CN111024725A - Track slab crack detection method - Google Patents
Track slab crack detection method Download PDFInfo
- Publication number
- CN111024725A CN111024725A CN201911271846.8A CN201911271846A CN111024725A CN 111024725 A CN111024725 A CN 111024725A CN 201911271846 A CN201911271846 A CN 201911271846A CN 111024725 A CN111024725 A CN 111024725A
- Authority
- CN
- China
- Prior art keywords
- section
- crack
- cross
- fracture
- gradient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000007689 inspection Methods 0.000 claims abstract description 22
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 238000010998 test method Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
- B61K9/10—Measuring installations for surveying permanent way for detecting cracks in rails or welds thereof
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a track slab crack detection method, which comprises the following steps: (1) calculating the gradient of the cross section to distinguish the convex cross section from the suspected crack cross section and initially identify the crack; (2) testing the Gaussian distribution significance of the section by using a specially designed W test method, and finding out the actual crack section; (3) and carrying out edge gradient characteristic inspection on the actual crack section to obtain the actual crack section which is consistent with the crack width. The invention realizes the automation of crack detection, provides a method for detecting cracks of a track slab based on a laser three-dimensional image technology, and aims to overcome the problems in the prior art.
Description
Technical Field
The invention belongs to the technical field of high-speed railway maintenance, relates to a track slab crack detection method, and particularly relates to a track slab crack detection method based on a laser three-dimensional technology.
Background
The high-speed railway is used as an important component of a modern transportation system and plays a key role in the development of national economy. The cracks are one of the main forms of rail plate breakage, and the safe operation and service level of the high-speed railway is seriously influenced.
In the prior art, static manual detection is adopted as the current main mode, the manual detection efficiency is low, the accuracy is low, and the serious missed detection is commonly known. In addition, in order to ensure the normal operation of the high-speed railway, the detection needs to be carried out at night, and the detection difficulty of the cracks is undoubtedly increased. Therefore, it is very important to accurately obtain the geometric information of the crack by using an automatic detection technology and provide a scientific basis for subsequent railway maintenance. Since the 70 s in the 20 th century, with the rapid development of sensors and computer technologies, an automatic detection technology based on digital image processing has come into existence, and the advantages of high precision, high speed and the like make it possible to replace manual judgment.
Disclosure of Invention
The invention aims to provide a track slab crack detection method based on a laser three-dimensional image technology for realizing the automation of crack detection, and the method is a ballastless track slab crack detection method capable of overcoming the problems or solving part of the problems.
The specific technical scheme is as follows:
a rail plate crack detection method comprises the following steps:
(1) calculating the gradient of the cross section to distinguish the convex cross section from the suspected crack cross section and initially identify the crack;
(2) testing the Gaussian distribution significance of the section by using a specially designed W test method, and finding out the actual crack section;
(3) and carrying out edge gradient characteristic inspection on the actual crack section to obtain the actual crack section which is consistent with the crack width.
Further, a vehicle-mounted railway track surface state inspection system is adopted, and the system comprises a control computer with 8 cores, a system power supply box WPC, a system control box WCC, a positioning system consisting of a GPS receiver and an inertial gyroscope IMU, 7 laser-camera acquisition units, a distance measuring instrument DMI, a driving recording camera ROW and the like.
Further, adopting gradient characteristic inspection in the step (1);
to accommodate for the variation in crack width, a normalized index is used to measure the cross-sectional slope. Probability is a measure of the magnitude of the probability of a random event occurring, with values in the range of [0,1], with values closer to 1 being more likely for the event to occur. The principle is that whether the section has the characteristic of a crack shape or not is judged by respectively calculating the inclination degree of curves at two sides of the section to the center of the section, and the specific calculation process is as follows:
n1＝N(I(xj-1)-I(xj)≥Δt),j∈[i-r+1,i](2)
n2＝N(I(xj+1)-I(xj)≥Δt),j∈[i,i+r-1](3)
in the formula: x is the number ofiIs the pixel at the center of the section, and the other pixels at both sides of the center of the section, i (x) is the height of the pixel x, and r is the radius of the section. N (a) represents the total number of inequalities a that hold within the range of values. p is a radical of1And p2Respectively represent the condition ΔtInclination of both sides of the lower section, whereintThe minimum gradient, obviously Δ, that two adjacent pixels need to satisfytShould be selected as positive. After calculating the gradient of the two sides of the section, the section with the crack shape characteristic can be identified by setting corresponding threshold values:
S∈C if p≥pt， (4)
S＝[i-r,i+r],p＝p1p2， (5)
in the formula: s denotes by pixel xiA cross section with a radius at the center r; c represents a set of cross sections satisfying a gradient feature test; p represents the inclination of the section S; p is a radical oftThe minimum inclination representing that the section meets the characteristic test of the shape of the fracture section is that the inclination of the section is close to 0 for a flat section and is larger for the fracture section, so that the fracture section of the track slab can be extracted by selecting a proper threshold value.
