method for product in production line - Google Patents
Detection system and method for product in production line Download PDFInfo
- Publication number
- CN115266744A CN115266744A CN202210691406.3A CN202210691406A CN115266744A CN 115266744 A CN115266744 A CN 115266744A CN 202210691406 A CN202210691406 A CN 202210691406A CN 115266744 A CN115266744 A CN 115266744A
- Authority
- CN
- China
- Prior art keywords
- defect picture
- target product
- detection result
- workstation
- production line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 137
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims description 34
- 230000007547 defect Effects 0.000 claims abstract description 103
- 230000003287 optical effect Effects 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 25
- 238000007689 inspection Methods 0.000 claims description 19
- 238000002372 labelling Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 29
- 238000007726 management method Methods 0.000 description 17
- 238000003860 storage Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000012360 testing method Methods 0.000 description 7
- 230000001276 controlling effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000003466 welding Methods 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the application provides a detection system and a detection method for production line products, which are used for acquiring defect pictures of target products, confirming detection results of the target products based on the defect pictures and issuing sorting results based on the detection results.
Description
Technical Field
The application relates to the technical field of production line detection, in particular to a detection system and method for production line products.
Background
In the related art, for the equipment of controller, need a large amount of production circuit boards (PCB board), because the PCB board output of production is higher, after production is accomplished, need utilize check-out equipment to inspect the PCB board, qualified circuit board (can understand as the OK board) is carried to next station, unqualified circuit board (can understand as the NG board) need be retrieved, the detection to PCB in prior art is handled through AOI equipment, AOI equipment all is the stand-alone operation, system operation data all is the stand-alone storage, data can only rely on afterwards to carry out statistical processing after artifical uploading, lead to the unable effective utilization of system operation production data, unable real-time monitoring real-time quality data, there is the lower problem of efficiency in adopting manual letter sorting to OK board and NG board.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the application provides a detection system and a detection method for production line products, and aims to at least solve the problem of low efficiency caused by the fact that in the related technology, detection data can only be subjected to statistical processing after being uploaded manually afterwards, and OK boards and NG boards are sorted manually.
In a first aspect, an embodiment of the present application provides a detection system for a product in a production line, including: an automated optical inspection system, a workstation, and an inference system; the automatic optical detection system is used for detecting a target product and acquiring a defect picture of the target product; the workstation is used for acquiring a defect picture from the automatic optical detection system and sending the defect picture to an inference system; the reasoning system is used for determining a detection result based on the defect picture and sending the detection result to a workstation, and the workstation is also used for controlling the target product to be sorted based on the detection result.
In some embodiments, a prediction model is pre-established in the inference system, and the prediction model is used for determining whether a target product corresponding to the defect picture sent by the workstation is qualified.
In some embodiments, the workstation further comprises: a centralized control system and a transplanter;
the centralized control system is used for detecting the target product with unqualified detection result again and sending the detection result to the transplanter; the transplanter is used for sorting the target products to a preset position based on the detection result.
In some embodiments, the target product is sorted to a first area by the transplanter in case of passing detection result, and sorted to a second area by the transplanter in case of failing detection result.
In some embodiments, the detection system further comprises: an automatic labeling system and a training system;
the automatic labeling system is used for labeling the defect picture and sending the labeled defect picture to a training system; and the training system is used for training the labeled defect picture to obtain an updated training model and sending the updated training model to the reasoning system.
In some embodiments, the detection system further comprises: a production information management system;
the production information management system is used for acquiring the detection result and the defect picture from the workstation and establishing the association between the detection result and the defect picture and the target product through the bar code.
In some embodiments, the automatic optical inspection system has a cache area, and when acquiring a defect picture of a target product, the automatic optical inspection system stores the defect picture in the cache area, and the workstation is further configured to monitor a change condition of the defect picture in the cache area, where when monitoring that the defect picture in the cache area changes, the workstation acquires the defect picture from the cache area.
