CN217332186U - Plank AI visual defect detection device - Google Patents
Plank AI visual defect detection device Download PDFInfo
- Publication number
- CN217332186U CN217332186U CN202121238015.3U CN202121238015U CN217332186U CN 217332186 U CN217332186 U CN 217332186U CN 202121238015 U CN202121238015 U CN 202121238015U CN 217332186 U CN217332186 U CN 217332186U
- Authority
- CN
- China
- Prior art keywords
- assembly line
- defect detection
- wood board
- visual defect
- reverse side
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model discloses a plank AI visual defect detection device, the device detect the assembly line including openly detecting the assembly line and reverse side, openly detect the assembly line and reverse side and detect and connect through tilting mechanism between the assembly line, openly detect the assembly line entrance and be provided with balance feed mechanism, openly detect the assembly line and be equipped with positive visual defect detection device, reverse side detection assembly line is equipped with reverse side visual defect detection device. The utility model discloses an automatic system and visual system's integration, this system have saved the process of artifical categorised plank, have improved production efficiency and categorised accuracy, also can provide the guarantee for the quality is traceed back simultaneously.
Description
Technical Field
The utility model belongs to the technical field of machine vision detects, especially, relate to plank AI visual defect detection device.
Background
With the rapid development of automated production in modern manufacturing industry, many industries have higher requirements for inspection and measurement in industrial production. For example, inspection of a print packaging process, inspection of a package of a semiconductor chip, inspection of a product quality in a production line of a factory, inspection of high-precision parts, and the like. In these applications, most automated plants require high volume production, with part of the assembly accuracy requirements being very high. The traditional manual detection method can not meet the current process requirements, and the development and progress of the manufacturing industry are limited to a great extent. On the one hand, the traditional manual detection method has low efficiency, high error rate and high labor cost; on the other hand, the physiological limits of the human eye also result in human being unable to achieve the accuracy of computer detection techniques in this respect. The rapidity, reliability and accuracy of the computer are combined with the intellectualization of human vision, so that the machine vision is more and more widely applied to industrial detection.
Machine vision mainly uses a computer to simulate the visual function of a human, but not only is the simple extension of human eyes, but also has a part of functions of human brain, namely, information is extracted from the image of an objective object, processed and understood, and finally the information is used for actual detection, measurement and control.
Wood defects refer to various defects present in wood that can affect the quality and use value of the wood. Including wood natural defects, drying defects, processing defects. The manual detection method is adopted to detect the processing defects, so that the efficiency is low, the error rate is high, and a large amount of labor cost is consumed.
In the process of cutting the wood board, N different types of defective wood boards usually appear on the production line of a factory. Because each wood board has special texture, a method of manual experience judgment is generally adopted when a traditional factory classifies the defects of the wood boards, the method is low in efficiency, the defects are difficult to trace, and the like, and the streamlined operation cannot be realized.
Disclosure of Invention
An object of the utility model is to overcome prior art defect, provide plank AI visual defect detection device, the utility model discloses an automatic system and visual system's integration, this system has saved the process of artifical categorised plank, has improved production efficiency and categorised accuracy, also can provide the guarantee for the quality is traceed back simultaneously.
The purpose of the utility model is realized through the following technical scheme:
plank AI visual defect detection device includes: the front side detection assembly line and the back side detection assembly line are connected through the turnover mechanism, the inlet of the front side detection assembly line is provided with the swing disc feeding mechanism, the front side detection assembly line is provided with the front side visual defect detection device, and the back side detection assembly line is provided with the back side visual defect detection device.
Furthermore, the outlet of the reverse side detection production line is also connected with a rejection production line, and the rejection production line is provided with one or more rejection stations.
Further, the front visual defect detection device comprises a front line scanning camera, a light source and a bracket for fixing the front line scanning camera and the light source on the production line; the reverse side visual defect detection device comprises a reverse side scanning camera, a light source and a bracket for fixing the reverse side scanning camera and the light source on the production line; the front side line scanning camera and the back side line scanning camera are in communication connection with the data processing center.
