CN105798927A - Crucible defect grinding processing method based on image and processing system with crucible defect grinding processing method based on image - Google Patents
Crucible defect grinding processing method based on image and processing system with crucible defect grinding processing method based on image Download PDFInfo
- Publication number
- CN105798927A CN105798927A CN201610342546.4A CN201610342546A CN105798927A CN 105798927 A CN105798927 A CN 105798927A CN 201610342546 A CN201610342546 A CN 201610342546A CN 105798927 A CN105798927 A CN 105798927A
- Authority
- CN
- China
- Prior art keywords
- crucible
- image
- processing method
- defect
- method based
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/005—Manipulators for mechanical processing tasks
- B25J11/0065—Polishing or grinding
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Grinding And Polishing Of Tertiary Curved Surfaces And Surfaces With Complex Shapes (AREA)
- Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
Abstract
The invention relates to the field of quartz ceramic crucible processing, in particular to a crucible defect grinding processing method based on an image and a processing system with the crucible defect grinding processing method based on the image. The processing method includes the following steps that firstly, a crucible is manually marked; secondly, an appearance image model of the crucible is established; thirdly, a gray level histogram is generated; fourthly, a binarization image is generated; fifthly, zero setting processing is performed on a single pixel value; sixthly, an initial position and an end position are determined; seventhly, an initial position and an end position of an intersection area region are acquired; eighthly, a digit set and a region set are obtained; ninthly, matching processing is performed on the digit set and the region set; tenthly, normalization is performed on digits and regions; eleventhly, digits in a defect region are recognized, and the position and the number of grinding times of the defect region are acquired; and twelfthly, a processing path file is generated. The method provides essential processing parameters and generates the processing path file when a robot is used for grinding the crucible, and the grinding robot can automatically grind the crucible.
Description
Technical field
The present invention relates to the manufacture field of quartz ceramic crucible, particularly relate to a kind of defect utilizing Machine Vision Recognition quartz ceramic crucible and generate the method for machining locus file and apply its system of processing.
Background technology
Quartz ceramic crucible full name is ceramics quartz glass crucible, is be the pottery crucible that raw material is made with quartz glass, mostly is square.Fine fused silica ceramic material, due to the feature such as have fine structure, thermal conductivity is low, thermal coefficient of expansion is little, dimensional accuracy is high, high temperature is indeformable, good thermal shock stability, good electrical property, chemerosiveness resistent are good, is therefore used widely in fields such as glass post-processing industry, metallurgical industry, electronics industry, chemical engineering industry, Aero-Space.
In recent years being constantly taken seriously along with eco-friendly power source and develop, solar energy is subject to the most attention of countries in the world as green energy resource, obtains development and utilization widely, and this makes the consumption of the polysilicon for solar energy conversion sharply increase.Thus having promoted the fast development of production of polysilicon, the consumption of corresponding large size, thin walled square fused quartz ceramic crucible is also sharply increasing, and the market prospect of this product is very good in the world.Fused quartz ceramic crucible, with its Heat stability is good, resistance to melt (silicon, aluminum, copper etc.) aggressivity with to the characteristic such as machined goods are pollution-free, is widely used in production of polysilicon and non-ferrous metal metallurgy industry.Quartz ceramic crucible is the critical component of polycrystalline silicon used for solar battery ingot furnace, it as load polycrystalline silicon raw material container will continuous operation more than 50 hours under the high temperature more than 1500 DEG C, so as to melt the polysilicon silicon ingot produced for manufacturing solaode.Owing to it uses condition extremely harsh, stability, dimensional accuracy etc. that the purity of crucible, intensity, open defect, inherent quality, high-temperature behavior, heat are shaken has extremely strict requirement.
Traditional quartz ceramic crucible open defect polishing is dependent on the experienced workman defect to crucible surface and is identified and judges whether to the number of times of polishing, then carries out manual polishing.Such method length consuming time, inefficiency, long-term work is in the adverse circumstances of full dust, and healthy to workman also has a great impact.So, it is possible to use robot replaces workman to carry out the polishing work of crucible open defect, it is achieved the automatization of production.And the premise realizing polishing automatization is exactly the defect area position obtaining and needing polishing and the number of times needing polishing.Therefore the position obtaining the defect area of arbitrary shape quartz ceramic crucible and the number of times technology identifying polishing are the major issues that quartz ceramic crucible manufacture field is urgently to be resolved hurrily.