In a second aspect, based on the detection system of the first aspect, the application also provides a detection method of the production line product, which comprises the following steps:
acquiring a defect picture of the target product;
confirming a detection result of the target product based on the defect picture;
and confirming that the target product issues a sorting result based on the detection result.
In some embodiments, the determining the target product to issue a sorting result based on the detection result includes:
if the detection result represents that the target product corresponding to the defect picture is qualified, sorting the target product to a first area;
and if the detection result represents that the target product corresponding to the defect picture is unqualified, re-detecting the detection result.
In some embodiments, the preset location includes a second area, and the confirming that the target product issues a sorting result based on the detection result further includes:
if the re-detection result represents that the target product corresponding to the defect picture is qualified, sorting the target product to the first area;
and if the re-detection result represents that the target product corresponding to the defect picture is unqualified, sorting the target product to a second area.
The embodiment of the application provides a detection system and a method of production line product for acquire the defect picture of target product, confirm based on the defect picture the testing result of target product, confirm based on the testing result the sorting result is issued to the target product, and system architecture includes automatic optical detection system, workstation and inference system, and automatic optical detection system is used for detecting the target product, acquires the defect picture of target product, and the workstation is used for following automatic optical detection system acquires the defect picture, and will the defect picture sends to inference system, and inference system is used for confirming the testing result based on the defect picture, and will the testing result sends for the workstation, the workstation still is used for controlling based on the testing result the target product sorts to accomplish the automatic upload of AOI equipment data, realize OK board, NG board automatic sorting, alleviate manual sorting work load.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The present application will be described in more detail below on the basis of embodiments and with reference to the accompanying drawings.
Fig. 1 is a schematic diagram illustrating a system architecture and a process for inspecting circuit boards in a production line according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a method for inspecting circuit boards in a production line according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating step S130 in a method for inspecting circuit boards in a production line according to an embodiment of the present application;
fig. 4 shows another schematic flow chart of step S130 in the inspection method for circuit boards in a production line in the embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Prior to the description of the embodiments of the present application, a brief description of related art will be provided.
Terms, definitions of related matters:
automatic Optical Inspection (AOI): is an apparatus for detecting common defects encountered in welding production based on optical principles.
Printed Circuit Board (PCB): are important electronic components, which are manufactured by electronic printing, because of the designation printed circuit board.
MES (manufacturing execution system, abbreviated as MES) system: the system is a production informatization management system facing to a workshop execution layer of a manufacturing enterprise. The MES can provide a manufacturing collaborative management platform for enterprises, which comprises management modules such as manufacturing data management, planning and scheduling management, production scheduling management, inventory management, quality management, human resource management, work center/equipment management, tool and tool management, purchasing management, cost management, project board management, production process control, bottom layer data integration analysis, upper layer data integration decomposition and the like.
A central control automatic optical inspection system (CCAOI) can operate by feature extraction and machine learning methods and autonomously inspect the quality of the weld.
In the related technology, the existing AOI equipment is operated by a single machine, the system operation data is stored by the single machine, the data generated by the system operation cannot be effectively utilized in time, manual data uploading is needed, the equipment detection data cannot be uploaded in time, the real-time quality data cannot be effectively monitored, the detection data can only depend on post statistics, and the OK board and the NG board are manually sorted, so that the problem of low efficiency is caused.
In view of the above problems, the prior art has a problem of low efficiency, and the applicant proposes a system and a method for detecting a product in a production line according to an embodiment of the present application, in which a detection system for a product in a production line is mounted, the detection system being composed of at least an automatic optical detection system, a workstation, and an inference system. The automatic optical detection system is used for detecting a target product and obtaining a defect picture of the target product, the workstation is used for obtaining the defect picture from the automatic optical detection system and sending the defect picture to the inference system, the inference system is used for determining a detection result based on the defect picture and sending the detection result to the workstation, the workstation is also used for controlling the target product to be sorted based on the detection result, the single-machine AOI equipment is accessed to a network, the operation of the equipment is analyzed and the data obtained by the equipment is extracted, the automatic uploading of the equipment data is realized, and the automatic sorting of the OK board of the production line is realized, wherein the detection system and the method of the products of the production line are explained in detail in the subsequent embodiments.