On the other hand, the utility model also provides a plank AI visual defect detection method, include:
s11: placing the wood board to be detected on a swinging plate feeding mechanism, and performing high-definition imaging when the wood board passes through a front visual defect detection device of a front detection assembly line;
s12: preprocessing the high-definition image, detecting and positioning, and sending the high-definition image into a board visual defect detection model for AI algorithm defect identification;
s13: if the wood board is defective, recording is carried out, the defective wood board is removed when passing through a removal assembly line, if the wood board is not defective, the wood board enters a reverse side detection assembly line through a turnover mechanism, and high-definition imaging is carried out when the wood board passes through a reverse side visual defect detection device of the reverse side detection assembly line;
s14: step S12 is executed, if the wood board is defective, recording is carried out, the defective wood board is removed when passing through the removing assembly line, and if the wood board is not defective, the step S15 is executed;
s15: when the front surface and the back surface of the wood board are not detected with defects, the wood board enters a production line.
Further, the specific construction method of the wood board visual defect detection model comprises the following steps:
s21: collecting the data of the picture of the surface of the shot wood board by a front visual defect detection device or a back visual defect detection device;
s22: carrying out data annotation on the picture data on the surface of the wood board;
s23: and training the marked data to obtain a wood board visual defect detection model.
Further, the wood board surface picture data comprise a wood board defect picture and a normal wood board picture.
Further, the method also comprises an accuracy verification step:
s24: deploying the model to a data processing center;
s25: carrying out defect detection on the plurality of wood boards by using the wood board visual defect detection model;
s26: the detection accuracy of the wood board visual defect detection model is rechecked, the absolute value of the error is qualified within 1%, otherwise, the absolute value is unqualified;
s27: and judging whether the detection accuracy of the wood board visual defect detection model reaches 95%, if so, determining that the wood board visual defect detection model is qualified, otherwise, determining that the wood board visual defect detection model is not qualified.
Further, the AI algorithm defect identification performed by the wood board visual defect detection model specifically comprises:
s121: inputting the preprocessed wood floor picture into a pre-trained ResNet50 neural network to obtain a corresponding feature map;
s122: setting an ROI corresponding to the wood floor picture for each point in the obtained feature map, so that each wood floor picture can obtain a plurality of candidate ROIs;
s123: sending the candidate ROI into an RPN network for binary classification and BB regression, and filtering out partial candidate ROI;
s124: ROIAlign operation is carried out on the rest ROIs;
s125: and classifying the rest ROI, performing BB regression and generating MASK to obtain a final defect identification result.
On the other hand, the utility model also provides a computer equipment, computer equipment includes treater and memory, the memory stores computer program, computer program by the treater is loaded and is executed in order to realize the plank AI visual defect detection method as in any one above.
In another aspect, the present invention further provides a computer-readable storage medium, in which a computer program is stored, the computer program being loaded and executed by a processor to implement the wood board AI visual defect detection method according to any one of the above embodiments.
The beneficial effects of the utility model reside in that:
the utility model discloses an automatic system and visual system's integration, this system have saved the process of artifical categorised plank, have improved production efficiency and categorised accuracy, also can provide the guarantee for the quality is traceed back simultaneously.
The method has low implementation cost, strong flexibility and expandability, and the accuracy of the whole set of system can be continuously improved in the operation process. Enterprises can realize self-growth on the system according to own actual conditions, and the economic value brought by a production line is improved while the labor cost is reduced.
Drawings
Fig. 1 is a schematic projection diagram of a wood board AI visual defect detecting device provided in embodiment 1 of the present invention;
fig. 2 is a schematic side view of a wood board AI visual defect detection apparatus provided in embodiment 1 of the present invention;
fig. 3 is a block diagram of a flow chart of a wood board AI visual defect detection method provided in embodiment 2 of the present invention;
fig. 4 is a block diagram of an algorithm model design implementation flow in the wood board AI visual defect detection method provided in embodiment 2 of the present invention;
fig. 5 is a block diagram of the flow chart of AI algorithm defect recognition performed by the board visual defect detection model in the board AI visual defect detection method provided by embodiment 2 of the present invention.