Further, adopting Gaussian distribution characteristic inspection in the step (2);
and then testing the Gaussian distribution significance of the cross section by adopting a W test method, wherein the test method can test whether a group of small sample discrete data meets the Gaussian distribution and has higher precision, and the principle is to calculate the W statistic and judge the Gaussian distribution significance of the measured data through a corresponding threshold value:
in the formula: x(1),...,X(n)Is a sample X1,...,XnThe order statistics of (a) to (b),
is the mean value of the samples, aknIs a constant coefficient. When n is an odd number, r is (n-1)/2, and when n is an even number, r is n/2, typically n ∈ [3,50 ∈]Since the section examined is symmetrical about the central pixel, n is always an odd number. Applying the above formula to the section S, the gaussian distribution significance of the section can be verified:
21) a height value I (x) of 2r +1 pixels for n included in the section Si-r)...I(xi),...,I(xi+r) Arranged as I from small to large(1)(x),I(2)(x),...,I(n)(x) While calculating the mean value thereof
22) Looking up the W inspection constant coefficient table to find out a corresponding to the total number n of the section pixelsknValues, and cross-section statistics w(s) are calculated. The crack section is in a Gaussian curve shape with higher and thinner parts, and the texture section has the characteristic of shorter or thicker parts; therefore, the fracture section needs to satisfy:
E≥χnσc， (7)
in the formula: e is an index for representing the shape of the cross section and can measure the height, fat and thinness of the Gaussian curve.Smaller E indicates that the section is "shorter or thicker" and is more likely to belong to a textured region, while larger E indicates that the section is "taller and thinner" and is more likely to be a fractured section. SigmacThe variance of the whole preprocessed image is shown, n is the total number of pixels of the section S, and χ is a constant coefficient.
Further, in the step (3), edge gradient characteristic inspection is adopted;
the fracture section meeting the Gaussian inspection contains a real fracture part and also contains gentle tails on two sides, and the tails belong to flat areas, so that the width of the fracture section is larger than the real width of the fracture. And in order to reflect the real width of the crack, cutting the crack at the maximum gradient position of the section of the crack, namely performing edge gradient characteristic inspection to obtain the real crack.
Compared with the prior art, the invention has the beneficial effects that:
when the method is used for actual engineering, all crack images can be automatically identified by adopting a threshold value x of 0.2; then, adjusting optimization parameters according to feedback of engineering personnel, and carrying out semi-automatic identification on certain road sections which generate misjudgment or missed detection; the method can well meet engineering requirements in a mode of combining automation and semi-automation, and through inspection, the method can achieve 89.19% of accuracy and 93.69% of recall rate.
Drawings
Fig. 1 is a visual display diagram of track slab data acquired by 7 groups of laser-camera acquisition units after preprocessing and reconstruction;
fig. 2 is a detailed view of cracks and non-cracks in an image of a track slab, wherein (a) is a flat section and (b) is a crack section.
Detailed Description
The technical solution of the present invention will be described in further detail with reference to examples.
A rail plate crack detection method adopts a vehicle-mounted railway rail surface state inspection system, and the system comprises an 8-core control computer, a system power supply box (WPC), a system control box (WCC), a positioning system consisting of a GPS receiver and an inertial gyroscope (IMU), 7 laser-camera acquisition units, a Distance Measuring Instrument (DMI), a driving recording camera (ROW) and the like.
The track slab is formed by pouring cement concrete, so the plane of the track slab has the characteristic of depression at cracks, and other areas are relatively flat. After the track slab is transversely cut, the plane section of the track slab can be divided into two main section types, namely a flat section and a crack section.