Embodiments of the present application will be described in detail below with reference to the accompanying drawings.
In the embodiment of the present application, a circuit board is used as one product in the following embodiments for description, but the product of the production line may also include other products, which is not limited in the present application.
Referring to fig. 1, fig. 1 is a schematic diagram illustrating a detection system architecture and a detection flow of a product (circuit board) in a production line according to an embodiment of the present disclosure.
In the figure, the detection system of the production line circuit board can comprise: the automatic optical detection system, the workstation and the reasoning system can be in communication connection with each other, the automatic optical detection system is used for detecting a target circuit board and obtaining a defect picture of the target circuit board, the workstation is used for obtaining the defect picture from the automatic optical detection system and sending the defect picture to the reasoning system, the reasoning system is used for determining a detection result based on the defect picture and sending the detection result to the workstation, and the workstation is also used for controlling the target circuit board to be sorted based on the detection result.
Exemplarily, in a process of detecting a PCB, after an AOI detects a target circuit board, a defect picture corresponding to the target circuit board is obtained, and the defect picture is sent to a CCAOI workstation, the CCAOI workstation obtains the defect picture of the currently detected target circuit board and sends the defect picture to an inference system to judge whether the defect picture is qualified, the inference system returns an inference result to the CCAOI workstation, and the CCAOI workstation performs subsequent sorting operation on the target circuit board according to the detection result.
In the embodiment of the application, considering that the device is limited in calculation capacity with a GPU during AOI detection and cannot judge diversity defects, the detection system of a production line circuit board is formed by carrying an automatic optical detection system, a workstation and an inference system to upload various data of AOI detection results to corresponding devices in real time for storage, so that automatic uploading of AOI device data is realized, the workload of manual statistics is reduced, more accurate judgment results can be obtained on various data of the AOI detection results on the inference system through the deployed GPU of the inference system, the detection efficiency of products is improved, and the CCAOI workstation also carries out automatic sorting on OK and NG circuit boards according to the detection results so as to reduce the workload of manual sorting of staff.
The problem that the detection efficiency is low due to the fact that in the related technology, CCAOI has more false alarms and needs manual secondary rechecking is considered.
In some embodiments, a prediction model is pre-established in the inference system, and the prediction model is used for determining whether a target circuit board corresponding to a defect picture sent by the workstation is qualified.
In the embodiment of the application, the inference system may be provided with a corresponding Al prediction model, where the prediction model may include a neural network model for processing an image, such as a convolutional neural network, a BP neural network, and the like, and the inference system obtains an inspection picture sent by the CCAOI workstation, and obtains an inference result, and returns the inference result to the CCAOI workstation to complete the judgment of whether a target circuit board corresponding to the defect picture is qualified.
It should be noted that the inference system may be provided with a corresponding memory to implement real-time storage and processing of defect pictures transmitted by AOI, and in addition, the inference system may have an edge calculation function, which may provide a nearest-end service for AOI to improve inspection efficiency of a target circuit board.
In consideration of the problem of low efficiency in the related art that the CCAOI centralized control adopts one machine for one person to one machine for control detection.
In some embodiments, the workstation further comprises: a centralized control system and a transplanter;
and the centralized control system is used for detecting the target circuit board with unqualified detection result again and sending the detection result to the transplanter.
The transplanter is used for sorting the target circuit board to a preset position based on the detection result.