Reference numerals: 1-a swing plate feeding mechanism, 2-a front visual defect detection device, 3-a front detection assembly line, 4-a turnover mechanism, 5-a back visual defect detection device and 6-a back detection assembly line.
Detailed Description
The following description of the embodiments of the present invention is provided for illustrative purposes, and other advantages and effects of the present invention will be readily apparent to those skilled in the art from the disclosure herein. The present invention can also be implemented or applied through other different specific embodiments, and various details in the present specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that, in order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described below, and it is obvious that the described embodiments are part of the embodiments of the present invention, but not all of the embodiments.
Thus, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative efforts belong to the protection scope of the present invention.
Example 1
As shown in the attached figures 1 and 2, the projection schematic diagram and the side schematic diagram of the wood board AI visual defect detection device provided by the embodiment are respectively shown, the device specifically comprises a front detection assembly line and a back detection assembly line, the front detection assembly line and the back detection assembly line are connected through a turnover mechanism, a swing disc feeding mechanism is arranged at the inlet of the front detection assembly line, the front detection assembly line is provided with a front visual defect detection device, and the back detection assembly line is provided with a back visual defect detection device. The outlet of the reverse side detection production line is also connected with a rejection production line, the rejection production line is provided with one or more rejection stations, and the rejection production line is not shown in the figure.
The front visual defect detection device comprises a front line scanning camera, a light source and a bracket for fixing the front line scanning camera and the light source on the production line; the reverse side visual defect detection device comprises a reverse side scanning camera, a light source and a bracket for fixing the reverse side scanning camera and the light source on the production line; the front side line scanning camera and the back side line scanning camera are in communication connection with the data processing center.
The wood board to be detected is placed in the swing disc feeding mechanism, passes through the lower portion of the visual lens through the conveying belt, is subjected to high-definition imaging firstly, is subjected to image preprocessing, and is sent to the neural network model for AI algorithm defect identification through detection and positioning. If the board is defective, the algorithm will record that the board is defective and reject it as it passes through the reject mechanism. If the wood board has no defect, the wood board enters the reverse side detection mechanism of the wood board through the turnover mechanism, and if the wood board also has no defect on the reverse side, the wood board enters the next production line through the material distribution production line. If the reverse side is defective, then the station is removed again and the next production line is not entered.
The plank AI visual defect detection device that this embodiment provided, through automatic system and visual system's integration, this system has saved the process of artifical categorised plank, has improved production efficiency and categorised accuracy, also can provide the guarantee for the quality is traceed back simultaneously.
Example 2
As shown in fig. 3, a flow chart of the wood board AI visual defect detection method provided in this embodiment is specifically shown, and the method specifically includes:
s11: placing the wood board to be detected on a swinging plate feeding mechanism, and performing high-definition imaging when the wood board passes through a front visual defect detection device of a front detection assembly line;
s12: preprocessing the high-definition image, detecting and positioning, and sending the high-definition image into a board visual defect detection model for AI algorithm defect identification;
s13: if the wood board is defective, recording is carried out, the defective wood board is removed when passing through a removal assembly line, if the wood board is not defective, the wood board enters a reverse side detection assembly line through a turnover mechanism, and high-definition imaging is carried out when the wood board passes through a reverse side visual defect detection device of the reverse side detection assembly line;
s14: step S12 is executed, if the wood board is defective, recording is carried out, the defective wood board is removed when passing through the removing assembly line, and if the wood board is not defective, the step S15 is executed;
s15: when the front surface and the back surface of the wood board are not detected with defects, the wood board enters a production line.
The specific construction method of the wood board visual defect detection model comprises the following steps:
s21: collecting the data of the picture of the surface of the shot wood board by a front visual defect detection device or a back visual defect detection device; and (4) preparing equipment in advance to collect the picture data of the surface of the shot wood board. Collecting a large number of wood board pictures according to requirements, wherein the pictures comprise wood board defect pictures and normal wood board pictures.
