CN114399473A - Defect sample image acquisition device applied to industrial production - Google Patents
Defect sample image acquisition device applied to industrial production Download PDFInfo
- Publication number
- CN114399473A CN114399473A CN202111636449.3A CN202111636449A CN114399473A CN 114399473 A CN114399473 A CN 114399473A CN 202111636449 A CN202111636449 A CN 202111636449A CN 114399473 A CN114399473 A CN 114399473A
- Authority
- CN
- China
- Prior art keywords
- defect sample
- module
- data
- sample image
- defect
- 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
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
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to the technical field of image data collection in a visual model of a training depth learning machine, and provides a defect sample image collection device applied to industrial production. The application provides a flexible data acquisition rack, is a low-cost simulation production station, but different production lines of various detection tasks of abstract simulation, emulation gather defect image data in a concentrative way. Moreover, the defect image data can be from a defect sample reserved in historical manual detection, and can also be a sample removed in the detection process by other detection means.
Description
Technical Field
The application relates to the technical field of image data collection, in particular to a defect sample image collection device applied to industrial production.
Background
In industrial production, quality detection based on machine vision is a novel advanced detection means based on artificial intelligence, can replace artificial detection defects, and is an important measure for improving production efficiency, reducing labor force, reducing manual labor intensity and ensuring product quality. However, the quality detection method based on machine vision mainly acquires a large amount of target defect image data, obtains a relatively accurate machine vision model after training through a deep learning model, and then applies the trained machine vision model to an industrial production line.
The conventional defect data acquisition method usually requires that an image acquisition device is additionally arranged in a production line, and a defect part is photographed when a defect is generated, so as to obtain target defect image data. However, in actual industrial production, the generation of defective products is usually small and discontinuous, so it is difficult to predict when defects are generated, to acquire defect image data by using a conventional defect data acquisition method, and to obtain a large number of defect samples. In this case, if the conventional defect data acquisition method is still used, a large amount of time cost and labor cost are required to be invested.
At present, in the prior art, image data acquisition is still mostly completed on line by adding an image acquisition module in a production line, and samples of certain defect types are intentionally manufactured manually or the image acquisition module is notified after the defect samples are found by other quality detection means to acquire the image data. However, the above scheme is difficult to apply to industrial production scenes, and cannot be used for collecting randomly generated defect image information in a targeted and efficient manner, so that great limitations exist in convenience and timeliness of data collection.
Disclosure of Invention
In order to overcome the defects of the prior art, the defect image acquisition device solves the problems that the prior art cannot pointedly and efficiently acquire randomly generated defect image information and has great limitation on convenience and timeliness of data acquisition.
In order to achieve the above object, the present application provides a defect sample image capturing device applied to industrial production, which specifically includes:
and the flexible simulation station module is used for simulating a target installation station of the defect sample image acquisition device on the actual production line.
And the data acquisition module is arranged on the flexible simulation station module and is used for acquiring image information of the defect sample in an off-line manner.
And the data processing module is used for processing the defect sample image information acquired offline to obtain processing data and storing the processing data.
And the control module is in signal connection with the data acquisition module and the data processing module and is used for controlling the operation of the data acquisition module and the data processing module.
Further, the control module is integrated with the data processing module.
Furthermore, the data acquisition module comprises an adjustable support and an image acquisition sensor, and the image acquisition sensor is installed on the flexible simulation station module through the adjustable support and can be adjusted in an all-dimensional and multi-dimensional mode.
Furthermore, the data acquisition module can also be used for acquiring real-time defect sample image information on line.
Furthermore, the defect sample image acquisition device is arranged on a flexible data acquisition rack, and the flexible data acquisition rack is used for abstractly simulating target installation stations and environments of all devices used for acquiring defect sample images on an actual production line.
Further, the flexible data acquisition rack further comprises an adjustable light source, a multi-dimensional adjustable clamp and a rack frame.
The adjustable light source is used for lighting the target detection object.