The crack section presents a remarkable inverted Gaussian curve shape, and the automatic track slab crack identification method based on the crack section multi-feature inspection is designed according to the embodiment of the invention and mainly comprises three parts: (1) and calculating the gradient of the cross section to distinguish the convex cross section from the suspected crack cross section and initially identify the crack. (2) And testing the Gaussian distribution significance of the section by using a specially designed W test method, finding out an actual crack section (3), and carrying out edge gradient characteristic test on the actual crack section to obtain a real crack section which is consistent with the crack width.
1 gradient feature test
To accommodate for the variation in crack width, a normalized index is used to measure the cross-sectional slope. Probability is a measure of the magnitude of the probability of a random event occurring, with values in the range of [0,1], with values closer to 1 being more likely for the event to occur. The principle is that whether the section has the characteristic of a crack shape or not is judged by respectively calculating the inclination degree of curves at two sides of the section to the center of the section, and the specific calculation process is as follows:
n1＝N(I(xj-1)-I(xj)≥Δt),j∈[i-r+1,i](2)
n2＝N(I(xj+1)-I(xj)≥Δt),j∈[i,i+r-1](3)
in the formula: x is the number ofiIs the pixel at the center of the cross section, and the other pixels at both sides of the center of the cross section, i (x) is the height at the pixel x, and r is the radius of the cross section, as shown in fig. 2 (b). N (a) represents the total number of inequalities a that hold within the range of values. p is a radical of1And p2Respectively represent the condition ΔtLower section twoInclination of sides, whereintThe minimum gradient, obviously Δ, that two adjacent pixels need to satisfytShould be selected as positive. After calculating the gradient of the two sides of the section, the section with the crack shape characteristic can be identified by setting corresponding threshold values:
S∈C if p≥pt， (4)
S＝[i-r,i+r],p＝p1p2， (5)
in the formula: s denotes by pixel xiA cross section with a radius at the center r; c represents a set of cross sections satisfying a gradient feature test; p represents the inclination of the section S; p is a radical oftThe minimum inclination representing that the section meets the characteristic test of the shape of the fracture section is that the inclination of the section is close to 0 for a flat section and is larger for the fracture section, so that the fracture section of the track slab can be extracted by selecting a proper threshold value.
2 Gauss distribution feature inspection
And then testing the Gaussian distribution significance of the cross section by adopting a W test method, wherein the test method can test whether a group of small sample discrete data meets the Gaussian distribution and has higher precision, and the principle is to calculate the W statistic and judge the Gaussian distribution significance of the measured data through a corresponding threshold value:
in the formula: x(1),...,X(n)Is a sample X1,...,XnThe order statistics of (a) to (b),
is the mean value of the samples, aknIs constant coefficient]. When n is an odd number, r is (n-1)/2, and when n is an even number, r is n/2, typically n ∈ [3,50 ∈]Since the section examined is symmetrical about the central pixel, n is always an odd number. Applying the above formula to the section S, the gaussian distribution significance of the section can be verified:
1. height value I (x) for 2r +1 pixels n included in section Si-r)...I(xi),...,I(xi+r) Arranged as I from small to large(1)(x),I(2)(x),...,I(n)(x) While calculating the mean value I (x)i)。
2. Looking up W checking constant coefficient table to find out a corresponding to the total number n of pixels of the sectionknValues, and cross-section statistics w(s) are calculated. The crack section is in a Gaussian curve shape with higher and thinner parts, and the texture section has the characteristic of shorter or thicker parts; therefore, the fracture section needs to satisfy:
E≥χnσc， (7)
in the formula: e is an index for representing the shape of the cross section and can measure the height, fat and thinness of the Gaussian curve. Smaller E indicates that the section is "shorter or thicker" and is more likely to belong to a textured region, while larger E indicates that the section is "taller and thinner" and is more likely to be a fractured section. SigmacThe variance of the whole preprocessed image is shown, n is the total number of pixels of the section S, and χ is a constant coefficient.
3 edge gradient feature inspection
The fracture section meeting the Gaussian inspection contains a real fracture part and also contains gentle tails on two sides, and the tails belong to flat areas, so that the width of the fracture section is larger than the real width of the fracture. And in order to reflect the real width of the crack, cutting the crack at the maximum gradient position of the section of the crack, namely performing edge gradient characteristic inspection to obtain the real crack.
The above description is only a preferred embodiment of the present invention, and the scope of the present invention is not limited thereto, and any simple modifications or equivalent substitutions of the technical solutions that can be obviously obtained by those skilled in the art within the technical scope of the present invention are within the scope of the present invention.
Claims (5)
1. A rail plate crack detection method is characterized by comprising the following steps:
(1) calculating the gradient of the cross section to distinguish the convex cross section from the suspected crack cross section and initially identify the crack;
(2) testing the Gaussian distribution significance of the section by using a specially designed W test method, and finding out the actual crack section;
(3) and carrying out edge gradient characteristic inspection on the actual crack section to obtain the actual crack section which is consistent with the crack width.
2. The rail plate crack detection method according to claim 1, wherein a vehicle-mounted railway rail surface state inspection system is adopted, and the system comprises an 8-core control computer, a system power supply box WPC, a system control box WCC, a positioning system consisting of a GPS receiver and an inertial gyroscope IMU, 7 laser-camera acquisition units, a distance measuring instrument DMI and a driving record camera ROW.
3. The track slab crack detection method of claim 1 wherein a slope characteristic test is employed in step (1);
in order to adapt to the change of the width of the crack, the section gradient is measured by adopting a normalized index; the probability is used as a measure of the size of the probability of the occurrence of the random event, the value range is [0,1], and the closer the value is to 1, the higher the probability of the occurrence of the event is; the principle is that whether the section has the characteristic of a crack shape or not is judged by respectively calculating the inclination degree of curves at two sides of the section to the center of the section, and the specific calculation process is as follows:
n1＝N(I(xj-1)-I(xj)≥Δt),j∈[i-r+1,i](2)
n2＝N(I(xj+1)-I(xj)≥Δt),j∈[i,i+r-1](3)
in the formula: x is the number ofiIs the pixel at the center of the cross section, the other pixels at both sides of the cross section, I (x) is the imageHeight at pixel x, r is the cross-sectional radius; n (A) represents the total number of the inequalities A established in the value range; p is a radical of1And p2Respectively represent the condition ΔtInclination of both sides of the lower section, whereintThe minimum gradient, obviously Δ, that two adjacent pixels need to satisfytTaking the positive value; after the gradients of the two sides of the section are calculated, the section with the shape characteristics of the crack can be identified by setting corresponding thresholds:
S∈Cif p≥pt， (4)
S＝[i-r,i+r],p＝p1p2， (5)
in the formula: s denotes by pixel xiA cross section with a radius at the center r; c represents a set of cross sections satisfying a gradient feature test; p represents the inclination of the section S; p is a radical oftThe minimum inclination that the cross section satisfies the characteristic inspection of the shape of the fracture cross section is represented, for a flat cross section, the inclination tends to be 0, and for a fracture cross section, the inclination is larger, and the fracture cross section of the track slab is extracted by selecting a proper threshold value.
4. The track slab crack detection method of claim 1 wherein a gaussian distribution signature test is used in step (2);
and then testing the Gaussian distribution significance of the cross section by adopting a W test method, wherein the test method can test whether a group of small sample discrete data meets the Gaussian distribution and has higher precision, and the principle is to calculate the W statistic and judge the Gaussian distribution significance of the measured data through a corresponding threshold value:
in the formula: x(1),...,X(n)Is a sample X1,...,XnThe order statistics of (a) to (b),
is the mean value of the samples, aknIs a constantA coefficient; when n is an odd number, r is (n-1)/2, and when n is an even number, r is n/2, n is [3,50 ]]Since the section examined is symmetrical about the central pixel, n is always an odd number; applying the above formula to the section S can verify the Gaussian distribution significance of the section:
21) a height value I (x) of 2r +1 pixels for n included in the section Si-r)...I(xi),...,I(xi+r) Arranged as I from small to large(1)(x),I(2)(x),...,I(n)(x) While calculating the mean value thereof
22) Looking up the W inspection constant coefficient table to find out a corresponding to the total number n of the section pixelsknValues, and calculating a cross-section statistic W (S); the crack section is in a Gaussian curve shape with higher and thinner parts, and the texture section has the characteristic of shorter or thicker part; therefore, the fracture section needs to satisfy:
E≥χnσc， (7)
in the formula: e is an index for representing the shape of the cross section and can measure the height, the weight and the thinness of the Gaussian curve; the smaller E is, the shorter or the thicker the section is, the higher the possibility of belonging to the texture region is, and the larger E is, the taller or the thinner the section is, the more the section can be a crack section; sigmacThe variance of the whole preprocessed image is shown, n is the total number of pixels of the section S, and χ is a constant coefficient.
5. The track slab crack detection method of claim 1 wherein step (3) employs an edge gradient feature test;
the fracture section meeting the Gaussian inspection contains a real fracture part, and two sides of the fracture section also contain a relatively smooth tail part, and the tail part belongs to a flat area, so that the width of the fracture section is larger than the real width of the fracture; and in order to reflect the real width of the crack, cutting the crack at the maximum gradient position of the section of the crack, namely performing edge gradient characteristic inspection to obtain the real crack.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911271846.8A CN111024725A (en) | 2019-12-12 | 2019-12-12 | Track slab crack detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911271846.8A CN111024725A (en) | 2019-12-12 | 2019-12-12 | Track slab crack detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111024725A true CN111024725A (en) | 2020-04-17 |
Family
ID=70206060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911271846.8A Pending CN111024725A (en) | 2019-12-12 | 2019-12-12 | Track slab crack detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111024725A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118150585A (en) * | 2024-05-11 | 2024-06-07 | 深圳亚太航空技术股份有限公司 | Crimping terminal detection system and method thereof |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008167336A (en) * | 2006-12-29 | 2008-07-17 | Seiko Epson Corp | Apparatus, method, and program for restoring image |
-
2019
- 2019-12-12 CN CN201911271846.8A patent/CN111024725A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008167336A (en) * | 2006-12-29 | 2008-07-17 | Seiko Epson Corp | Apparatus, method, and program for restoring image |
Non-Patent Citations (1)
| Title |
|---|
| 邱延峻等: "基于多特征检验的沥青路面三维图像裂缝检测算法", 《西南交通大学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118150585A (en) * | 2024-05-11 | 2024-06-07 | 深圳亚太航空技术股份有限公司 | Crimping terminal detection system and method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104101600B (en) | Cross Section of CC Billet testing of small cracks method | |
| CN115272334B (en) | Method for detecting tiny defects on surface of steel rail under complex background | |
| WO2017120897A1 (en) | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud | |
| CN110533229B (en) | Track maintenance time prediction method and device | |
| CN101408937B (en) | Method and apparatus for locating character row | |
| CN104537651B (en) | Proportion detecting method and system for cracks in road surface image | |
| CN108731599B (en) | Steel rail abrasion depth calculation method | |
| CN111311560A (en) | Method and device for detecting state of steel rail fastener | |
| CN102679883A (en) | Tobacco shred width measuring method based on image processing | |
| CN110490918A (en) | Existing railway track switch frog extracting method based on three-dimensional laser scanning technique | |
| CN117173661B (en) | Asphalt road quality detection method based on computer vision | |
| CN115063400B (en) | Musical instrument production defect detection method using visual means | |
| CN110443278B (en) | Method, device and equipment for detecting thickness abnormality of grid line of solar cell | |
| CN110704805B (en) | Pre-stressed concrete beam bridge cracking early warning method based on live load strain | |
| CN112950532A (en) | Train pantograph state detection method | |
| CN111024725A (en) | Track slab crack detection method | |
| CN113689392A (en) | Railway fastener defect detection method and device | |
| CN107609757B (en) | Method for evaluating long-term benefit of pavement maintenance | |
| CN108931206A (en) | Method for distinguishing is known for rail profile outlier detection and effective profile | |
| CN104019772A (en) | Bridge structure concrete surface voids and pits area tester and detection method | |
| CN115619972A (en) | Road marking abrasion identification and evaluation method based on point cloud data | |
| CN115078377A (en) | Automatic bridge damage evaluation system and method based on point cloud fitting | |
| CN105279488B (en) | A kind of mileage Sign Board automatic identifying method of highway video routing inspection | |
| CN108416790A (en) | A kind of detection method for workpiece breakage rate | |
| CN116309598A (en) | Intelligent grading method for steel continuous casting billet macrostructure cracks based on machine vision |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200417 |
|
| WD01 | Invention patent application deemed withdrawn after publication |