S22: carrying out data annotation on the picture data on the surface of the wood board;
s23: and training the marked data to obtain a wood board visual defect detection model. The difficulty of the wood board visual identification algorithm is to accurately find the positions of the defects of the wood board. In an actual scene, under the influence of illumination and shielding, the algorithm model cannot be well positioned at the position of the wood board, and the conditions of false detection and missed detection also exist. Therefore, in order to accurately predict the number of the defects on each wood board, two different algorithms of detecting and dividing the defects of the wood board are respectively tested to position the defects of the wood board. The detection algorithm can detect the specific position of the board in the image, and the segmentation algorithm can calculate which pixels belong to the defects and which pixels belong to the background. The example segmentation algorithm can not only be used for positioning the wood board, but also be used for calculating the part of the pixel area belonging to the defect. And finally, taking 10 pictures as a group of test data in order to improve the accuracy of identifying the defects of the wood board, and then taking the mode of the prediction results of the ten pictures as the inventory number of the group of pictures. The test result proves that the strength segmentation algorithm can well complete the detection task of the defects of the wood board, and all indexes meet the requirements.
After the wood board visual defect detection model is specifically constructed, the method further comprises the following accuracy verification steps:
s24: deploying the model to a data processing center;
s25: carrying out defect detection on the plurality of wood boards by using the wood board visual defect detection model; and taking 2000 pictures as a test set, and performing defect prediction reasoning. The 2000 boards are classified and selected manually, and after selection is finished, the 2000 boards are processed by the vision equipment. And (4) one person is selected for detailed review, and the absolute value of the error between the machine detection accuracy and the manual detection accuracy is qualified within 1% in the same time.
S26: the detection accuracy of the wood board visual defect detection model is rechecked, the absolute value of the error is qualified within 1%, otherwise, the absolute value is unqualified;
s27: and judging whether the detection accuracy of the wood board visual defect detection model reaches 95%, if so, determining that the wood board visual defect detection model is qualified, otherwise, determining that the wood board visual defect detection model is unqualified.
And packaging and delivering the AI model which meets the requirements, and using the AI model on line.
The board AI visual defect detection method provided by the embodiment can be combined with the board AI visual defect detection device provided by the embodiment 1 to obtain a whole set of board automatic visual recognition machine equipment. The wood board to be detected is placed in the swing disc feeding mechanism, passes through the lower portion of the visual lens through the conveying belt, is subjected to high-definition imaging firstly, is subjected to image preprocessing, and is sent to the neural network model for AI algorithm defect identification through detection and positioning. If the board is defective, the algorithm will record that the board is defective and reject it as it passes through the reject mechanism. If the wood board has no defect, the wood board enters the reverse side detection mechanism of the wood board through the turnover mechanism, and if the wood board also has no defect on the reverse side, the wood board enters the next production line through the material distribution production line. If the reverse side is defective, then the station is removed again and the next production line is not entered.
The whole set of equipment has strong expansibility and self-optimization capability in the operation process, the identification accuracy of the algorithm can be continuously improved in the continuous operation process, and even if accidental identification failure or identification errors occur in a certain special case of a certain defect type wood board, the wood board characteristics can be accurately identified in the next special condition after being added into a training sample. And because enough sample training is carried out before the algorithm is obtained, the occurrence probability of the situation is low, and the system can stably run in the initial stage.
Example 3
The preferred embodiment provides a computer device, which can implement the steps in any embodiment of the wood board AI visual defect detection method provided in the embodiment of the present application, and therefore, the beneficial effects of the wood board AI visual defect detection method provided in the embodiment of the present application can be achieved, which are detailed in the foregoing embodiment and will not be described herein again.
Example 4
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor. Therefore, the embodiment of the present invention provides a storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps of any embodiment of the method for detecting the visual defects of the wood board AI provided by the embodiment of the present invention.
Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
Because the instruction of storage in this storage medium can carry out the utility model discloses step in the arbitrary plank AI visual defect detection method embodiment that the embodiment provided, consequently, can realize the utility model discloses the beneficial effect that arbitrary plank AI visual defect detection method that the embodiment provided can realize sees in detail the embodiment in the foregoing, does not reiterate here.
The aforesaid the utility model discloses basic embodiment and each further alternative can the independent assortment in order to form a plurality of embodiments, is the utility model discloses can adopt and claim the embodiment of protection. In the scheme of the utility model, each selection example can be combined with any other basic examples and selection examples at will. Numerous combinations will be known to those skilled in the art.