The multi-dimensional adjustable clamp is used for clamping a defect sample and can be adjusted in multiple dimensions.
The rack frame is used for bearing all devices of the flexible data acquisition rack.
Further, the gantry frame is movable and expandable in both axial and radial directions.
Furthermore, the off-line data acquisition rack is combined together in a building block mode, and the combination mode can be changed at will to simulate different production stations and environments.
Further, the defect sample image includes a visible light image, an infrared image, and an ultraviolet image.
Furthermore, the defect sample image acquisition device further comprises a data annotation module for performing data annotation on the acquired defect sample image.
The application provides a defect sample image acquisition device for industrial production, which acquires defect image data in a non-real-time manner in an off-line state to solve the problem of difficulty in acquiring the defect image data on line. The application provides a flexible data acquisition rack, is a low-cost simulation production station, but different production lines of various detection tasks of abstract simulation, emulation gather defect image data in a concentrative way. Moreover, the defect image data can be from a defect sample reserved in historical manual detection, and can also be a sample removed in the detection process by other detection means.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a defect sample image acquisition device applied to industrial production according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a flexible data acquisition gantry according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be fully and clearly described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all 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 application.
In order to facilitate understanding of technical solutions of the embodiments of the present application, some concepts related to the embodiments of the present application are first described below.
In the embodiment of the application, the flexible data acquisition rack is designed for solving the difficulty of on-line data acquisition. Since the number of defective parts generated during the production process is small, it is inefficient to collect data only in an online manner, and there is a possibility of interference with normal production. In contrast, defective part samples can be collected centrally and offline by the flexible data collection gantry, and normal production processes are not affected.
After the characteristics of the defective parts are collected in a centralized and offline mode by the aid of the flexible data collecting rack, the same equipment is installed on a production line, and only a small amount of pictures are collected in an online mode to be corrected, so that high-precision defect identification can be achieved. Moreover, a large amount of data acquisition and labeling work can be realized in a short time by using a small amount of manpower, and the training progress of the deep learning model is greatly improved. Compare in traditional image data collection and mark mode, the defect sample image acquisition device who is applied to industrial production that this application embodiment provided can raise the efficiency by a wide margin.
Referring to fig. 1, an embodiment of the present application provides a defect sample image capturing device applied to industrial production, which specifically includes: the flexible simulation station module, the data acquisition module, the data processing module, the control module and the data marking module.
In the embodiment of the application, the flexible simulation station module is used for simulating the target installation station of the defect sample image acquisition device on the actual production line. Specifically, the flexible simulation station module has the main function of simulating and restoring the image characteristics of the target installation station in the image information acquired by the image acquisition module at low cost. Including but not limited to visible light images, infrared image features, and the like. Typically the module consists of a fixture used in the actual work station and a conversion mounting structure enabling the fixture to be mounted on a bench.
In the embodiment of the application, the data acquisition module is arranged on the flexible simulation station module and used for acquiring the image information of the defect sample in an off-line manner and acquiring the image information of the real-time defect sample in an on-line manner. Specifically, the defect sample image includes a visible light image, an infrared image, and an ultraviolet image. It should be noted that the defect sample image provided by the embodiment of the present application is not limited to the visible light image, the infrared image and the ultraviolet image, as long as the image data in any format that can be collected by the collecting device is within the protection scope of the embodiment of the present application.
In the embodiment of the application, the data acquisition module contains adjustable support and image acquisition sensor, wherein, the image acquisition sensor passes through adjustable support and installs on flexible simulation station module for this image acquisition sensor can carry out all-round multidimension degree and adjust. Specifically, through adjustable support, the position adjustment in each position can be realized to the image acquisition module to the installation environment of adaptation low-cost flexible simulation station module is convenient for adjust.
In the embodiment of the application, the data annotation module is used for performing data annotation on the acquired defect sample image so as to save subsequent processing time.
In the embodiment of the application, the data processing module is used for processing the defect sample image information acquired offline, obtaining processing data and storing the processing data. Specifically, the data processing module can be used for processing not only the acquired image information but also other information, and the data processing module is pre-loaded with software required for processing images and related signals.