Summary of the invention
It is an object of the invention to propose a kind of defect utilizing Machine Vision Recognition quartz ceramic crucible and generate the method for machining locus file and apply its processing method.
For reaching this purpose, the present invention by the following technical solutions:
Based on the crucible defect grinding processing method of image, its application with numerical control sander device people, described processing method its comprise the steps:
(1) defective locations of crucible to be processed and the number of times of corresponding defective locations needs polishing are manually marked
(2) in digital control system, the outward appearance of crucible to be processed is set up iconic model;
(3) image processed and generate grey level histogram;
(4) according to grey level histogram, set pixel threshold, image is carried out two and directly changes and generate binary image;
(5) travel through the pixel of binary image, namely do not set to 0 single in each connected domain of binary image with other same pixel bigger pixel values of value continuous print;
(6) according to pixel value in binary image more than the position of pixel threshold set, forwardly and rearwardly search in binary image, it is determined that the original position of every a line connected domain and end position in binary image;
(7) judging whether the connected domain of adjacent rows has crossing region, if there being crossing region, writing down original position that in corresponding two row, pixel value is less than normal and pixel value end position bigger than normal;
(8) resolution of binary image in extraction step (7), and repeat step (6) n time altogether, wherein n is less than or equal to d!, the set of regions of the set of digits obtaining polishing number of times numeral composition and the region composition intersected;
(9) set of digits obtained in step (8) and set of regions are carried out discrete point optimal solution respectively to solve, and the discrete point optimal solution of set of digits is mated with corresponding set of regions discrete point optimal solution;
(10) the discrete point optimal solution according to set of digits, does normalization to corresponding region, obtains numeric area;
(11) numeric area after normalization and template numeric area are subtracted each other, the sum of the pixel value in this numeric area after calculating difference, and masterplate numeral minimum in template numeric area;Pixel value in described numeric area and minimum in template numeric area masterplate numeral respectively defect area position and polishing number of times;
(12) the defect area position result that will identify that and polishing number of times deliver to Trajectory Planning System, generate machining locus file.
Concrete, comprising the steps: when described step (4) generates binary image more than the pixel setting pixel threshold, gray scale in image is set to 255, gray scale being set to 0 less than the pixel setting pixel threshold, thus obtaining binary image.
Concrete, step (7) if in judges the connected domain of adjacent rows whether have the step in crossing region comprise the steps: the i-th row certain connected domain original position as till i_start and end as i_end, the connected domain position of the position of this connected domain Yu i+1 row is compared, the original position assuming wherein certain connected domain is i+1_start and i+1_end, one of if meeting i_start<i+1_start and i_end>i+1_end or i_start>i+1_start and i_end<i+1_end both of these case, then think that the connected domain of this two row is to have the region of overlap, otherwise it is assumed that the connected domain of this two row does not have the region of overlap.
More excellent, the method carrying out respectively when discrete point optimal solution solves set of digits and set of regions in described step (9) being to adopt bounding box calculates.Defect area on one face of quartz ceramic crucible has multiple, and the number of times of each region polishing neither be different.The bounding box position of defect area and numeral can all be found out by above-mentioned step, and defect area and corresponding polishing number of times numeral is mated.Owing to numeral is to be imprinted in defect area, so the digital bounding box position in the bounding box position of defect area and corresponding defect area should be inclusion relation.Such as assume that certain defect area position coordinates in the picture isWith, numeral bounding box position coordinates isWithIf this numeral is at this defect area, should meet condition:,,,。
More excellent, described step (12) also includes the step setting up masterplate numeral:
A, machine in digital control system and do not have the outward appearance of defective quartz ceramic crucible to set up iconic model;
Content described in b, basis (1)-(9) obtains masterplate numeric area.
More excellent, discrete point optimal solution according to set of digits in described step (10), comprise the steps: when corresponding region is done normalization all numerals to be zoomed in or out to and the template equirotal size of numeral bounding box.All of numeral is carried out above-mentioned normalization operation, improves the accuracy that numeral identifies, also ensure that the Digit Control Machine Tool accurate machining to silica crucible to be processed.