In the embodiment of the application, the CCAOI centralized control system adopts centralized control, under the condition that the inspection result obtained by the CCAOI workstation is identified to be an unqualified target circuit board (detection result NG), the detection result is sent to the transplanting machine of the corresponding CCAOI workstation through the CCAOI centralized control system, the transplanting machine sorts the corresponding target circuit board to the preset position, wherein the preset position can be an NG frame position and an OK frame position, and the CCAOI centralized control system is used for controlling a plurality of CCAOI workstation devices to realize the less-human detection.
In some embodiments, the transplanter sorts the target circuit board to the first area if the test result is qualified, and sorts the target circuit board to the second area if the test result is unqualified.
In the embodiment of the application, under the condition that the detection result is qualified through manual confirmation, the CCAOI centralized control system controls the transplanters of the CCAOI workstations with the corresponding number to sort the target circuit boards to the OK frame positions, and under the condition that the detection result is unqualified through manual confirmation, the CCAOI centralized control system controls the transplanters of the CCAOI workstations with the corresponding number to sort the target circuit boards to the NG frame positions.
Considering that in the related art, there is a problem that the detected PCB defective data needs to be marked manually, resulting in low efficiency.
In some embodiments, the detection system further comprises: an automatic labeling system and a training system.
The automatic labeling system is used for labeling the defect picture and sending the labeled defect picture to the training system.
In the embodiment of the application, a sample of a defect picture acquired at a CCAOI workstation is marked by an automatic marking system, the marked defect picture is sent to a training system for training, namely, the automatic marking system can automatically upload the acquired defect picture to a corresponding sample server, automatic marking of the sample is realized by automatic marking software based on the automatic marking system through neural network model feature extraction, and the sample is provided for the training system after marking of the sample is completed.
The training system is used for training the labeled defect pictures to obtain an updated training model and sending the updated training model to the reasoning system.
In the embodiment of the application, the training system trains the AI detection model, and the trained AI detection model is provided for the AI inference server for iterative upgrade of the detection model, namely, the inference system is updated, so that a better defect picture detection effect is realized.
When the circuit board which is detected to be unqualified is maintained, the informatization processing of the maintenance station is realized.
In some embodiments, the detection system further comprises: a production information management system.
The production information management system is used for acquiring the detection result and the defect picture from the workstation and establishing the association between the detection result, the defect picture and the target circuit board through the bar code.
In the embodiment of the application, after the target circuit board is detected, the detection result, the defect picture and the target circuit board are uploaded to an MES (manufacturing execution system) through an Http (Http protocol) interface for subsequent data statistics and quality tracing, so that the later maintenance is facilitated.
In some embodiments, the automatic optical inspection system has a buffer, the automatic optical inspection system stores the defect picture in the buffer when acquiring the defect picture of the target circuit board, and the workstation is further configured to monitor a change condition of the defect picture in the buffer, wherein the defect picture is acquired from the buffer when the workstation monitors that the defect picture in the buffer changes.
In this embodiment, the automatic optical inspection system may have a Buffer area, and the Buffer area may be configured with two folders of device data Buffer/SPC, and when data in the folders changes and the Buffer folders are written in, the CCAOI workstation determines transmission change of a defect picture in the Buffer area, and extracts a corresponding file from the Buffer area.
Referring to fig. 2, fig. 2 is a schematic flow chart of a method for detecting a production line product (circuit board) according to an embodiment of the present disclosure, where the method for detecting a production line circuit board is applied to a system for detecting a production line circuit board, and the method includes the steps of:
s110: and acquiring a defect picture of the target circuit board.
In the embodiment of the application, after AOI detection, the defect picture is stored in a computer buffer area, and the CCAOI workstation identifies and extracts the current detected defect picture of the target circuit board by monitoring the working buffer area in the AOI workstation.
S120: and confirming the detection result of the target circuit board based on the defect picture.
In the embodiment of the application, the obtained defect picture is sent to an inference system to operate an AI detection model to infer whether the product picture belongs to a qualified product.
S130: and confirming the target circuit board to issue a sorting result based on the detection result.
