CN108672316A - A kind of micro parts quality detecting system based on convolutional neural networks - Google Patents
A kind of micro parts quality detecting system based on convolutional neural networks Download PDFInfo
- Publication number
- CN108672316A CN108672316A CN201810256711.3A CN201810256711A CN108672316A CN 108672316 A CN108672316 A CN 108672316A CN 201810256711 A CN201810256711 A CN 201810256711A CN 108672316 A CN108672316 A CN 108672316A
- Authority
- CN
- China
- Prior art keywords
- image
- micro
- convolutional neural
- neural networks
- micro parts
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/38—Collecting or arranging articles in groups
-
- 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
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)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of micro parts quality detecting system based on convolutional neural networks, includes the following steps：A, micro parts surface image information is acquired by the image capture module that micro-vision is constituted；B, micro-vision the image collected is detected using convolutional neural networks model and is classified to the defect image detected；C, classification results are sent into master controller and control signal is sent out to end effector；D, control signal that manipulator actuator in end is sent out according to controller executes the pickup to corresponding micro parts and classification, i.e., part is sent into corresponding storage box.So far, whole system completes the detection to micro parts surface quality and classifies with defect.System of the present invention can be effectively used for micro parts detection, improve detection degree of automation and efficiency and reduce the labor intensity of influence and worker of the human factor to detection process.
Description
Technical field
The present invention relates to micro parts detection technique field, specially a kind of micro parts matter based on convolutional neural networks
Amount detection systems.
Background technology
With the continuous development of Chinese industrial, the research in micro-nano field also becomes more and more important, and micro assemby conduct
One important link of micro-nano field operation also becomes increasingly to be taken seriously, and in the process, the quality of micro parts then can
The quality of micro assemby product is directly influenced, therefore, then becomes particularly important using suitable micro parts quality testing means.
Traditional artificial detection method there is detection efficiency it is low, great work intensity, the drawbacks such as precision is low, other researcher
Computer micro-vision is introduced into the system and micro parts are detected by edge detection in conjunction with some edge detection operators
Defect situation, this method can comparatively fast and accurately detect the defect of piece surface, but it is unnecessary to still remain some
Mistake is detected, for example, when edge detection threshold setting not will appear part own edges error detection at that time into defect, or will
The relatively large defect of part is mistakenly considered into part edge, in addition this case where also or by the noise misidentification of image at defect
Detection mode can not distinguish the various defects detected.
In recent years, with the appearance of millions of tape label training set and the appearance based on GPU training algorithms, make training
Complicated convolutional network model no longer extravagantly hopes that convolutional neural networks are a kind of gradually development, and cause the efficient image paid attention to extensively
Recognition methods.It is largely identified in hand-written script based on the model of convolutional neural networks, is obtained in the class test in the libraries ImageNet
Original achievement, many papers all utilize convolutional neural networks, good achievement are obtained in vision sorter task.
Therefore convolutional neural networks, which are introduced into micro parts Surface Quality Inspection System, based on the above becomes one kind
Feasible program simplifies detecting step compared to edge detection method, while improving detection certainly compared to traditional artificial detection
Dynamicization degree and efficiency and the labor intensity for reducing influence and worker of the human factor to detection process.
Invention content
It is an object of the invention to design and provide a kind of micro parts quality detecting system based on convolutional neural networks,
To solve the problems mentioned in the above background technology.
To achieve the above object, the present invention provides the following technical solutions：A kind of micro parts based on convolutional neural networks
Quality detecting system includes the following steps：
A, micro parts surface image information is acquired by the image capture module that micro-vision is constituted；
B, using convolutional neural networks model micro-vision the image collected is detected and the defect image to detecting
Classify；
C, classification results are sent into master controller and control signal is sent out to end effector；
D, the control signal that manipulator actuator in end is sent out according to controller come execute the pickup to corresponding micro parts with point
Part is sent into corresponding storage box by class.
Preferably, image capture module includes with lower part in the step A：
A, microlens are connected with CCD camera, and are fixed on a Three Degree Of Freedom micromotion platform together；
B, after position adjustment is suitable, CCD camera obtains the surface image of micro parts by microlens；
C, image is acquired and is preserved by host computer, for subsequent detection and classification.
Preferably, it detects in the step B and includes the following steps with defect classification method：
A, convolutional neural networks structure and parameter are initialized；
B, the micro parts surface image in training set is analyzed, is classified to image according to the defect type of its appearance
And complete the hand labeled before training；
C, the training set image marked is uniformly formatted as fixed size：2M*2M；
D, it is based on existing deep learning framework, training convolutional neural networks is treated using formatted training set and is trained,
Trained iterative process includes the backpropagation of the propagated forward and error to each small lot data successively, weighting parameter
The unified update after batch data revert all propagation finishes, the weighting parameter after updating are used for next round iteration, directly
To setting iterations are reached, the final accuracy rate of network is calculated；
E, network structure and relevant parameter are constantly adjusted, makes that accuracy rate is trained to converge to an ideal value；
The data such as model and weighting parameter that F, export trains are used for subsequent control system；
G, the collected image to be detected feeding of micro-vision module is trained into network, exports testing result.
Preferably, end effector module includes with lower part in the step D：
A, for completing the manipulator to part pickup and placement according to control signal；
B, manipulator is fixed on the micromotion platform of another Three Degree Of Freedom, for realizing the movement of its Three Degree Of Freedom, convenient for pickup
Part in different location simultaneously puts it into different storage boxes；
C, motion controller is sent to micromotion platform for receiving image classification result and converting thereof into corresponding control signal
It goes to complete to pick up part accordingly to act with placement with manipulator；
D, part classification storage box classifying for certified products and all kinds of substandard products parts that detect.
Compared with prior art, the beneficial effects of the invention are as follows：
（1）Micro parts detecting system provided by the invention can effectively improve detection the degree of automation and accuracy and effect
Rate.
（2）The detecting system can reflect part defect type in real time, and there have convenient for the total quality to part to be a relatively accurate
Assessment is conducive to manufacturer according to defect type modified technique, improves production efficiency.
Description of the drawings
Fig. 1 is flow chart of the present invention.
Fig. 2 is the overall system architecture figure of the present invention.
Fig. 3 is that convolutional neural networks train flow chart.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
It please refers to Fig.1, attached drawing 2 and attached drawing 3, the present invention provide a kind of system schema：It is a kind of based on convolutional neural networks
Micro parts quality detecting system.Present invention is further described in detail with specific implementation mode below in conjunction with the accompanying drawings：Wherein
Attached drawing 1 is system overall flow figure, and attached drawing 2 is overall system architecture figure, and attached drawing 3 is the entirety training flow of convolutional neural networks
Figure：
Include the following steps：
A, micro parts surface image information is acquired by the image capture module that micro-vision is constituted；
B, using convolutional neural networks model micro-vision the image collected is detected and the defect image to detecting
Classify；
C, classification results are sent into master controller and control signal is sent out to end effector；
D, the control signal that manipulator actuator in end is sent out according to controller come execute the pickup to corresponding micro parts with point
Part is sent into corresponding storage box by class.
In the present invention, image capture module includes the following steps in step A：
A, microlens are connected with CCD camera, are fixed on a Three Degree Of Freedom micromotion platform together；
B, after position adjustment is suitable, CCD camera obtains the surface image of micro parts by microlens；
C, image is acquired and is preserved by host computer, for subsequent detection and classification.
The present invention replaces the work of human eye in traditional artificial detection, microlens and CCD phases using micro-vision module
Machine, which is fixed on the micromotion platform of Three Degree Of Freedom, may be implemented, to piece surface image multiposition, more fully to acquire, and ensure inspection
The reliability of survey, improves the degree of automation of detection process, while reducing error caused by human factor.
In the present invention, sort operation method includes the following steps in step B：
A, convolutional neural networks structure and parameter are initialized；
B, the micro parts surface image in training set is analyzed, is classified to image according to the defect type of its appearance
And complete the hand labeled before training；
C, the training set image marked is uniformly formatted as fixed size：2M*2M；
D, it is based on existing deep learning framework, training convolutional neural networks is treated using formatted training set and is trained,
Trained iterative process includes the backpropagation of the propagated forward and error to each small lot data successively, weighting parameter
The unified update after batch data revert all propagation finishes, the weighting parameter after updating are used for next round iteration, directly
To setting iterations are reached, the final accuracy rate of network is calculated；
E, network structure and relevant parameter are constantly adjusted, makes that accuracy rate is trained to converge to an ideal value；
The data such as model and weighting parameter that F, export trains are used for subsequent control system；
G, the collected image to be detected feeding of micro-vision module is trained into network, exports testing result.
The detection that the present invention uses utilizes convolutional neural networks with defect classification method, is needed before testing first with
Some training set images are trained designed convolutional neural networks, and trained network model can be used for acquisition
To image be detected and classify, relied in recent years the largely appearance of the training algorithm based on GPU, and made network training and answer
With becoming more universal, the program improves the intelligence degree of detection, while reducing the labor intensity of worker.
In the present invention, end effector module includes with lower part in step D：
A, for completing the manipulator to part pickup and placement according to control signal；
B, manipulator is fixed on the micromotion platform of another Three Degree Of Freedom, for realizing the movement of its Three Degree Of Freedom, convenient for pickup
Part in different location；
C, motion controller is sent to micromotion platform for receiving image classification result and converting thereof into corresponding control signal
It goes to complete to pick up part accordingly to act with placement with manipulator；
D, part classification storage box classifying for certified products and all kinds of substandard products parts that detect.
The end effector module of the present invention can complete the sorting according to part quality situation to part, convenient for part
Quality condition carries out timely statistics and feedback.
In conclusion image classification method provided by the invention is efficient, can effectively improve image classification accuracy and
Efficiency.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding without departing from the principles and spirit of the present invention can carry out these embodiments a variety of variations, modification, replace
And modification, the scope of the present invention is defined by the appended.
Claims (4)
1. a kind of micro parts quality detecting system based on convolutional neural networks, it is characterised in that：Include the following steps：
A, micro parts surface image information is acquired by the image capture module that micro-vision is constituted；
B, using convolutional neural networks model micro-vision the image collected is detected and the defect image to detecting
Classify；
C, classification results are sent into master controller and control signal is sent out to end effector；
D, the control signal that manipulator actuator in end is sent out according to controller come execute the pickup to corresponding micro parts with point
Part is sent into corresponding storage box by class.
2. a kind of micro parts quality detecting system based on convolutional neural networks according to claim 1, feature exist
In：Image capture module includes with lower part in the step A：
A, microlens are connected with CCD camera, and are fixed on a Three Degree Of Freedom micromotion platform together；
B, after position adjustment is suitable, CCD camera obtains the surface image of micro parts by microlens；
C, image is acquired and is preserved by host computer, for subsequent detection and classification.
3. a kind of image classification method based on convolutional neural networks according to claim 1, it is characterised in that：The step
It detects in rapid B and includes the following steps with defect classification method：
A, convolutional neural networks structure and parameter are initialized；
B, the micro parts surface image in training set is analyzed, is classified to image according to the defect type of its appearance
And complete the hand labeled before training；
C, the training set image marked is uniformly formatted as fixed size：2M*2M；
D, it is based on existing deep learning framework, training convolutional neural networks is treated using formatted training set and is trained,
Trained iterative process includes the backpropagation of the propagated forward and error to each small lot data successively, weighting parameter
The unified update after batch data revert all propagation finishes, the weighting parameter after updating are used for next round iteration, directly
To setting iterations are reached, the final accuracy rate of network is calculated；
E, network structure and relevant parameter are constantly adjusted, makes that accuracy rate is trained to converge to an ideal value；
The data such as model and weighting parameter that F, export trains are used for subsequent control system；
G, the collected image to be detected feeding of micro-vision module is trained into network, exports testing result.
4. a kind of image classification method based on convolutional neural networks according to claim 1, it is characterised in that：The step
End effector module includes with lower part in rapid D：
A, for completing the manipulator to part pickup and placement according to control signal；
B, manipulator is fixed on the micromotion platform of another Three Degree Of Freedom, for realizing the movement of its Three Degree Of Freedom, convenient for pickup
Part in different location simultaneously puts it into different storage boxes；
C, motion controller is sent to micromotion platform for receiving image classification result and converting thereof into corresponding control signal
It goes to complete to pick up part accordingly to act with placement with manipulator；
D, part classification storage box classifying for certified products and all kinds of substandard products parts that detect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810256711.3A CN108672316A (en) | 2018-03-27 | 2018-03-27 | A kind of micro parts quality detecting system based on convolutional neural networks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810256711.3A CN108672316A (en) | 2018-03-27 | 2018-03-27 | A kind of micro parts quality detecting system based on convolutional neural networks |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108672316A true CN108672316A (en) | 2018-10-19 |
Family
ID=63799691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810256711.3A Pending CN108672316A (en) | 2018-03-27 | 2018-03-27 | A kind of micro parts quality detecting system based on convolutional neural networks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108672316A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109283906A (en) * | 2018-11-10 | 2019-01-29 | 国网电力科学研究院武汉南瑞有限责任公司 | A kind of monitoring system and method stacking process |
| CN110310260A (en) * | 2019-06-19 | 2019-10-08 | 北京百度网讯科技有限公司 | Sub-material decision-making technique, equipment and storage medium based on machine learning model |
| CN111054658A (en) * | 2019-11-15 | 2020-04-24 | 西安和光明宸科技有限公司 | Color sorting system and sorting method |
| CN111054650A (en) * | 2019-11-15 | 2020-04-24 | 西安和光明宸科技有限公司 | Size sorting system and sorting method |
| CN111069080A (en) * | 2019-11-15 | 2020-04-28 | 西安和光明宸科技有限公司 | Shape sorting system and sorting method |
| CN111300144A (en) * | 2019-11-25 | 2020-06-19 | 上海大学 | Automatic detection method for tool wear state based on image processing |
| CN113245238A (en) * | 2021-05-13 | 2021-08-13 | 苏州迪宏人工智能科技有限公司 | Elbow welding flaw detection method, device and system |
| CN113269736A (en) * | 2021-05-17 | 2021-08-17 | 唐旸 | Method, system and medium for automated inspection of fastener dimensions |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02200198A (en) * | 1989-01-27 | 1990-08-08 | Kazuo Sugamura | Monoclonal antibody against il-2 receptor and hybridoma producing the same antibody |
| US5957307A (en) * | 1995-01-18 | 1999-09-28 | Siemens Aktiengesellschaft | Coding station for a mail sorting system |
| CN102854194A (en) * | 2012-09-11 | 2013-01-02 | 中南大学 | Object surface defect detection method and apparatus based on linear array CCD |
| CN106018415A (en) * | 2016-05-20 | 2016-10-12 | 哈尔滨理工大学 | System for detecting quality of small parts based on micro-vision |
| CN107064170A (en) * | 2017-04-11 | 2017-08-18 | 深圳市深视智能科技有限公司 | One kind detection phone housing profile tolerance defect method |
| CN107437094A (en) * | 2017-07-12 | 2017-12-05 | 北京木业邦科技有限公司 | Plank method for sorting and system based on machine learning |
| CN107607554A (en) * | 2017-09-26 | 2018-01-19 | 天津工业大学 | A kind of Defect Detection and sorting technique of the zinc-plated stamping parts based on full convolutional neural networks |
| CN107657603A (en) * | 2017-08-21 | 2018-02-02 | 北京精密机电控制设备研究所 | A kind of industrial appearance detecting method based on intelligent vision |
| CN107742132A (en) * | 2017-11-07 | 2018-02-27 | 江南大学 | Potato detection method of surface flaw based on convolutional neural networks |
-
2018
- 2018-03-27 CN CN201810256711.3A patent/CN108672316A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02200198A (en) * | 1989-01-27 | 1990-08-08 | Kazuo Sugamura | Monoclonal antibody against il-2 receptor and hybridoma producing the same antibody |
| US5957307A (en) * | 1995-01-18 | 1999-09-28 | Siemens Aktiengesellschaft | Coding station for a mail sorting system |
| CN102854194A (en) * | 2012-09-11 | 2013-01-02 | 中南大学 | Object surface defect detection method and apparatus based on linear array CCD |
| CN106018415A (en) * | 2016-05-20 | 2016-10-12 | 哈尔滨理工大学 | System for detecting quality of small parts based on micro-vision |
| CN107064170A (en) * | 2017-04-11 | 2017-08-18 | 深圳市深视智能科技有限公司 | One kind detection phone housing profile tolerance defect method |
| CN107437094A (en) * | 2017-07-12 | 2017-12-05 | 北京木业邦科技有限公司 | Plank method for sorting and system based on machine learning |
| CN107657603A (en) * | 2017-08-21 | 2018-02-02 | 北京精密机电控制设备研究所 | A kind of industrial appearance detecting method based on intelligent vision |
| CN107607554A (en) * | 2017-09-26 | 2018-01-19 | 天津工业大学 | A kind of Defect Detection and sorting technique of the zinc-plated stamping parts based on full convolutional neural networks |
| CN107742132A (en) * | 2017-11-07 | 2018-02-27 | 江南大学 | Potato detection method of surface flaw based on convolutional neural networks |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109283906A (en) * | 2018-11-10 | 2019-01-29 | 国网电力科学研究院武汉南瑞有限责任公司 | A kind of monitoring system and method stacking process |
| CN110310260A (en) * | 2019-06-19 | 2019-10-08 | 北京百度网讯科技有限公司 | Sub-material decision-making technique, equipment and storage medium based on machine learning model |
| CN110310260B (en) * | 2019-06-19 | 2021-10-15 | 北京百度网讯科技有限公司 | Material distribution decision method, equipment and storage medium based on machine learning model |
| CN111054658A (en) * | 2019-11-15 | 2020-04-24 | 西安和光明宸科技有限公司 | Color sorting system and sorting method |
| CN111054650A (en) * | 2019-11-15 | 2020-04-24 | 西安和光明宸科技有限公司 | Size sorting system and sorting method |
| CN111069080A (en) * | 2019-11-15 | 2020-04-28 | 西安和光明宸科技有限公司 | Shape sorting system and sorting method |
| CN111300144A (en) * | 2019-11-25 | 2020-06-19 | 上海大学 | Automatic detection method for tool wear state based on image processing |
| CN113245238A (en) * | 2021-05-13 | 2021-08-13 | 苏州迪宏人工智能科技有限公司 | Elbow welding flaw detection method, device and system |
| CN113269736A (en) * | 2021-05-17 | 2021-08-17 | 唐旸 | Method, system and medium for automated inspection of fastener dimensions |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108672316A (en) | A kind of micro parts quality detecting system based on convolutional neural networks | |
| CN110314854B (en) | Workpiece detecting and sorting device and method based on visual robot | |
| CN106971152B (en) | Method for detecting bird nest in power transmission line based on aerial images | |
| CN105891233B (en) | Lens surface defect intelligent checking system and its implementation based on machine vision | |
| CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
| CN107944504B (en) | Board recognition and machine learning method and device for board recognition and electronic equipment | |
| CN107832780B (en) | Artificial intelligence-based wood board sorting low-confidence sample processing method and system | |
| CN109959661A (en) | Automatic optical detection method, equipment and its deep learning system | |
| CN107369635B (en) | Intelligent semiconductor equipment system based on deep learning | |
| CN107486415A (en) | Thin bamboo strip defect on-line detecting system and detection method based on machine vision | |
| KR20220095216A (en) | BBP-assisted defect detection flow for SEM images | |
| CN112318485B (en) | Object sorting system and image processing method and device thereof | |
| CN102998316B (en) | Transparent liquid impurity detection system and detection method thereof | |
| CN107328787A (en) | A kind of metal plate and belt surface defects detection system based on depth convolutional neural networks | |
| CN107084992A (en) | A kind of capsule detection method and system based on machine vision | |
| CN103324937A (en) | Method and device for labeling targets | |
| CN113077450B (en) | Cherry grading detection method and system based on deep convolutional neural network | |
| CN105044122A (en) | Copper part surface defect visual inspection system and inspection method based on semi-supervised learning model | |
| CN108320306A (en) | Merge the video target tracking method of TLD and KCF | |
| CN113569922A (en) | Intelligent lossless apple sorting method | |
| CN114359199A (en) | Fish counting method, device, equipment and medium based on deep learning | |
| CN113780423A (en) | Single-stage target detection neural network based on multi-scale fusion and industrial product surface defect detection model | |
| Wu et al. | An end-to-end learning method for industrial defect detection | |
| CN104952754A (en) | Coated silicon chip sorting method based on machine vision | |
| CN114863311A (en) | Automatic tracking method and system for inspection target of transformer substation robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181019 |
|
| RJ01 | Rejection of invention patent application after publication |