The above description is only exemplary of the present invention and should not be taken as limiting the scope of the present invention, as any modifications, equivalents, improvements and the like made within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (3)
1. Plank AI visual defect detection device, its characterized in that includes: openly detect assembly line and reverse side and detect the assembly line, openly detect and connect through tilting mechanism between the assembly line and the reverse side detects the assembly line, openly detect the assembly line entrance and be provided with balance feed mechanism, openly detect the assembly line and be equipped with positive visual defect detection device, reverse side detects the assembly line and is equipped with reverse side visual defect detection device.
2. The wood board AI visual defect detection apparatus of claim 1 wherein the reverse side detection assembly line outlet is further connected to a rejection assembly line, the rejection assembly line having one or more rejection stations.
3. The wood board AI visual defect detecting device according to claim 1, wherein the front visual defect detecting device includes a front line scanning camera, a light source and a bracket for fixing the front line scanning camera and the light source on a production line; the reverse side visual defect detection device comprises a reverse side scanning camera, a light source and a bracket for fixing the reverse side scanning camera and the light source on the production line; the front side line scanning camera and the back side line scanning camera are in communication connection with the data processing center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202121238015.3U CN217332186U (en) | 2021-06-03 | 2021-06-03 | Plank AI visual defect detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202121238015.3U CN217332186U (en) | 2021-06-03 | 2021-06-03 | Plank AI visual defect detection device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN217332186U true CN217332186U (en) | 2022-08-30 |
Family
ID=82944789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202121238015.3U Active CN217332186U (en) | 2021-06-03 | 2021-06-03 | Plank AI visual defect detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN217332186U (en) |
-
2021
- 2021-06-03 CN CN202121238015.3U patent/CN217332186U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10964004B2 (en) | Automated optical inspection method using deep learning and apparatus, computer program for performing the method, computer-readable storage medium storing the computer program, and deep learning system thereof | |
| CN111325713B (en) | Neural network-based wood defect detection method, system and storage medium | |
| CN109829914B (en) | Method and device for detecting product defects | |
| CN110659660B (en) | Automatic optical detection classification equipment using deep learning system and training equipment thereof | |
| CN109724984B (en) | Defect detection and identification device and method based on deep learning algorithm | |
| CN111189837B (en) | Cigarette appearance online detection method and device | |
| CN110956191B (en) | Classifier, classification method and classification system based on probability fusion | |
| CN113744244B (en) | Online visual detection system for measuring distance from edge of lithium battery pole piece to edge of pole lug | |
| US11657599B2 (en) | Method for detecting appearance of six sides of chip multi-layer ceramic capacitor based on artificial intelligence | |
| CN110239997A (en) | A kind of automatic inspection rejects method and apparatus of rewinding machine | |
| CN111712769A (en) | Method, apparatus, system, and program for setting lighting condition, and storage medium | |
| CN113240673B (en) | Defect detection method, defect detection device, electronic equipment and storage medium | |
| CN112258459A (en) | Lithium battery defect detection method based on integrated deep learning | |
| CN115953373B (en) | Glass defect detection method, device, electronic equipment and storage medium | |
| CN116385430A (en) | Machine vision flaw detection method, device, medium and equipment | |
| CN117392042A (en) | Defect detection method, defect detection apparatus, and storage medium | |
| CN114612418A (en) | Method, device and system for detecting surface defects of mouse shell and electronic equipment | |
| CN110095475A (en) | A kind of tin graphed sheet vision detection system and tin graphed sheet pattern detecting method | |
| CN113267506A (en) | Wood board AI visual defect detection device, method, equipment and medium | |
| CN114549414A (en) | Abnormal change detection method and system for track data | |
| CN217332186U (en) | Plank AI visual defect detection device | |
| CN116958035A (en) | Product part defect detection method, device, medium and electronic equipment | |
| CN116342502A (en) | Industrial vision detection method based on deep learning | |
| JP3892258B2 (en) | Automatic inspection device and automatic inspection method | |
| CN112215149A (en) | Accessory sorting system and method based on visual detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |