CN112016555A - Machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloy - Google Patents
Machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloy Download PDFInfo
- Publication number
- CN112016555A CN112016555A CN202010844070.0A CN202010844070A CN112016555A CN 112016555 A CN112016555 A CN 112016555A CN 202010844070 A CN202010844070 A CN 202010844070A CN 112016555 A CN112016555 A CN 112016555A
- Authority
- CN
- China
- Prior art keywords
- crack
- growth
- aluminum alloy
- image
- learning
- 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
- 229910000838 Al alloy Inorganic materials 0.000 title claims abstract description 25
- 238000005336 cracking Methods 0.000 title claims abstract description 15
- 238000010801 machine learning Methods 0.000 title claims abstract description 14
- 230000012010 growth Effects 0.000 claims abstract description 36
- 230000000877 morphologic effect Effects 0.000 claims abstract description 23
- 230000000977 initiatory effect Effects 0.000 claims abstract description 20
- 238000001914 filtration Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 16
- 239000000956 alloy Substances 0.000 claims abstract description 11
- 238000003672 processing method Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 7
- 230000009646 cyclic growth Effects 0.000 claims description 3
- 230000004931 aggregating effect Effects 0.000 claims description 2
- 229910045601 alloy Inorganic materials 0.000 claims 5
- 229910001095 light aluminium alloy Inorganic materials 0.000 claims 5
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 239000000463 material Substances 0.000 abstract description 4
- 238000004891 communication Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 description 12
- 230000007797 corrosion Effects 0.000 description 11
- 238000005260 corrosion Methods 0.000 description 11
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 239000012266 salt solution Substances 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000011780 sodium chloride Substances 0.000 description 1
- 238000004901 spalling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
Abstract
The invention relates to the technical field of aviation aluminum alloy, in particular to an image recognition algorithm based on machine learning and aiming at surface cracking of aviation aluminum alloy, which comprises the following steps: s1, processing the image by adopting a self-adaptive filtering algorithm based on semi-supervised learning; s2, segmenting the image by adopting a morphological processing method, and determining the initiation edge of the crack; s3, positioning the position of the crack by introducing a morphological concept into a communication algorithm based on the region growth of the image growth, and aiming at the defects of the prior art in the accuracy and the real-time property of the image recognition of the crack on the surface material of the airplane in the aviation field, providing a crack recognition algorithm with high speed and high accuracy, which can monitor whether the aluminum alloy material on the surface of the airplane has the crack or not and the length of the crack in real time, and can reduce the safety incident caused by the failure of the surface material of the airplane for preventing the structural failure of the airplane.
Description
Technical Field
The invention relates to the technical field of aviation aluminum alloy, in particular to an image recognition algorithm based on machine learning and aiming at surface cracking of aviation aluminum alloy.
Background
The aviation aluminum alloy has the advantages of low density, high strength and the like, and is widely applied to some important bearing structures of airplanes, such as skins, fuselages, undercarriages, partition frames, wing ribs and the like. The aluminum alloy material has strong environmental sensitivity, and is easy to generate local corrosion such as pitting corrosion, intergranular corrosion, spalling corrosion and the like in the service process. The stress corrosion cracking of the aviation aluminum alloy is one of important failure modes of an airplane aluminum alloy structure, and brings great hidden danger to the safe operation of an airplane. Aiming at the problem of stress corrosion cracking of aviation aluminum alloy in salt solution, the method for analyzing the crack initiation and expansion rules of the aluminum alloy material under different working conditions has important significance for preventing the failure of the airplane structure, improving the corrosion management method and prolonging the service life of the airplane.
At present, the domestic image recognition algorithm aiming at the cracks mainly adopts two types of algorithms: (1) a crack image enhancement and segmentation method; (2) and (4) a crack image feature extraction technology combined with machine learning. The existing algorithm needs to spend a great deal of time cost in practical application and does not meet the requirement of the aviation field on real-time property. In order to improve the accuracy and real-time performance of crack image identification, the aluminum alloy test piece (AA7075) is researched to have cracks in a normal-temperature salt solution, and the following problems are found to exist: (1) because some cracks are extremely fine, the initiation positions of the cracks are difficult to determine; (2) various noises exist on the surface of the test piece, and the accuracy of crack identification results is interfered; (3) the thinnest spot at the crack tip is usually only 1 pixel and can easily be ignored.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an image recognition algorithm based on machine learning for aviation aluminum alloy surface cracking.
In order to achieve the purpose, the invention adopts the following technical scheme:
the image recognition algorithm based on machine learning for surface cracking of the aviation aluminum alloy comprises the following steps:
s1, processing the image by adopting a self-adaptive filtering algorithm based on semi-supervised learning, wherein the filtering algorithm comprises two parts: the first part of contents is characterized in that a gray value interval with a good filtering effect is found by analyzing the learning result of every 50 gray values of 0-255, and the interval is marked as [ n-50, n +50], the second part of contents is that the learning result of the first learning is learned every 10 gray values in the [ n-50, n +50] interval, and finally the gray value with the best effect is obtained and is used as the gray value used for filtering;
s2, segmenting the image by adopting a morphological processing method, determining the crack initiation edge, analyzing the crack width and length by collecting a large number of crack samples, performing morphological processing by adopting different shapes, and further determining which morphological image processing method is adopted to position the crack initiation edge;
and S3, identifying the crack by adopting a modified image growth algorithm according to the initiation edge determined in the step, and positioning the position of the crack by introducing a morphological concept into a connection algorithm based on the region growth of the image growth.
Preferably, in S3, the region growing is a process of gradually aggregating one pixel or sub-region into a complete independent connected region according to a predefined growing rule.
Preferably, the independent connected region forming process includes the steps of: for the image interested target region R, z is a seed point found in advance on the region R, pixels which are in a certain neighborhood with the seed point z and meet the similarity criterion are gradually combined into a seed group according to a specified growth criterion for the growth of the next stage, and the cyclic growth is continuously carried out until the growth stopping condition is met, so that the process of growing the interested region from one seed point into an independent connected region is completed.
Preferably, the region growing algorithm is generally implemented in three steps: determining a growing seed point; defining a growth criterion; growth stop conditions were determined.
Preferably, the selection of growing seed points: using morphological processing methods, a rectangular pattern was used to locate the initiation edge of the crack.
Preferably, in S3, connectivity of 5 neighboring pixels of the pixel where the growth point is located is calculated, where whether the connectivity is the standard is to determine whether gray values of the pixel of the growth point and the neighboring pixels are consistent, and if the gray values are equal, the connection is determined, and otherwise, the connection is determined.
The invention has the beneficial effects that: aiming at the defects of accuracy and instantaneity of image recognition of cracks on the surface material of the airplane in the aviation field in the prior art, the crack recognition algorithm with high speed and high accuracy is provided, whether cracks appear on the surface aluminum alloy material of the airplane and the length of the cracks can be monitored in real time, the crack initiation and expansion rules of the aluminum alloy material under different load conditions are verified through a large number of experiments, the time and the position of the cracks possibly appearing on the surface aluminum alloy material of the airplane are further predicted, the structural failure of the airplane is prevented, and safety incidents caused by the failure of the surface material of the airplane are reduced.
Drawings
FIG. 1 is a schematic diagram comparing different growth criteria proposed by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1, the image recognition algorithm based on machine learning for surface cracking of the aviation aluminum alloy comprises the following steps:
s1, processing the image by adopting a self-adaptive filtering algorithm based on semi-supervised learning, wherein the self-adaptive filtering algorithm specifically comprises two parts of learning contents: in the first learning process, the optimal gray value interval is determined by performing filtering processing on every 50 gray values of 0-255 and by performing comparative analysis on all learning results, and 500 samples are adopted, wherein 200 samples are taken as learning samples, and 300 samples are taken as testing samples. The method comprises the steps of equally dividing 255 pixels into 52 gray values every 50 pixels, 0, 50, 100, 150, …, 250 and 255, determining the optimal gray value range to be [ n-50, n +50] through the result after learning by adopting an adaptive filtering algorithm, learning every 10 gray values in the [ n-50, n +50] interval by aiming at the result of the first learning in the second part of learning content, and finally obtaining the gray value with the best effect as the gray value used by the adaptive filtering algorithm;
and S2, secondly, segmenting the image by adopting a morphological processing method, and determining the initiation edge of the crack. In the experimental process, the surface of the test piece is not smooth, corrosion spots exist, and the length and the width of the actual crack are very small due to the small size of the test piece, so that great difficulty is brought to the positioning of the crack. The method comprises the steps of collecting a large number of crack samples, analyzing the width and the length of the cracks, performing morphological processing by adopting different shapes, and further determining which morphological image processing method is adopted to position the initiation edge of the cracks (namely the position where the cracks begin to appear);
s3, starting from the initiation edge determined in the above step, identifying the crack using a modified image growth algorithm, the position of the crack is positioned by introducing a morphological concept into a connected algorithm based on the region growth of the image growth, the basic idea of the region growth is to gradually aggregate one pixel or a sub-region into a complete independent connected region process according to a growth criterion defined in advance, for the image interested target region R, z is a seed point found in advance on the region R, pixels which are in certain proximity with the seed point z and meet the similarity criterion are gradually combined into a seed group according to a specified growth criterion for the growth of the next stage, the cyclic growth is continuously carried out until the growth stop condition is met, therefore, the process of growing the interested region from one seed point to an independent connected region is completed, and the region growing algorithm is generally realized by three steps: determining a growing seed point; defining a growth criterion; growth stop conditions were determined.
The invention improves the traditional region growing algorithm, and the specific improvement measures are as follows:
(1) selection of growing seed points: using morphological processing methods, a rectangular pattern was used to locate the initiation edge of the crack.
(2) Improving the growth criterion: due to the fact that noise and interference points exist in an image and a large number of photos are required to be processed in real time, the number of pixels of a connected region of interest to be processed is too large (larger than 500) due to the large number of interference points, a copy of a function is built through a large number of recursive calls, and a large amount of time and memory are consumed.
And respectively calculating the connectivity of 5 neighborhood pixels of the pixel where the growing point is located, wherein the standard of whether the connectivity is the standard is to judge whether the gray values of the pixel of the growing point and the pixels of the neighborhood are consistent, if the gray values are equal, the connectivity is determined, and if not, the connectivity is determined. It has been found experimentally that the improved image-growth-based connectivity algorithm results in crack location results with insufficient accuracy, and further morphological processing is required to locate the exact location of the crack. The crack position is determined under the double constraints of a rectangular morphological image processing technology and a fixed gray value range.
The invention discloses an image processing algorithm for quickly identifying cracks when cracks appear on the surface of an aviation aluminum alloy. The method comprises the steps of loading an aluminum alloy test piece (AA7075) in a normal-temperature salt solution (3.5% NaCl solution), shooting a surface digital image data set of the test piece in the stress corrosion process, and identifying the length and the width of cracks in the digital image data set by adopting a self-adaptive filtering algorithm based on semi-supervised learning and an improved image communication algorithm. In the experiment of the invention, the filter effect between the gray values of 150 and 250 is found to be better by carrying out adaptive filter learning on 500 collected images (one image can be obtained by one aluminum alloy test piece crack), the filter processing is carried out on 500 images at the gray values of 150, 160, … and 250 (the interval is 10) respectively, the filter result is optimal when the gray value is 160 is finally found, and the optimal gray value of the adaptive filter is finally obtained by learning and is 160. After the image is filtered, a morphological image processing method is needed to determine the crack initiation edge, in the experimental process, the rectangular shape with 1 x 1 pixel to the rectangular shape with 1 x N (N < 10) are adopted for processing, and the crack initiation edge obtained after the rectangular shape with 1 x 7 pixels is processed is found to have better effect through the processing result. And then determining the position of the initial crack by adopting an improved image region growing algorithm according to the growth point seeds determined by the crack initiation edge. Finally, determining the position information of the crack accurately by adopting a morphological image processing technology and double constraints of fixed gray values, and analyzing morphological image processing results of different shapes through experiments to form a rectangle from 1 × 1 pixel to N × 1 pixel; it was found that the use of a rectangle of 6 x 1 pixels gave better results. The method can solve the problems of surface corrosion spots, unsmooth surface of the test piece and the like of the test piece in the stress corrosion environment, and performs a self-adaptive filtering algorithm and an improved image communication algorithm on the image according to the characteristic that the local gray value of the crack in the image of the test piece is large in change and continuously changed, determines the crack initiation and expansion area through a morphological image positioning algorithm, and accurately positions the position of the crack on the surface of the aviation aluminum alloy test piece.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (6)
1. The image recognition algorithm based on machine learning for surface cracking of the aviation aluminum alloy is characterized by comprising the following steps of:
s1, processing the image by adopting a self-adaptive filtering algorithm based on semi-supervised learning, wherein the filtering algorithm comprises two parts: the first part of contents is characterized in that a gray value interval with a good filtering effect is found by analyzing the learning result of every 50 gray values of 0-255, and the interval is marked as [ n-50, n +50], the second part of contents is that the learning result of the first learning is learned every 10 gray values in the [ n-50, n +50] interval, and finally the gray value with the best effect is obtained and is used as the gray value used for filtering;
s2, segmenting the image by adopting a morphological processing method, determining the crack initiation edge, analyzing the crack width and length by collecting a large number of crack samples, performing morphological processing by adopting different shapes, and further determining which morphological image processing method is adopted to position the crack initiation edge;
and S3, identifying the crack by adopting a modified image growth algorithm according to the initiation edge determined in the step, and positioning the position of the crack by introducing a morphological concept into a connection algorithm based on the region growth of the image growth.
2. The machine-learning based image recognition algorithm for surface cracking of an aircraft aluminum alloy according to claim 1, wherein in the step S3, the region growing is a process of gradually aggregating one pixel or sub-region into a complete independent connected region according to a predefined growing criterion.
3. The machine-learning based image recognition algorithm for aerospace aluminum alloy surface cracking according to claim 2, wherein the independent connected region formation process comprises the steps of: for the image interested target region R, z is a seed point found in advance on the region R, pixels which are in a certain neighborhood with the seed point z and meet the similarity criterion are gradually combined into a seed group according to a specified growth criterion for the growth of the next stage, and the cyclic growth is continuously carried out until the growth stopping condition is met, so that the process of growing the interested region from one seed point into an independent connected region is completed.
4. The machine learning-based image recognition algorithm for surface cracking of an aircraft aluminum alloy according to claim 1 or 3, wherein in S3, the region growing algorithm is generally implemented in three steps: determining a growing seed point; defining a growth criterion; growth stop conditions were determined.
5. The machine-learning based image recognition algorithm for aerospace aluminum alloy surface cracking according to claim 4, wherein the selection of growth seed points: using morphological processing methods, a rectangular pattern was used to locate the initiation edge of the crack.
6. The machine learning-based image recognition algorithm for surface cracking of an aircraft aluminum alloy according to claim 3, wherein in S3, connectivity of 5 neighborhood pixels of a pixel where the growth point is located is calculated, and whether the connectivity is the standard is to judge whether gray values of the pixel of the growth point and the neighborhood pixels are consistent, if the gray values are equal, the connectivity is determined, and if not, the connectivity is determined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010844070.0A CN112016555A (en) | 2020-08-20 | 2020-08-20 | Machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010844070.0A CN112016555A (en) | 2020-08-20 | 2020-08-20 | Machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112016555A true CN112016555A (en) | 2020-12-01 |
Family
ID=73505250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010844070.0A Pending CN112016555A (en) | 2020-08-20 | 2020-08-20 | Machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112016555A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240252A (en) * | 2014-09-22 | 2014-12-24 | 电子科技大学 | Detecting Algorithm for cracks of surface of high-temperature billet of machine vision bar |
| CN109859160A (en) * | 2018-12-10 | 2019-06-07 | 湖南航天天麓新材料检测有限责任公司 | Almag internal defect in cast image-recognizing method based on machine vision |
| CN110288088A (en) * | 2019-06-28 | 2019-09-27 | 中国民航大学 | Semi-supervised width study classification method based on manifold regularization and broadband network |
| CN110687122A (en) * | 2019-09-19 | 2020-01-14 | 湖北三江航天万峰科技发展有限公司 | Method and system for detecting surface cracks of ceramic tile |
| CN111256594A (en) * | 2020-01-18 | 2020-06-09 | 中国人民解放军国防科技大学 | Method for measuring physical characteristics of surface state of aircraft skin |
-
2020
- 2020-08-20 CN CN202010844070.0A patent/CN112016555A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240252A (en) * | 2014-09-22 | 2014-12-24 | 电子科技大学 | Detecting Algorithm for cracks of surface of high-temperature billet of machine vision bar |
| CN109859160A (en) * | 2018-12-10 | 2019-06-07 | 湖南航天天麓新材料检测有限责任公司 | Almag internal defect in cast image-recognizing method based on machine vision |
| CN110288088A (en) * | 2019-06-28 | 2019-09-27 | 中国民航大学 | Semi-supervised width study classification method based on manifold regularization and broadband network |
| CN110687122A (en) * | 2019-09-19 | 2020-01-14 | 湖北三江航天万峰科技发展有限公司 | Method and system for detecting surface cracks of ceramic tile |
| CN111256594A (en) * | 2020-01-18 | 2020-06-09 | 中国人民解放军国防科技大学 | Method for measuring physical characteristics of surface state of aircraft skin |
Non-Patent Citations (1)
| Title |
|---|
| 闫莉莉: "碳纤维增强铝基复合材料层间裂纹图像检测系统的研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109859160B (en) | Aluminum magnesium alloy casting internal defect image identification method based on machine vision | |
| CN107274401B (en) | High-resolution SAR image ship detection method based on visual attention mechanism | |
| CN109461148A (en) | Steel rail defect based on two-dimentional Otsu divides adaptive fast algorithm | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN113592861A (en) | Bridge crack detection method based on dynamic threshold | |
| CN109781737B (en) | Detection method and detection system for surface defects of hose | |
| Liu et al. | Inspection of rail surface defects based on image processing | |
| CN108596930A (en) | It must algorithm and the morphologic ray image weld seam extracting method of mathematics based on longicorn | |
| CN113469951B (en) | Hub defect detection method based on cascade region convolutional neural network | |
| CN108596151B (en) | Method for rapidly extracting ship target slice in large-scene SAR image | |
| CN108335294A (en) | The power distribution room abnormality image-recognizing method of complex condition | |
| CN105069778A (en) | Industrial product surface defect detection method constructed based on target characteristic saliency map | |
| CN115100174B (en) | Ship sheet metal part paint surface defect detection method | |
| CN112819812A (en) | Powder bed defect detection method based on image processing | |
| Tian et al. | Corrosion identification of fittings based on computer vision | |
| CN112381084B (en) | Automatic contour recognition method for tomographic image | |
| CN112016555A (en) | Machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloy | |
| CN115619799B (en) | Grain image segmentation method and system based on transfer learning | |
| CN108828549B (en) | Target extraction method based on airport scene surveillance radar system | |
| Gao et al. | Solder Joint Defect Detection Based on Image Segmentation and Deep Learning | |
| CN112651936B (en) | Steel plate surface defect image segmentation method and system based on image local entropy | |
| Chong et al. | Fabric Defect Detection Method Based on Projection Location and Superpixel Segmentation | |
| CN112330633B (en) | Jumper wire adhesive tape damage fault image segmentation method based on self-adaptive band-pass filtering | |
| CN115526867B (en) | Method and device for extracting crack defects of X-ray image of carbon fiber composite gas cylinder | |
| Rippel et al. | Automated Segmentation of Profiled Fibers in cross-sectional Micrographs for Quality Control |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201201 |
|
| RJ01 | Rejection of invention patent application after publication |