In the embodiment of the application, the inference system returns the inference result to the CCAOI workstation, and if the product is detected to be qualified, the inference result is issued to the corresponding sorting frame according to the corresponding inference result or is issued to the corresponding frame after further confirmation of an operator.
Referring to fig. 3, fig. 3 is a schematic flow chart of step S130 in a method for detecting circuit boards in a production line according to an embodiment of the present application, including:
s132: and if the detection result represents that the target circuit board corresponding to the defect picture is qualified, sorting the target circuit board to a first area.
In the embodiment of the application, the inference system returns the inference result to the CCAOI workstation, and if the product is detected to be qualified, the transplanter is controlled to put the product into an OK box.
S134: and if the detection result represents that the target circuit board corresponding to the defect picture is unqualified, re-detecting the detection result.
In the embodiment of the application, the reasoning system returns the reasoning result to the CCAOI workstation, if the product is detected to be unqualified, the result is sent to the CCAOI centralized control system to wait for further confirmation by an operator, and the operator confirms the result and then controls the transplanter to place the product in the corresponding frame.
Referring to fig. 3, fig. 3 is a schematic flow chart of a step S130 in the method for detecting products (circuit boards) in a production line according to an embodiment of the present application, including:
s136: and if the re-detection result represents that the target circuit board corresponding to the defect picture is qualified, sorting the target circuit board to the first area.
In the embodiment of the application, when the target circuit board corresponding to the manual detection result characterization defect picture is qualified, the operator confirms the result CCAOI workstation and controls the transplanter to put the product into the corresponding OK frame.
S138: and if the re-detection result represents that the target circuit board corresponding to the defect picture is unqualified, sorting the target circuit board to a second area.
In the embodiment of the application, when the target circuit board corresponding to the manual detection result characterization defect picture is unqualified, the operator confirms the result CCAOI workstation and controls the transplanter to place the product in the corresponding NG product frame.
The method can be specifically applied to a PCB welding production line, namely, whether the PCB is qualified for welding can be identified and completed based on the SMT of the controller, and the method can be implemented in a specific mode and comprises the following steps:
the SMT production line equipment is independently connected into the network, data acquisition equipment is researched and developed, two folders of AOI equipment data Buffer/SPC are monitored, when data in the folders change and the Buffer folders write in OPG files, the system immediately uploads the data to a CCAOI workstation, the CCAOI workstation receives the data and then sends the data back to an inference system, the inference system infers whether the pictures are qualified according to a pre-trained AI detection model and returns a calculation result to the CCAOI workstation, and the CCAOI workstation sends an instruction to a PLC (programmable logic controller) of the transplanter through a serial port to control the automatic sorting OK and NG products of the transplanter. And synchronously storing the correlated MES barcodes of the NG pictures on the edge computing equipment, scanning the MES barcodes by a maintainer to automatically call the NG component pictures when NG products are delivered for maintenance, and finishing maintenance by the maintainer by contrasting defective pictures.
The system synchronously collects defect pictures during operation, is used for AI detection model training, improves system detection precision, and has the following specific flows:
and after the NG picture is stored in the Buffer area, the automatic labeling system collects the NG picture and automatically uploads the NG picture to the sample server, automatic labeling of the sample is realized by automatic labeling software through neural network model characteristic extraction, the sample is provided for the training system to carry out AI detection model training after the labeling is finished, and the trained AI detection model is provided for the AI inference server for iterative upgrade of the detection model.
In summary, the present application provides a system and a method for detecting a production line circuit board, which are used for acquiring a defect picture of a target circuit board, confirming a detection result of the target circuit board based on the defect picture, and confirming a target circuit board to issue a sorting result based on the detection result, the system architecture includes an automatic optical detection system, a workstation and an inference system, the automatic optical detection system is used for detecting the target circuit board and acquiring the defect picture of the target circuit board, the workstation is used for acquiring the defect picture from the automatic optical detection system and sending the defect picture to the inference system, the inference system is used for determining the detection result based on the defect picture and sending the detection result to the workstation, the workstation is further used for controlling the target circuit board to sort based on the detection result so as to complete automatic uploading of data of AOI equipment, realize automatic sorting of OK boards and NG boards, reduce workload of manual sorting, realize automatic marking of sample data, informationization of the maintenance station, automatically extract the defect picture by scanning MES barcode, realize AOI detection and provide a nearest service, and improve product detection efficiency.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
It should be noted that, in this document, 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. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit may be implemented in the form of hardware, or in the form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
Alternatively, the integrated units described above in the present application may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application, which are essentially or partly contributing to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a controller to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The above description is only for the embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A system for inspecting production line products, comprising: an automated optical inspection system, a workstation, and an inference system;
the automatic optical detection system is used for detecting a target product and acquiring a defect picture of the target product;
the workstation is used for acquiring a defect picture from the automatic optical detection system and sending the defect picture to an inference system;
the reasoning system is used for determining a detection result based on the defect picture and sending the detection result to a workstation, and the workstation is also used for controlling the target product to be sorted based on the detection result.
2. The system for detecting the products in the production line according to claim 1, wherein a prediction model is pre-established in the inference system, and the prediction model is used for determining whether the target product corresponding to the defect picture sent by the workstation is qualified.
3. The production line product inspection system of claim 2, wherein the workstation further comprises: a centralized control system and a transplanter;
the centralized control system is used for detecting the target product with unqualified detection result again and sending the detection result to the transplanter;
the transplanter is used for sorting the target products to a preset position based on the detection result.
4. The system for inspecting products in a production line according to claim 3, wherein the target products are sorted to a first area by the transplanter in case that the inspection result is acceptable, and sorted to a second area by the transplanter in case that the inspection result is unacceptable.
5. The inspection system for production line products as recited in claim 2, further comprising: an automatic labeling system and a training system;
the automatic labeling system is used for labeling the defect picture and sending the labeled defect picture to a training system;
and the training system is used for training the labeled defect picture to obtain an updated training model and sending the updated training model to the reasoning system.
6. The inspection system for production line products of claim 1, further comprising: a production information management system;
the production information management system is used for acquiring the detection result and the defect picture from the workstation and establishing the association between the detection result and the defect picture and the target product through the bar code.
7. The system for detecting production line products as claimed in claim 1, wherein the automatic optical detection system has a buffer area, the automatic optical detection system stores the defect picture in the buffer area when acquiring the defect picture of the target product, the workstation is further configured to monitor a change condition of the defect picture in the buffer area, and the workstation acquires the defect picture from the buffer area when monitoring the change condition of the defect picture in the buffer area.
8. A method for inspecting products in a production line, which is implemented based on the inspection system for products in a production line according to any one of claims 1 to 7, and comprises:
acquiring a defect picture of the target product;
confirming a detection result of the target product based on the defect picture;
and confirming that the target product issues a sorting result based on the detection result.
9. The method of claim 8, wherein the preset location comprises a first area, and the confirming the target product issuing a sorting result based on the detection result comprises:
if the detection result represents that the target product corresponding to the defect picture is qualified, sorting the target product to a first area;
and if the detection result represents that the target product corresponding to the defect picture is unqualified, detecting the detection result again.
10. The method of claim 9, wherein the predetermined location comprises a second area, and the confirming the target product issues a sorting result based on the detection result further comprises:
if the re-detection result represents that the target product corresponding to the defect picture is qualified, sorting the target product to the first area;
and if the re-detection result represents that the target product corresponding to the defect picture is unqualified, sorting the target product to a second area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210691406.3A CN115266744A (en) | 2022-06-17 | 2022-06-17 | Detection system and method for product in production line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210691406.3A CN115266744A (en) | 2022-06-17 | 2022-06-17 | Detection system and method for product in production line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115266744A true CN115266744A (en) | 2022-11-01 |
Family
ID=83761307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210691406.3A Pending CN115266744A (en) | 2022-06-17 | 2022-06-17 | Detection system and method for product in production line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115266744A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274245A (en) * | 2023-11-17 | 2023-12-22 | 深圳市嘉熠精密自动化科技有限公司 | AOI optical detection method and system based on image processing technology |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109060817A (en) * | 2018-05-24 | 2018-12-21 | 牧德科技股份有限公司 | Artificial intelligence reinspection system and method thereof |
| CN110455822A (en) * | 2019-07-10 | 2019-11-15 | 苏州卓融新能源科技有限公司 | A kind of detection method of pcb board defect |
| CN113538341A (en) * | 2021-03-31 | 2021-10-22 | 联合汽车电子有限公司 | Automatic optical detection auxiliary method, device and storage medium |
-
2022
- 2022-06-17 CN CN202210691406.3A patent/CN115266744A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109060817A (en) * | 2018-05-24 | 2018-12-21 | 牧德科技股份有限公司 | Artificial intelligence reinspection system and method thereof |
| CN110455822A (en) * | 2019-07-10 | 2019-11-15 | 苏州卓融新能源科技有限公司 | A kind of detection method of pcb board defect |
| CN113538341A (en) * | 2021-03-31 | 2021-10-22 | 联合汽车电子有限公司 | Automatic optical detection auxiliary method, device and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274245A (en) * | 2023-11-17 | 2023-12-22 | 深圳市嘉熠精密自动化科技有限公司 | AOI optical detection method and system based on image processing technology |
| CN117274245B (en) * | 2023-11-17 | 2024-02-27 | 深圳市嘉熠精密自动化科技有限公司 | AOI optical detection method and system based on image processing technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017084186A1 (en) | System and method for automatic monitoring and intelligent analysis of flexible circuit board manufacturing process | |
| CN206921161U (en) | It is a kind of to include inspection management and defect processing and the intelligent inspection system of examination | |
| CN110567974A (en) | Cloud artificial intelligence based surface defect detection system | |
| US20220284699A1 (en) | System and method of object detection using ai deep learning models | |
| CN107390649B (en) | Project type product processing Internet of things support system | |
| CN115266744A (en) | Detection system and method for product in production line | |
| CN114858806A (en) | Cigarette quality inspection data analysis system and method | |
| CN117097727A (en) | Edge computing system based on industrial Internet of things platform | |
| CN118179989A (en) | Raw materials intelligence screening weighing system | |
| JP2022508398A (en) | Identification of nozzle condition or type in metalworking equipment | |
| CN110763979A (en) | LED wafer point measurement automatic system based on MES system | |
| CN118052793A (en) | Real-time monitoring system and method for plush toy production process | |
| CN113012097B (en) | Image rechecking method, computer device and storage medium | |
| CN117495156A (en) | Product quality tracing method, device, equipment and storage medium | |
| CN109492780B (en) | Repair tracking method, device and system for repaired parts | |
| CN112085221A (en) | Digital pole and tower intelligent operation and detection method and system | |
| JP2023133160A (en) | Inspection system, method for managing ai model data, and ai model data set | |
| CN115375961A (en) | Product accessory identification and weight assessment method, device and related equipment | |
| CN204857670U (en) | Detection and treatment facility of bad granule among chip resistor | |
| CN109540467B (en) | Optical fiber automatic test system based on industrial internet platform | |
| CN111768150A (en) | Logistics equipment health management platform based on 5G network | |
| CN110059935A (en) | The method of full-automatic typing and output in material flow | |
| JP2005128714A (en) | Failure handling support system and method, and service center system | |
| CN110989422A (en) | Management system and management method for AOI (automated optical inspection) over-inspection parameters based on serial number code spraying | |
| CN110252686A (en) | Method and device for determining quality of remote controller |
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 |