CN112816496B - Automatic optical detection method and device for interface assembly quality of automobile domain controller - Google Patents

Automatic optical detection method and device for interface assembly quality of automobile domain controller Download PDF

Info

Publication number
CN112816496B
CN112816496B CN202110015425.XA CN202110015425A CN112816496B CN 112816496 B CN112816496 B CN 112816496B CN 202110015425 A CN202110015425 A CN 202110015425A CN 112816496 B CN112816496 B CN 112816496B
Authority
CN
China
Prior art keywords
interface
socket
label
domain controller
mask
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
Application number
CN202110015425.XA
Other languages
Chinese (zh)
Other versions
CN112816496A (en
Inventor
林镇秋
黄瑛娜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Huajie Electronic Technology Co ltd
Original Assignee
Guangzhou Huajie Electronic Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Huajie Electronic Technology Co ltd filed Critical Guangzhou Huajie Electronic Technology Co ltd
Priority to CN202110015425.XA priority Critical patent/CN112816496B/en
Publication of CN112816496A publication Critical patent/CN112816496A/en
Application granted granted Critical
Publication of CN112816496B publication Critical patent/CN112816496B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
    • G01N35/00584—Control arrangements for automatic analysers

Abstract

The invention discloses an automatic optical detection method and device for interface assembly quality of an automobile domain controller, wherein the method comprises the following steps: placing a prototype, controlling a strip-shaped light source to be started by an optical sensing subsystem, collecting an image of a detection surface of an automobile domain controller, and identifying various interface connectors, sockets, labels and positioning marks by using a Mask R-CNN detection and segmentation frame; counting the number of various interface connectors, the number of sockets and the number of labels, and judging the number of the interface connectors, the sockets and the label mounting feet of the automobile domain controller; identifying pixel coordinates of the positioning mark as reference pixel coordinates, identifying coordinates of the interface connector, the interface socket and the label, and respectively judging whether the mounting positions of the interface connector and the interface socket are correct or not and whether the label pasting position is correct or not; and when the number of the interface connectors, the sockets and the labels of the automobile domain controller is enough, the mounting positions of the interface connectors, the interface sockets and the labels are correct, and the automobile domain controller is judged to be qualified.