More excellent, described step (2) step also comprises the steps: to utilize each face that quartz ceramic crucible to be processed is included lateral surface, medial surface and bottom surface by industrial camera to take pictures, then by image transmitting to PC end.Only silica crucible to be processed being carried out comprehensive image acquisition, the iconic model that guarantee is set up in digital control system can record the defect of silica crucible to be processed completely, could facilitate the follow-up accurate extraction to these defects.
More excellent, in upper described step (3) before generating described grey level histogram, also comprise the steps: image is sequentially carried out the operation of pretreatment, noise filtering and gray processing.If gray processing is the necessary operation setting up grey level histogram, as pretreatment and noise filtering are to ensure that gray scale directly puts the operation of figure accuracy.
A kind of system of processing applying the above-mentioned crucible defect grinding processing method based on image;It includes digital control system, milling robot and computer;Described milling robot includes controlling seat and being located at the mechanical arm controlling seat and the sanding apparatus of installation and mechanical arm tail end;
Described computer includes industrial camera, computer vision module, trajectory planning module, computer and milling robot communication module, computer and digital control system communication module and computer and industrial camera communication module;
The control seat of described milling robot and described digital control system all electrically connect with described computer.
The present invention proposes a kind of crucible defect grinding processing method based on image according to foregoing and applies its system of processing, the method, by identifying that crucible needs defect area position and the grinding number of times of grinding, carries out, for robot below, the machined parameters that polishing provides necessary.This processing method is applicable to the polishing of silica crucible defect, after the regional location marking defect workman and the number of times needing grinding, industrial camera is utilized to be taken pictures in all faces of crucible respectively, then by image transmitting to PC end, by PC, image is carried out pretreatment, the defect area position and grinding number of times that need grinding are identified by the algorithm that recycling regional location identification and numeral identify, planning for next step polishing track is prepared, and ultimately generates the machining locus file that can make milling robot that crucible carries out automatically grinding.
Accompanying drawing explanation
Fig. 1 is the flow process frame diagram of an embodiment of heretofore described processing method.
Detailed description of the invention
Technical scheme is further illustrated below in conjunction with accompanying drawing and by detailed description of the invention.
Based on the crucible defect grinding processing method of image, its application and numerical control sander device people, as it is shown in figure 1, described processing method comprises the steps:
(1) defective locations on quartz ceramic crucible to be processed and the number of times of corresponding defective locations needs polishing are manually marked.
(2) in digital control system, the outward appearance of quartz ceramic crucible to be processed is set up iconic model: utilize each face that quartz ceramic crucible to be processed is included lateral surface, medial surface and bottom surface by industrial camera to take pictures, then by image transmitting to PC end.
(3) image is sequentially carried out the operation of pretreatment, noise filtering and gray processing and generates grey level histogram.
(4) gray scale in image being set to 255 more than the pixel setting pixel threshold, gray scale being set to 0 less than the pixel setting pixel threshold, thus obtaining binary image.
(5) travel through the pixel of binary image, namely do not set to 0 single in each connected domain of binary image with the pixel value of other same pixel value continuous print and pixel value 255;This step is to remove the pixel value of single appearance in connected domain, namely the whole binary image being is made up of the region that pixel value is 255 and the region that pixel value is 0, do not have the connected domain of a same pixel value occurs scattered, single and with this connected domain pixel value pixel value not etc..
(6) according to pixel value in binary image more than the position of pixel threshold set, forwardly and rearwardly search in binary image, it is determined that the original position of every a line connected domain and end position in binary image.
(7) if the original position of certain connected domain of the i-th row is i_end till being i_start and end, the connected domain position of the position of this connected domain Yu i+1 row is compared, the original position assuming wherein certain connected domain is i+1_start and i+1_end, one of if meeting i_start<i+1_start and i_end>i+1_end or i_start>i+1_start and i_end<i+1_end both of these case, then think that the connected domain of this two row is to have the region of overlap, otherwise it is assumed that the connected domain of this two row does not have the region of overlap;If there being crossing region, write down pixel value original position less than normal and pixel value end position bigger than normal in corresponding two row.
(8) resolution of binary image in extraction step (7), and repeat step (6) n time altogether, wherein n is less than or equal to d!, the set of regions of the set of digits obtaining polishing number of times numeral composition and the region composition intersected;
(9) according to position relationship, the bounding box of set of digits and the bounding box of set of regions are mated;
(10) the discrete point optimal solution according to set of digits, does normalization to corresponding region, obtains numeric area;
(11) masterplate numeral is set up: a, machined in digital control system and do not have the outward appearance of defective quartz ceramic crucible to set up iconic model;B, content according to step (1)-(9) obtain masterplate numeric area;Numeric area after normalization and template numeric area are subtracted each other, the sum of the pixel value in this numeric area after calculating difference, and masterplate numeral minimum in template numeric area;Pixel value in described numeric area and minimum in template numeric area masterplate numeral respectively defect area position and polishing number of times;
(12) the defect area position result that will identify that and polishing number of times deliver to Trajectory Planning System, generate machining locus file.
A kind of system of processing applying the above-mentioned crucible defect grinding processing method based on image;It includes digital control system, milling robot and computer;
Described milling robot includes controlling seat and being located at the mechanical arm controlling seat and the sanding apparatus of installation and mechanical arm tail end;
Described computer includes industrial camera, computer vision module, trajectory planning module, computer and milling robot communication module, computer and digital control system communication module and computer and industrial camera communication module;
The control seat of described milling robot and described digital control system all electrically connect with described computer.
The present invention proposes a kind of crucible defect grinding processing method based on image according to described content and applies its system of processing, the method, by identifying that crucible needs defect area position and the grinding number of times of grinding, carries out, for robot below, the machined parameters that polishing provides necessary.The method is applicable to the polishing of silica crucible defect, after the regional location marking defect workman and the number of times needing grinding, industrial camera is utilized to be taken pictures in all faces of crucible respectively, then by image transmitting to PC end, by PC, image is carried out pretreatment, the defect area position and grinding number of times that need grinding are identified by the algorithm that recycling regional location identification and numeral identify, planning for next step polishing track is prepared, and ultimately generates the machining locus file that can make milling robot that crucible carries out automatically grinding.
The know-why of the present invention is described above in association with specific embodiment.These descriptions are intended merely to explanation principles of the invention, and can not be construed to limiting the scope of the invention by any way.Based on explanation herein, those skilled in the art need not pay performing creative labour can associate other detailed description of the invention of the present invention, and these modes fall within protection scope of the present invention.
Claims (9)
1., based on the crucible defect grinding processing method of image, it is applied to numerical control sander device people, it is characterised in that: comprise the steps:
(1) defective locations of crucible to be processed and the number of times of corresponding defective locations needs polishing are manually marked;
(2) in digital control system, the outward appearance of crucible to be processed is set up iconic model;
(3) image processed and generate grey level histogram;
(4) according to grey level histogram, set pixel threshold, image is carried out binaryzation and generates binary image;
(5) travel through the pixel of binary image, namely do not set to 0 single in each connected domain of binary image with other same pixel bigger pixel values of value continuous print;
(6) according to pixel value in binary image more than the position of pixel threshold set, forwardly and rearwardly search in binary image, it is determined that the original position of every a line connected domain and end position in binary image;
(7) judging whether the connected domain of adjacent rows has crossing region, if there being crossing region, writing down original position that in corresponding two row, pixel value is less than normal and pixel value end position bigger than normal;
(8) resolution of binary image in extraction step (7), and repeat step (6) n time altogether, wherein n is less than or equal to d!, the set of regions of the set of digits obtaining polishing number of times numeral composition and the region composition intersected;
(9) set of digits obtained in step (8) and set of regions are carried out discrete point optimal solution respectively to solve, and the discrete point optimal solution of set of digits is mated with corresponding set of regions discrete point optimal solution;
(10) the discrete point optimal solution according to set of digits, does normalization to corresponding region, obtains numeric area;
(11) numeric area after normalization and template numeric area are subtracted each other, the sum of the pixel value in this numeric area after calculating difference, and masterplate numeral minimum in template numeric area;Pixel value in described numeric area and minimum in template numeric area masterplate numeral respectively defect area position and polishing number of times;
(12) the defect area position that will identify that and polishing number of times deliver to Trajectory Planning System, generate machining locus file, and crucible is polished by milling robot according to this machining locus file.
2. the crucible defect grinding processing method based on image according to claim 1, it is characterized in that: comprise the steps: when described step (4) generates binary image more than the pixel setting pixel threshold, gray scale in image is set to 255, gray scale is set to 0 less than the pixel setting pixel threshold, thus obtaining binary image.
3. the crucible defect grinding processing method based on image according to claim 1, it is characterised in that: step (7) judging, whether the connected domain of adjacent rows has in the step in crossing region and comprises the steps:
If the original position of certain connected domain of the i-th row is i_end till being i_start and end, the connected domain position of the position of this connected domain Yu i+1 row is compared, the original position assuming wherein certain connected domain is i+1_start and i+1_end, one of if meeting i_start<i+1_start and i_end>i+1_end or i_start>i+1_start and i_end<i+1_end both of these case, then it is assumed that the connected domain of this two row is to have the region of overlap;Otherwise it is assumed that the connected domain of this two row does not have the region of overlap.
4. the crucible defect grinding processing method based on image according to claim 1, it is characterised in that: the method carrying out respectively when discrete point optimal solution solves set of digits and set of regions in described step (9) being to adopt bounding box calculates.
5. the crucible defect grinding processing method based on image according to claim 4, it is characterised in that: described step (12) also includes the step setting up masterplate numeral:
A, in digital control system, set up iconic model to machining the outward appearance not having defective crucible;
Content described in b, basis (1)-(9) obtains masterplate numeric area.
6. the crucible defect grinding processing method based on image according to claim 5, it is characterized in that: discrete point optimal solution according to set of digits in described step (10), comprise the steps: when corresponding region is done normalization all numerals to be zoomed in or out to and the template equirotal size of numeral bounding box.
7. the crucible defect grinding processing method based on image according to claim 1, it is characterized in that: described step (2) step also comprises the steps: to utilize each face that quartz ceramic crucible to be processed is included lateral surface, medial surface and bottom surface by industrial camera to take pictures, then by image transmitting to PC end.
8. the extracting method of the quartz ceramic crucible defect grinding parameter based on image according to claim 1, it is characterized in that: in upper described step (3) before generating described grey level histogram, also comprise the steps: image is sequentially carried out the operation of pretreatment, noise filtering and gray processing.
9. application system of processing of the crucible defect grinding processing method based on image as described in any one in claim 1-8;It is characterized in that: include digital control system, milling robot and computer;
Described milling robot includes controlling seat and being located at the mechanical arm controlling seat and the sanding apparatus of installation and mechanical arm tail end;
Described computer includes industrial camera, computer vision module, trajectory planning module, computer and milling robot communication module, computer and digital control system communication module and computer and industrial camera communication module;
The control seat of described milling robot and described digital control system all electrically connect with described computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610342546.4A CN105798927B (en) | 2016-05-23 | 2016-05-23 | Crucible defect grinding processing method based on image and processing system with crucible defect grinding processing method based on image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610342546.4A CN105798927B (en) | 2016-05-23 | 2016-05-23 | Crucible defect grinding processing method based on image and processing system with crucible defect grinding processing method based on image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105798927A true CN105798927A (en) | 2016-07-27 |
CN105798927B CN105798927B (en) | 2017-02-08 |
Family
ID=56452740
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610342546.4A Expired - Fee Related CN105798927B (en) | 2016-05-23 | 2016-05-23 | Crucible defect grinding processing method based on image and processing system with crucible defect grinding processing method based on image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105798927B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106568783A (en) * | 2016-11-08 | 2017-04-19 | 广东工业大学 | Hardware part defect detecting system and method |
CN107584375A (en) * | 2017-09-13 | 2018-01-16 | 中国电子科技集团公司第十三研究所 | Ceramic package grinding and polishing method and device |
CN108326853A (en) * | 2018-01-17 | 2018-07-27 | 广东工业大学 | A kind of milling robot system |
CN108460798A (en) * | 2017-12-29 | 2018-08-28 | 江苏金恒信息科技股份有限公司 | A kind of sample notch localization method and device |
CN108509947A (en) * | 2018-01-29 | 2018-09-07 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of automatic identification polishing process based on artificial neural network |
CN109584259A (en) * | 2019-01-18 | 2019-04-05 | 西安科技大学 | A kind of silica crucible bubble layering counting device and method |
CN110625491A (en) * | 2019-08-29 | 2019-12-31 | 中车青岛四方机车车辆股份有限公司 | Polishing apparatus and polishing method |
CN110625628A (en) * | 2019-10-24 | 2019-12-31 | 四川智能创新铸造有限公司 | Method and device for removing nondestructive testing defects of large steel castings |
CN110988140A (en) * | 2019-11-25 | 2020-04-10 | 西南交通大学 | Intelligent identification method for fatigue cracks of orthotropic steel bridge deck slab |
TWI704110B (en) * | 2018-10-15 | 2020-09-11 | 日商Sumco股份有限公司 | Method and device of estimating inner peripheral surface of quartz crucible |
CN116985143A (en) * | 2023-09-26 | 2023-11-03 | 山东省智能机器人应用技术研究院 | Polishing track generation system of polishing robot |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005030813A (en) * | 2003-07-09 | 2005-02-03 | Okamoto Machine Tool Works Ltd | Three-dimensional noncontact measuring apparatus and cnc precision grinding apparatus using the same |
CN1672871A (en) * | 2005-04-07 | 2005-09-28 | 上海第三机床厂 | Digital profile grinder |
CN102172869A (en) * | 2011-03-30 | 2011-09-07 | 铁道第三勘察设计院集团有限公司 | Vision-based track plate numerical controlled grinder optimization grinding method |
CN103163834A (en) * | 2011-12-11 | 2013-06-19 | 西安扩力机电科技有限公司 | Intelligent numerical control machine tool based on image processing |
CN103886579A (en) * | 2013-12-11 | 2014-06-25 | 西安交通大学 | Abrasive particle chain self-adaptive segmentation method orienting online ferrographic image automatic identification |
CN103995934A (en) * | 2014-05-22 | 2014-08-20 | 北京铭隆世纪科技有限公司 | Automatic polishing method and device |
CN104175222A (en) * | 2014-08-25 | 2014-12-03 | 上海交通大学 | Large-ball grinding trace feature image capturing device and sphericity judgment method |
-
2016
- 2016-05-23 CN CN201610342546.4A patent/CN105798927B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005030813A (en) * | 2003-07-09 | 2005-02-03 | Okamoto Machine Tool Works Ltd | Three-dimensional noncontact measuring apparatus and cnc precision grinding apparatus using the same |
CN1672871A (en) * | 2005-04-07 | 2005-09-28 | 上海第三机床厂 | Digital profile grinder |
CN102172869A (en) * | 2011-03-30 | 2011-09-07 | 铁道第三勘察设计院集团有限公司 | Vision-based track plate numerical controlled grinder optimization grinding method |
CN103163834A (en) * | 2011-12-11 | 2013-06-19 | 西安扩力机电科技有限公司 | Intelligent numerical control machine tool based on image processing |
CN103886579A (en) * | 2013-12-11 | 2014-06-25 | 西安交通大学 | Abrasive particle chain self-adaptive segmentation method orienting online ferrographic image automatic identification |
CN103995934A (en) * | 2014-05-22 | 2014-08-20 | 北京铭隆世纪科技有限公司 | Automatic polishing method and device |
CN104175222A (en) * | 2014-08-25 | 2014-12-03 | 上海交通大学 | Large-ball grinding trace feature image capturing device and sphericity judgment method |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106568783B (en) * | 2016-11-08 | 2019-12-03 | 广东工业大学 | A kind of hardware defect detecting system and method |
CN106568783A (en) * | 2016-11-08 | 2017-04-19 | 广东工业大学 | Hardware part defect detecting system and method |
CN107584375A (en) * | 2017-09-13 | 2018-01-16 | 中国电子科技集团公司第十三研究所 | Ceramic package grinding and polishing method and device |
CN108460798A (en) * | 2017-12-29 | 2018-08-28 | 江苏金恒信息科技股份有限公司 | A kind of sample notch localization method and device |
CN108326853B (en) * | 2018-01-17 | 2021-08-24 | 广东工业大学 | Polishing robot system |
CN108326853A (en) * | 2018-01-17 | 2018-07-27 | 广东工业大学 | A kind of milling robot system |
CN108509947A (en) * | 2018-01-29 | 2018-09-07 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of automatic identification polishing process based on artificial neural network |
TWI704110B (en) * | 2018-10-15 | 2020-09-11 | 日商Sumco股份有限公司 | Method and device of estimating inner peripheral surface of quartz crucible |
CN109584259A (en) * | 2019-01-18 | 2019-04-05 | 西安科技大学 | A kind of silica crucible bubble layering counting device and method |
CN109584259B (en) * | 2019-01-18 | 2021-10-01 | 赵谦 | Quartz crucible bubble layered counting device and method |
CN110625491A (en) * | 2019-08-29 | 2019-12-31 | 中车青岛四方机车车辆股份有限公司 | Polishing apparatus and polishing method |
CN110625628A (en) * | 2019-10-24 | 2019-12-31 | 四川智能创新铸造有限公司 | Method and device for removing nondestructive testing defects of large steel castings |
CN110625628B (en) * | 2019-10-24 | 2023-08-25 | 四川智能创新铸造有限公司 | Method and device for removing nondestructive testing defects of large steel castings |
CN110988140B (en) * | 2019-11-25 | 2021-10-01 | 西南交通大学 | Intelligent identification method for fatigue cracks of orthotropic steel bridge deck slab |
CN110988140A (en) * | 2019-11-25 | 2020-04-10 | 西南交通大学 | Intelligent identification method for fatigue cracks of orthotropic steel bridge deck slab |
CN116985143A (en) * | 2023-09-26 | 2023-11-03 | 山东省智能机器人应用技术研究院 | Polishing track generation system of polishing robot |
CN116985143B (en) * | 2023-09-26 | 2024-01-09 | 山东省智能机器人应用技术研究院 | Polishing track generation system of polishing robot |
Also Published As
Publication number | Publication date |
---|---|
CN105798927B (en) | 2017-02-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105798927A (en) | Crucible defect grinding processing method based on image and processing system with crucible defect grinding processing method based on image | |
CN110211182B (en) | Liquid crystal backlight visual positioning method based on gray scale matching and target contour | |
CN108760766B (en) | Image splicing method for detecting surface micro-defects of large-caliber optical crystal | |
CN105260693B (en) | A kind of laser two-dimensional code localization method | |
CN110717872B (en) | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning | |
CN103185730B (en) | Method for building rule of thumb of defect classification, and methods for classifying defect and judging killer defect | |
CN113538486B (en) | Method for improving identification and positioning accuracy of automobile sheet metal workpiece | |
CN101885152A (en) | Automatically-aligned numerical control cutting method for pre-printed image plate | |
CN108021683B (en) | Three-dimensional labeling-based similar model retrieval implementation method | |
AU2021104874A4 (en) | A surface roughness detection method based on machine vision and machine learning | |
CN107036560B (en) | The Surface Roughness Detecting Method of optical glass accurate grinding processing | |
He et al. | A critical review for machining positioning based on computer vision | |
CN108509947A (en) | A kind of automatic identification polishing process based on artificial neural network | |
CN114580559A (en) | Speed measuring method based on monocular vision system | |
CN112784894B (en) | Automatic labeling method for rock slice microscopic image | |
CN112508855A (en) | Roundness judgment method in iridium crucible edge rolling process | |
CN106841211A (en) | Platform and method of a kind of utilization machine vision to cell piece surface defects detection | |
CN107563990A (en) | A kind of photovoltaic cell chipping and the detection algorithm of blunt type and v-notch | |
CN108734706B (en) | Rotor winding image detection method fusing regional distribution characteristics and edge scale angle information | |
CN110470670A (en) | A kind of magnetic core defect detecting system and method based on image procossing | |
CN107292924B (en) | The characteristic automatic recognition method for the laser groove that a kind of pair of laser processing is formed | |
CN113160147B (en) | Image feature recognition and matching system for heat treatment workpiece | |
CN104408285A (en) | Intelligent computing method for dimensional chain | |
CN115609154A (en) | Multi-axis linkage laser superfinishing method and equipment | |
CN104655627A (en) | Method for detecting coating failure of workpiece |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170208 Termination date: 20180523 |
|
CF01 | Termination of patent right due to non-payment of annual fee |