In the embodiment of the application, the control module is in signal connection with the data acquisition module and the data processing module and is used for controlling the operation of the data acquisition module and the data processing module.
Specifically, the control module in the embodiment of the present application is integrated with the data processing module, so that the space is saved, and the operation and management are facilitated.
In the implementation of the application, the defect sample image acquisition device is arranged on a flexible data acquisition rack, and the flexible data acquisition rack is used for abstractly simulating the target installation stations and environments of all devices for acquiring the defect sample images on the actual production line. Specifically, the flexible data acquisition rack is a low-cost simulation production station, an image acquisition module is integrated in the simulation station, and the flexible data acquisition rack is combined together in a building block mode, so that the combination mode can be changed at will to simulate different production stations and environments. Referring to fig. 2, a schematic structural diagram of a flexible data acquisition stage provided in the embodiment of the present application is shown, and as can be seen from the diagram, the flexible data acquisition stage specifically includes an adjustable light source, a defect sample image acquisition device, a multi-dimensional adjustable clamp, and a stage frame. The adjustable light source is used for lighting a target detection object, so that sample defects or the target object are more obvious, and the position, the brightness and the color of the adjustable light source can be freely adjusted; the multi-dimensional adjustable clamp is used for clamping the defect sample and can perform multi-dimensional adjustment; the rack frame is used for bearing all device-level accessories arranged on the flexible data acquisition rack, and each beam or plane of the rack frame can move and can be expanded along the axial direction and the radial direction so as to adapt to the acquisition working conditions of different data. The multidimensional adjustable support is used as a data acquisition module carrier, has the function of bearing a data acquisition module, and can be adjusted in multiple dimensions so as to adapt to different positions or working distances of a target detection object in the data acquisition process.
The defect sample image capturing device applied to industrial production provided by the embodiment of the present application will be described in detail from the practical application point of view.
Specifically, the method for acquiring the defect image information offline by the defect sample image acquisition device is as follows: and installing the defect products on a fixture of the flexible data acquisition rack in the same way on the production line by utilizing the defect products accumulated in production and the defect products generated in the current production process. And controlling the data acquisition module to acquire image data of the target defect by using the data processing module and the control module on the flexible data acquisition rack. Specifically, the collected image information may include, but is not limited to, a general visible light image, an infrared image, and an ultraviolet image, however, the image information must be able to reflect the essential factors of the defect image characteristics; and the data acquisition module transmits the data to the data processing module for processing and storing after acquiring the image data. After the defect sample image acquisition device provided by the embodiment of the application is used for defect feature extraction, the interpretation precision of the model which is comparable to that trained by the full online data acquisition method can be achieved only by adjusting a few online acquired images in practical application.
More specifically, the flexible data acquisition rack that this application embodiment provided has following characteristics: the rack is an abstract simulation of a target installation station of a future image detection system of a production line. The stage portion within the field of view of the image to which the data acquisition module can radiate needs to be similar to the actual characteristics of the production line, preferably based on the similarity of the image characteristics in the image acquired by the data acquisition module to those of the image characteristics at the similar position of the actual production line. The image features may include, but are not limited to, a general visible light image, an infrared image, and an ultraviolet image, as long as the image features that can be acquired are within the scope of the embodiments of the present application. In addition, the flexible data acquisition rack can simulate a new production station through building block type combination in a short time, has strong universality on application occasions, and can be quickly and conveniently used for data offline acquisition tasks of different projects through quick modification. The flexible data acquisition rack not only is abstract of application targets such as an actual production line, but also can be used for directly installing an image information acquisition module and a data processing module on a production line for acquiring data on line for application of real-time on-line data acquisition.