Description

Automatic optical detection method and device for interface assembly quality of automobile domain controller
Technical Field
The invention relates to the technical field of automatic optical detection, in particular to an automatic optical detection method and device for interface assembly quality of an automobile domain controller.
Background
The automobile domain controller replaces the existing distributed electronic and electric architecture by relatively and intensively controlling each domain in the automobile through the multi-core chip with stronger processing capacity, and realizes the control of a plurality of domains such as a power assembly, an intelligent cabin, intelligent driving and the like. The automobile domain controller carries out wireless transmission on the automobile sensor data through BT, WIFI and the like, and the wireless transmission capability needs to be tested. However, at present, because the automobile domain controller is provided with a plurality of data transmission interfaces, different test boards are required to be used when the automobile domain controller is tested, the testing efficiency is not high, and the development of the automobile domain controller is restricted.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide an automatic optical detection method and apparatus for interface assembly quality of an automobile domain controller.
The purpose of the invention is realized by the following technical scheme:
an automatic optical detection method for interface assembly quality of an automobile domain controller comprises the following steps:
a, controlling a strip light source to be started, collecting an image of a detection surface of an automobile domain controller, and identifying various interface connectors, sockets, labels and positioning marks by using a Mask R-CNN detection and segmentation framework;
b statistics of the number N of various interface connectors plug Number of sockets N socket Label N label The number of the design interface connectors N of the automobile domain controller plug-d Number of sockets N socket-d Number of labels N label-d Comparing and judging the mounting feet of the interface connector, the socket and the label of the automobile domain controller;
c, using Mask R-CNN to detect and divide the frame to identify the positioning mark to obtain the pixel coordinate (u) of the positioning mark 0 ,v 0 ) And the pixel coordinates (u) of the location mark 0 ,v 0 ) As reference pixel coordinates, identify interface connector coordinates (u) plug ,v plug ) Obtaining the relative positioning mark coordinate (delta u) of the interface joint plug ,Δv plug ) Relative positioning mark size (delta u) with design interface joint plug-d ,Δv plug-d ) Judging whether the mounting position of the interface joint is correct or not;
d uses Mask R-CNN to detect and divide the frame recognition interface socket coordinate (u) socket ,v socket ) Coordinate (u) of the pixel of the location mark 0 ,v 0 ) Obtaining the coordinate (delta u) of the relative positioning mark of the interface socket as the reference pixel coordinate socket ,Δv socket ) Coordinate (delta u) of relative positioning mark with design interface socket socket-d ,Δv socket-d ) Judging whether the mounting position of the interface socket is correct or not;
e using Mask R-CNN to detect and segment frame identification label coordinate (u) label ,v label ) Coordinate (u) of the pixel of the location mark 0 ,v 0 ) Obtaining the coordinate (delta u) of the label relative to the positioning mark as the reference pixel coordinate label ,Δv label ) Positioning the landmark coordinates (Δ u) relative to the design label socket-d ,Δv socket-d ) Judging whether the label pasting position is correct or not;
and F, integrating the evaluation results of the step B, C, D, E, and judging that the automobile domain controller is qualified when the mounting positions of the interface connector, the interface socket and the label are correct when the mounting numbers of the interface connector, the interface socket and the label of the automobile domain controller are sufficient.
An automatic optical detection device for interface assembly quality of an automobile domain controller comprises: the system comprises an optical sensing subsystem, a motion control subsystem and an upper computer;
the optical sensing subsystem is used for controlling the strip-shaped light source to be started, collecting an image of a detection surface of the automobile domain controller, and identifying various interface connectors, sockets, labels and positioning marks by using a Mask R-CNN detection and segmentation frame;
the motion control subsystem consists of a four-axis motion control card, a program control power supply, 4 servo motors, an industrial personal computer, a display, a relay channel board and a CAN bus, and is used for placing a prototype, so that the prototype CAN move in X, Y, Z three directions and horizontally rotate to improve the test efficiency;
the upper computer is used for identifying the interface connector, the socket, the pins and the sticker labels in the uploaded images.
One or more embodiments of the present invention may have the following advantages over the prior art:
the method has the characteristics of high automation degree, high speed and low labor cost, and has practical significance and popularization value.
Drawings
FIG. 1 is a flow chart of an automatic optical inspection method for interface assembly quality of a car domain controller.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings.
As shown in fig. 1, the automatic optical detection method for the interface assembling quality of the automobile domain controller comprises the following steps:
step 10, controlling a strip light source to be started, collecting an image of a detection surface of an automobile domain controller, and identifying various interface connectors, sockets, labels and positioning marks by using a Mask R-CNN detection and segmentation framework;
step 20, counting the number N of various interface connectors plug Socket and socketNumber N socket Label N label The number of the design interface connectors N of the automobile domain controller plug-d Number of sockets N socket-d Number of labels N label-d Comparing and judging the mounting feet of the interface connector, the socket and the label of the automobile domain controller;
step 30, using Mask R-CNN to detect and segment the frame identification positioning mark to obtain the pixel coordinate (u) of the positioning mark 0 ,v 0 ) And will locate the mark pixel coordinate (u) 0 ,v 0 ) Identifying interface joint coordinates (u) as reference pixel coordinates plug ,v plug ) Obtaining the relative positioning mark coordinate (delta u) of the interface joint plug ,Δv plug ) Relative positioning mark size (delta u) with design interface joint plug-d ,Δv plug-d ) Judging whether the mounting position of the interface joint is correct or not;
step 40 of identifying the coordinates of the interface socket (u) by Mask R-CNN detection and segmentation framework socket ,v socket ) Coordinate (u) of the pixel of the location mark 0 ,v 0 ) Obtaining the coordinate (delta u) of the relative positioning mark of the interface socket as the reference pixel coordinate socket ,Δv socket ) Coordinate (delta u) of relative positioning mark with design interface socket socket-d ,Δv socket-d ) Judging whether the mounting position of the interface socket is correct or not;
step 50 of detecting and segmenting framework identification tag coordinates (u) using Mask R-CNN label ,v label ) Coordinate (u) of the pixel of the location mark 0 ,v 0 ) Obtaining coordinates (delta u) of the label relative to the positioning mark as reference pixel coordinates label ,Δv label ) Positioning the landmark coordinates (Δ u) relative to the design label socket-d ,Δv socket-d ) Judging whether the label pasting position is correct or not;
and step 60, integrating the evaluation results of the steps 20, 30, 40 and 50, and judging that the automobile domain controller is qualified when the number of the interface connectors, the sockets and the labels of the automobile domain controller is enough, and the mounting positions of the interface connectors, the interface sockets and the labels are correct.
In the step 10, the Mask R-CNN detection and segmentation framework can output the type (Class), the bounding Box (Box) and the Mask (Mask), and in the detection method of the automobile domain controller, the definition is
The upper left end of the image U-V image coordinate system is an image origin O (0,0), the positive direction of the U axis is horizontal to the right, and the positive direction of the V axis is vertical to the down;
type (Class): interface connector types (A-1, A-2 …), interface socket types (B-1, B-2 …), labels (C-1, C-2 …) or positioning marks (D);
bounding Box (Box): upper left point (u) 1 ,v 1 ) Lower right side point (u) 2 ,v 2 )；
Mask (Mask): the 28 × 28 bitmap, with 1 for presence and 0 for absence.
In order to ensure the detection accuracy, the accuracy rate is up to 100% in the aspect of type (Class) identification; COCO AP is adopted for the accuracy rate of the bounding box and the mask IoU＝0.5 、AP IoU＝0.75 Evaluation, Mask R-CNN detection and AP segmentation of the bounding Box (Box) IoU＝0.5 Should equal 100%; AP of Mask (Mask) IoU＝0.5 ≥95％。
The Mask R-CNN used in this embodiment detects and divides AP of frame bounding Box (Box) IoU＝0.5 100%, the bounding box mAP reaches 96.892%; AP of Mask (Mask) IoU＝0.5 100%, and the mask mAP reaches 96.220%.
In step 20, the conditions of the number of the interface connectors, the sockets and the labels of the automobile domain controller are as follows:
Figure BDA0002884343910000041
Figure BDA0002884343910000042
Figure BDA0002884343910000043
Figure BDA0002884343910000044
in step 30, setting the tolerance limit delta of the mounting position of the interface joint on the U axis in the image coordinate system plug-u Tolerance limit delta on the V axis plug-v If the interface connector is installed correctly, the conditions are as follows:
Figure BDA0002884343910000045
in step 40, the allowable deviation limit delta of the mounting position of the interface socket on the U axis is set in the image coordinate system socket-u Allowable deviation limit delta on V axis socket-v Then, the correct conditions for the installation of the interface socket are as follows:
Figure BDA0002884343910000051
step 50 is arranged in an image coordinate system, and the allowable deviation limit delta of the label pasting position on the U axis label-u Allowable deviation limit delta on V axis label-v Then the label pasting correct condition is as follows:
Figure BDA0002884343910000052
the embodiment also provides an automatic optical detection device for the interface assembly quality of the automobile domain controller, which comprises a motion control subsystem and an upper computer; the above-mentioned
The optical sensing subsystem is used for controlling the strip-shaped light source to be started, collecting an image of a detection surface of the automobile domain controller, detecting and segmenting a frame by using Mask R-CNN, and identifying various interface connectors, sockets, labels and positioning marks;
the motion control subsystem consists of a four-axis motion control card, a program control power supply, 4 servo motors, an industrial personal computer, a display, a relay channel board and a CAN bus, and is used for placing a prototype, so that the prototype CAN move in X, Y, Z three directions and horizontally rotate to improve the test efficiency;
the upper computer is used for identifying an interface connector, a socket, pins and sticker labels in the uploaded images.
The optical sensing subsystem consists of two industrial cameras, a lens, a light source controller and four strip light sources and is used for collecting front and rear panel images of the automobile domain controller.
Although the embodiments of the present invention have been described above, the above descriptions are only for the convenience of understanding the present invention, and are not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (6)

1. An automatic optical detection method for interface assembly quality of an automobile domain controller is characterized by comprising the following steps:
a, controlling a strip light source to be started, collecting an image of a detection surface of an automobile domain controller, and identifying various interface connectors, sockets, labels and positioning marks by using a Mask R-CNN detection and segmentation framework;
b statistics of the number N of various interface connectors plug And the number of the sockets N socket Label N label The number of the interface connectors N designed to interface with the automobile domain controller of the model number plug-d Number of sockets N socket-d Number of tags N label-d Comparing and judging the mounting feet of the interface connector, the socket and the label of the automobile domain controller;
c, using Mask R-CNN to detect and segment the frame identification positioning mark to obtain the pixel coordinate (u) of the positioning mark 0 ,v 0 ) And the pixel coordinates (u) of the location mark 0 ,v 0 ) Identifying interface joint coordinates (u) as reference pixel coordinates plug ,v plug ) Obtaining the relative positioning mark coordinate (delta u) of the interface joint plug ,Δv plug ) As opposed to designing interface jointsSize of location mark (delta u) plug-d ,Δv plug-d ) Judging whether the mounting position of the interface joint is correct or not;
d uses Mask R-CNN to detect and divide the frame recognition interface socket coordinate (u) socket ,v socket ) Coordinate (u) of the pixel of the location mark 0 ,v 0 ) Obtaining the coordinate (delta u) of the relative positioning mark of the interface socket as the reference pixel coordinate socket ,Δv socket ) Coordinate (delta u) of relative positioning mark with design interface socket socket-d ,Δv socket-d ) Judging whether the mounting position of the interface socket is correct or not;
e using Mask R-CNN to detect and segment frame identification label coordinate (u) label ,v label ) Coordinate (u) of the pixel of the location mark 0 ,v 0 ) Obtaining the coordinate (delta u) of the label relative to the positioning mark as the reference pixel coordinate label ,Δv label ) Positioning the landmark coordinates (Δ u) relative to the design label socket-d ,Δv socket-d ) Judging whether the label pasting position is correct or not;
f, integrating the evaluation results of the step B, C, D, E, and judging that the automobile domain controller is qualified when the mounting positions of the interface connector, the interface socket and the label are correct and the mounting positions of the interface connector, the interface socket and the label are correct;
in the step C, the deviation limit delta is allowed to be set in an image coordinate system and the mounting position of the interface joint is on the U axis plug-u Tolerance limit delta on the V axis plug-v If the interface connector is installed correctly, the conditions are as follows:
Figure FDA0003710224990000021
in the step D:
set in the image coordinate system, the allowable deviation limit delta of the mounting position of the interface socket on the U axis socket-u Allowable deviation limit delta on V axis socket-v Then, the correct conditions for the installation of the interface socket are as follows:
Figure FDA0003710224990000022
in the step E:
set in the image coordinate system, the allowable deviation limit delta of the label pasting position on the U axis label Tolerance limits δ on the u, V axes label-v Then the label pasting correct condition is:
Figure FDA0003710224990000023
2. the method of claim 1, wherein Mask R-CNN detects and partitions frame output type (Class), bounding Box (Box) and Mask (Mask), and in the method, definition is used for detecting the interface assembly quality of the car domain controller
The upper left end of the image U-V image coordinate system is an image origin O (0,0), the positive direction of the U axis is horizontal to the right, and the positive direction of the V axis is vertical to the down;
type (Class): interface connector types (A-1, A-2 …), interface socket types (B-1, B-2 …), labels (C-1, C-2 …) or positioning marks (D);
bounding Box (Box): upper left point (u) 1 ,v 1 ) Lower right side point (u) 2 ,v 2 )；
Mask (Mask): 28 x 28 bitmap, with 1 for presence, 0 for absence.
3. The automatic optical inspection method of interface assembling quality of automobile domain controller as claimed in claim 2, wherein the accuracy rate should reach 100% in type (Class) identification; the accuracy of the boundary frame and the mask adopts COCO AP IoU＝0.5 、AP IoU ＝0.75 Evaluation, Mask R-CNN detection and AP segmentation of the bounding Box (Box) IoU＝0.5 Should equal 100%; AP of Mask (Mask) IoU＝0.5 ≥95％。
4. The automatic optical inspection method for interface assembling quality of car domain controller according to claim 1, characterized in that in said step B: the conditions of the number of the interface joints, the sockets and the label installation feet of the automobile domain controller are as follows:
Figure FDA0003710224990000031
Figure FDA0003710224990000032
5. an automatic optical detection device for interface assembly quality of a car domain controller, characterized in that the device comprises: the system comprises an optical sensing subsystem, a motion control subsystem and an upper computer;
the optical sensing subsystem is used for controlling the strip-shaped light source to be started, collecting an image of a detection surface of the automobile domain controller, and identifying various interface connectors, sockets, labels and positioning marks by using a Mask R-CNN detection and segmentation frame;
the motion control subsystem consists of a four-axis motion control card, a program control power supply, 4 servo motors, an industrial personal computer, a display, a relay channel board and a CAN bus, and is used for placing a prototype, so that the prototype CAN move in X, Y, Z three directions and horizontally rotate to improve the test efficiency;
the upper computer is used for identifying the interface connector, the socket, the pins and the sticker labels in the uploaded images.
6. The automatic optical inspection device for interface assembling quality of automobile domain controller according to claim 5, wherein said optical sensing subsystem is composed of two industrial cameras and lens, light source controller, four bar light sources.
CN202110015425.XA 2021-01-05 2021-01-05 Automatic optical detection method and device for interface assembly quality of automobile domain controller Active CN112816496B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110015425.XA CN112816496B (en) 2021-01-05 2021-01-05 Automatic optical detection method and device for interface assembly quality of automobile domain controller

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110015425.XA CN112816496B (en) 2021-01-05 2021-01-05 Automatic optical detection method and device for interface assembly quality of automobile domain controller

Publications (2)

Publication Number Publication Date
CN112816496A CN112816496A (en) 2021-05-18
CN112816496B true CN112816496B (en) 2022-09-23

Family

ID=75857937

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110015425.XA Active CN112816496B (en) 2021-01-05 2021-01-05 Automatic optical detection method and device for interface assembly quality of automobile domain controller

Country Status (1)

Country Link
CN (1) CN112816496B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113888494B (en) * 2021-09-28 2022-08-30 广州市华颉电子科技有限公司 Artificial intelligence interface pin quality detection method of automobile domain controller
CN114324350A (en) * 2021-12-10 2022-04-12 巢湖学院 Intelligent five-hole socket panel defect detection method and system based on machine vision

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110765912A (en) * 2019-10-15 2020-02-07 武汉大学 SAR image ship target detection method based on statistical constraint and Mask R-CNN
CN111798516A (en) * 2020-07-01 2020-10-20 广东省特种设备检测研究院珠海检测院 Method for detecting running state quantity of bridge crane equipment and analyzing errors

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108759667B (en) * 2018-05-29 2019-11-12 福州大学 Front truck distance measuring method under vehicle-mounted camera based on monocular vision and image segmentation
CN109085174A (en) * 2018-07-02 2018-12-25 北京百度网讯科技有限公司 Display screen peripheral circuit detection method, device, electronic equipment and storage medium
US11037051B2 (en) * 2018-11-28 2021-06-15 Nvidia Corporation 3D plane detection and reconstruction using a monocular image
CN109738061B (en) * 2019-01-11 2020-02-18 华南理工大学 Illuminometer position automatic alignment method and system for illuminometer calibration
CN109974582B (en) * 2019-04-04 2023-10-31 江南大学 Device and method for non-contact visual detection of core wire size of automobile wire harness
EP3736741A1 (en) * 2019-05-06 2020-11-11 Dassault Systèmes Experience learning in virtual world
CN111044525B (en) * 2019-12-30 2021-10-29 歌尔股份有限公司 Product defect detection method, device and system
CN111402248B (en) * 2020-03-23 2023-05-09 华南理工大学 Power transmission line wire defect detection method based on machine vision

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110765912A (en) * 2019-10-15 2020-02-07 武汉大学 SAR image ship target detection method based on statistical constraint and Mask R-CNN
CN111798516A (en) * 2020-07-01 2020-10-20 广东省特种设备检测研究院珠海检测院 Method for detecting running state quantity of bridge crane equipment and analyzing errors

Also Published As

Publication number Publication date
CN112816496A (en) 2021-05-18

Similar Documents

Publication Publication Date Title
CN112816496B (en) Automatic optical detection method and device for interface assembly quality of automobile domain controller
CN104913722B (en) A kind of car body controller connector pin normotopia degree detection method
CN105184793A (en) Electric energy meter sample appearance and PCB element detection method
KR102378186B1 (en) Artificial intelligence vision inspection system for wiring harness
US20050259874A1 (en) Apparatus, method, and program for assisting in selection of pattern element for pattern matching
CN103487442A (en) Novel device and method for detecting defects of flexible circuit boards
CN203069520U (en) Multifunctional automatic PCB (Printed Circuit Board) test system
CN104345260A (en) Signal completeness automatic testing system and method
CN106664825A (en) Component data handling device, component data handling method, and component mounting system
CN111157532A (en) Visual detection device and method for scratches of mobile phone shell
CN204705323U (en) A kind of car body controller connector pin normotopia degree pick-up unit
CN113744252A (en) Method, apparatus, storage medium and program product for marking and detecting defects
CN115375608A (en) Detection method and device, detection equipment and storage medium
CN109712115A (en) A kind of pcb board automatic testing method and system
CN110817674B (en) Method, device and equipment for detecting step defect of escalator and storage medium
CN202948128U (en) Intelligent ammeter automatic detecting system with type detecting function
CN101398462B (en) Plaster bonding wire automatic detection system
CN102967844A (en) Automatic detection system with formal detection function of intelligent ammeters
CN110738170A (en) image recognition method for electric meter terminal fault recognition
CN2406256Y (en) On-line testing machine with picture identifying function
CN108268813B (en) Lane departure early warning method and device and electronic equipment
CN112784737B (en) Text detection method, system and device combining pixel segmentation and line segment anchor
CN203519508U (en) Novel flexible circuit board defect detecting device
CN113034418A (en) Circuit board identification and pad/chip rapid positioning method for electronic industry
CN111553210B (en) Training method of lane line detection model, lane line detection method and device

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
GR01 Patent grant
GR01 Patent grant