It should be noted that, in the data acquisition method provided in the embodiment of the present application, a virtual production line image environment may also be generated by simulating an image through a computer, and a defective product is synthesized into the virtual image environment in an image processing manner to perform defect image acquisition and feature extraction; and modeling defective products and characteristics by adopting a three-dimensional modeling mode, synthesizing the defective products and the characteristics into a virtual production environment, acquiring and extracting the characteristics of the defective images, and finally correcting the model by combining a small amount of real world target product image data.
It is further emphasized that during image acquisition, the target inspection piece is clamped using the clamp applied in the actual station, and then the clamp is securely mounted on the gantry via the conversion mounting structure. When the clamp of the actual station is too large or the cost is too high, other methods can be adopted to achieve the final target, and only in the visual field of the finally acquired image, the target workpiece and the background are similar to the actual installation position. Moreover, the image acquisition process is not carried out on the target production line, for example, the data acquisition module is installed on a training station which is not on the target production line, but is similar to a future target installation station and can be used as an equivalent substitute of the target installation station, so that the cost can be saved, and the normal operation of the production line is not influenced in the image acquisition process.
Compared with the prior art, the embodiment of the application has the following advantages:
firstly, in the process of acquiring image data of a defect sample, an original production line is not required to be changed.
Secondly, the defect sample image data acquisition process does not need to occupy the production resources and the process time of the existing production line.
The application provides a defect sample image acquisition device for industrial production specifically includes:
and the flexible simulation station module is used for simulating a target installation station of the defect sample image acquisition device on the actual production line.
And the data acquisition module is arranged on the flexible simulation station module and is used for acquiring image information of the defect sample in an off-line manner.
And the data processing module is used for processing the defect sample image information acquired offline to obtain processing data and storing the processing data.
And the control module is in signal connection with the data acquisition module and the data processing module and is used for controlling the operation of the data acquisition module and the data processing module.
According to the technical scheme, the defect sample image acquisition device applied to industrial production is used for acquiring defect image data in a non-real-time manner in an off-line state so as to solve the problem that the defect image data are difficult to acquire on line. The application provides a flexible data acquisition rack, is a low-cost simulation production station, but different production lines of various detection tasks of abstract simulation, emulation gather defect image data in a concentrative way. Moreover, the defect image data can be from a defect sample reserved in historical manual detection, and can also be a sample removed in the detection process by other detection means.
The present application has been described in detail with reference to specific embodiments and illustrative examples to enable those skilled in the art to understand or practice the present application, but the description is not intended to limit the present application. Those skilled in the art will appreciate that various equivalent substitutions, modifications or improvements may be made to the presently disclosed embodiments and implementations thereof without departing from the spirit and scope of the present disclosure, and these fall within the scope of the present disclosure. The protection scope of this application is subject to the appended claims.
Claims (10)
1. A defect sample image acquisition device applied to industrial production is characterized by comprising:
the flexible simulation station module is used for simulating a target installation station of the defect sample image acquisition device on the actual production line;
the data acquisition module is arranged on the flexible simulation station module and used for acquiring image information of the defect sample in an off-line manner;
the data processing module is used for processing the defect sample image information acquired offline to obtain processing data and storing the processing data;
and the control module is in signal connection with the data acquisition module and the data processing module and is used for controlling the operation of the data acquisition module and the data processing module.
2. The apparatus of claim 1, wherein the control module is integrated with the data processing module.
3. The defect sample image acquisition device applied to industrial production is characterized in that the data acquisition module comprises an adjustable bracket and an image acquisition sensor, and the image acquisition sensor is mounted on the flexible simulation station module through the adjustable bracket and can be adjusted in all directions and in multiple dimensions.
4. The defect sample image acquisition device applied to industrial production as claimed in claim 3, wherein the data acquisition module is further used for acquiring real-time defect sample image information on line.
5. The defect sample image acquisition device applied to industrial production according to any one of claims 1 to 4, wherein the defect sample image acquisition device is arranged on a flexible data acquisition platform, and the flexible data acquisition platform is used for abstractly simulating a target installation station and environment of all devices for acquiring defect sample images on an actual production line.
6. The defect sample image acquisition device applied to industrial production is characterized in that the flexible data acquisition rack further comprises an adjustable light source, a multi-dimensional adjustable clamp and a rack frame;
the adjustable light source is used for lighting a target detection object;
the multi-dimensional adjustable clamp is used for clamping a defect sample and can be used for multi-dimensional adjustment;
the rack frame is used for bearing all devices of the flexible data acquisition rack.
7. The defect sample image acquisition device applied to industrial production according to claim 6, wherein the gantry frame is movable and can be expanded in the axial direction and the radial direction.
8. The apparatus as claimed in claim 7, wherein the flexible data acquisition platforms are combined together in a building block manner, and the combination of the flexible data acquisition platforms can be changed arbitrarily to simulate different production stations and environments.
9. The defect sample image acquisition device applied to industrial production according to claim 1, wherein the defect sample image comprises a visible light image, an infrared image and an ultraviolet image.
10. The apparatus of claim 9, further comprising a data annotation module for performing data annotation on the acquired defect sample image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111636449.3A CN114399473A (en) | 2021-12-29 | 2021-12-29 | Defect sample image acquisition device applied to industrial production |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111636449.3A CN114399473A (en) | 2021-12-29 | 2021-12-29 | Defect sample image acquisition device applied to industrial production |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114399473A true CN114399473A (en) | 2022-04-26 |
Family
ID=81228176
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111636449.3A Pending CN114399473A (en) | 2021-12-29 | 2021-12-29 | Defect sample image acquisition device applied to industrial production |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114399473A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114863424A (en) * | 2022-05-07 | 2022-08-05 | 天津优海云图科技有限公司 | Classification data set construction method for instant noodle flaw detection |
-
2021
- 2021-12-29 CN CN202111636449.3A patent/CN114399473A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114863424A (en) * | 2022-05-07 | 2022-08-05 | 天津优海云图科技有限公司 | Classification data set construction method for instant noodle flaw detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104655641A (en) | High-precision full-automatic FPC (Flexible Printed Circuit) defect detecting device and detecting process | |
CN110293559B (en) | Installation method for automatically identifying, positioning and aligning | |
CN111968048B (en) | Method and system for enhancing image data of less power inspection samples | |
CN109405755B (en) | Large-size pipe plate aperture and pitch measuring device and measuring method | |
CN113900436B (en) | Inspection control method, inspection control device, inspection control equipment and storage medium | |
CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
CN106124512A (en) | Suspension type monorail box beam inspection device | |
CN115932530B (en) | Method for calibrating semiconductor detection equipment | |
CN108009547A (en) | Method and device for identifying nameplate of substation equipment | |
CN114399473A (en) | Defect sample image acquisition device applied to industrial production | |
CN113935971A (en) | Method and device for detecting surface defects of composite material | |
CN108844961A (en) | A kind of temperature controller case vision detection system and method | |
CN111127445A (en) | Distribution network line high-temperature area detection method and system based on deep learning | |
CN211827005U (en) | Multi-functional detection device of five-axis numerical control machine tool based on multi-eye vision | |
CN111189401B (en) | Real-time automatic measurement method and system for shield tail clearance | |
CN113628159A (en) | Full-automatic training method and device based on deep learning network and storage medium | |
CN112256060A (en) | Method for automatically naming pictures for automatic inspection of power transmission line unmanned aerial vehicle in real time | |
CN109015632A (en) | A kind of robot hand end localization method | |
CN110097042A (en) | A kind of the character machining system and detection method of the shaver shell with radian | |
CN211604116U (en) | Projection type augmented reality fastener assembly guiding and detecting device | |
CN113970560A (en) | Defect three-dimensional detection method based on multi-sensor fusion | |
CN113034620A (en) | Correction method, correction device, computer-readable storage medium, and computer apparatus | |
CN109622404B (en) | Automatic sorting system and method for micro-workpieces based on machine vision | |
CN117006972A (en) | Object detection method, device, equipment, three-dimensional scanning system and storage medium | |
CN204565789U (en) | CNC vision secondary process system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |