CN111251296B - Visual detection system suitable for pile up neatly electric motor rotor - Google Patents
Visual detection system suitable for pile up neatly electric motor rotor Download PDFInfo
- Publication number
- CN111251296B CN111251296B CN202010053352.9A CN202010053352A CN111251296B CN 111251296 B CN111251296 B CN 111251296B CN 202010053352 A CN202010053352 A CN 202010053352A CN 111251296 B CN111251296 B CN 111251296B
- Authority
- CN
- China
- Prior art keywords
- module
- data
- motor rotor
- rotor
- coordinate system
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 33
- 230000000007 visual effect Effects 0.000 title claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 230000004438 eyesight Effects 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 239000013598 vector Substances 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000001914 filtration Methods 0.000 claims description 22
- 238000011179 visual inspection Methods 0.000 claims 1
- 238000000034 method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- 230000004382 visual function Effects 0.000 description 1
Images
Classifications
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G61/00—Use of pick-up or transfer devices or of manipulators for stacking or de-stacking articles not otherwise provided for
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a visual detection system suitable for a palletizing motor rotor, which has the technical scheme that the visual detection system comprises a visual sensor, an image preprocessing module, a feature extraction module, a data processing module and a neural network monitoring module which are sequentially connected; the vision sensor is used for obtaining an original image of the motor rotor, a coordinate positioning module is arranged on the vision sensor, the image preprocessing module is electrically connected with a detection information database, the image preprocessing module is used for comparing and classifying the gray level of the original image with a preset value in comparison reference data, the feature extraction module can extract the distance between feature vertexes in the data to be compared and form feature vectors, the data processing module forms the comparison data and generates a corresponding output network mode, the neural network monitoring module is used for identifying and classifying the output network mode, and the vision detection system can accurately detect the motor rotor.
Description
Technical Field
The invention relates to the technical field of industrial robots, in particular to a visual detection system suitable for a palletizing motor rotor.
Background
The robot vision mainly uses a computer to simulate the visual function of a human, not only the simple extension of human eyes, but also a part of the functions of human brain. Information is extracted from the objective food image, processed and understood, and finally used for actual detection, measurement and control. The machine vision has the biggest characteristics of high speed, large information amount and multiple functions; the industrial robot is combined with a vision technology, so that the industrial robot can be helped to work more intelligently, and the trend of the application field of the industrial robot is achieved. Industrial robots are currently being used gradually in palletizing operations.
In the motor industry, because the motor industry is high in labor intensity, a plurality of production processes are completed manually, the labor intensity of workers is high, the working environment is harsh and the like, and therefore, the motor rotor is prone to artificial errors in the production process, and the phenomena of detection omission and detection errors are prone to occurring in the manual detection process.
However, at present, in the process of detecting industrial parts with high precision such as motor rotors, the detection efficiency is low, and the detection is not accurate enough, so that the industrial parts are difficult to be widely popularized and applied.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a visual detection system suitable for a motor rotor of a stacking machine, which can accurately detect the motor rotor.
In order to achieve the purpose, the invention provides the following technical scheme: a visual detection system suitable for a palletizing motor rotor comprises a visual sensor, an image preprocessing module, a feature extraction module, a data processing module and a neural network monitoring module which are sequentially connected;
the vision sensor is used for obtaining an original image of the motor rotor, a coordinate positioning module is arranged on the vision sensor and used for obtaining a cross central point by taking four vertex cross points in the length direction of the original image of the motor rotor, the coordinate positioning module takes the cross central point as an original point and takes the width direction of the original image of the electronic rotor as a direction axis to establish a rotor coordinate system and capture position data of each vertex of the motor rotor to form data to be compared;
the image preprocessing module is electrically connected with a detection information database, and the detection information database is used for prestoring comparison reference data of various motor rotors;
the image preprocessing module is used for comparing and classifying the gray level of the original image with a preset value in the comparison reference data;
the characteristic extraction module can extract the distance between characteristic vertexes in the data to be compared and form a characteristic vector;
the data processing module is connected with the detection information database, compares the feature vectors extracted by the feature extraction module with comparison reference data to form comparison data, and generates a corresponding output network mode;
the neural network monitoring module is used for identifying and classifying the output network mode.
The invention is further configured to: and a marking module is arranged in the neural network monitoring module and used for generating and storing an electronic tag for the motor rotor with a qualified detection result.
The invention is further configured to: the neural network monitoring module is electrically connected with a palletizing robot, and the palletizing robot is used for palletizing a motor rotor which is not marked with an electronic tag to a designated area.
The invention is further configured to: the robot palletizer is respectively connected with the characteristic extraction module and the detection information database and is used for receiving a rotor coordinate system and a preset coordinate system in comparison reference data, the visual sensor is arranged on the robot palletizer, and the robot palletizer can control the visual sensor to rotate so as to align the rotor coordinate system with the preset coordinate system in the comparison reference data.
The invention is further configured to: and the data processing module is used for comparing the data of each vertex position in the rotor coordinate system with the data of each vertex position in the preset coordinate system to form coincidence comparison data, generating a corresponding input network mode and transmitting the corresponding input network mode to the neural network monitoring module.
The invention is further configured to: the marking module can generate a coincidence degree label according to coincidence comparison data, and the palletizing robot palletizes the motor rotor which does not accord with the set coincidence degree to an appointed area according to the coincidence degree label.
The invention is further configured to: the image preprocessing module comprises a filtering module, the filtering module is provided with a conveying device model, the filtering module captures a filtering area in the data to be compared according to the conveying device model, the filtering area comprises the conveying device model in the data to be compared, and the filtering module deletes the data in the filtering area from the data to be compared to form filtered data to be compared.
In conclusion, the invention has the following beneficial effects: the motor rotor is classified in the first step through the gray level, the comparison amount is reduced, the subsequent comparison efficiency is improved, the motor rotor is coordinated, the vertex coordinates of each point are captured from a rotor coordinate system, the feature vector is generated according to each vertex coordinate, the comparison speed is accelerated and the comparison accuracy is improved through vectorization comparison.
Drawings
FIG. 1 is a schematic flow diagram of a vision inspection system;
fig. 2 is a schematic flow chart of a method of a vision inspection system.
Reference numerals: 1. a vision sensor; 11. a coordinate positioning module; 2. an image preprocessing module; 21. detecting an information database; 22. a filtration module; 3. a feature extraction module; 4. a data processing module; 5. a neural network monitoring module; 51. a marking module; 52. pile up neatly machine people.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. In which like parts are designated by like reference numerals. It should be noted that the terms "front," "back," "left," "right," "upper" and "lower" used in the following description refer to directions in the drawings, and the terms "bottom" and "top," "inner" and "outer" refer to directions toward and away from, respectively, the geometric center of a particular component.
Referring to fig. 1 to 2, in order to achieve the above object, the present invention provides the following technical solutions: in order to achieve the purpose, the invention provides the following technical scheme: a visual detection system suitable for a palletizing motor rotor comprises a visual sensor 1, an image preprocessing module 2, a feature extraction module 3, a data processing module 4 and a neural network monitoring module 5 which are sequentially connected;
the vision sensor 1 is used for obtaining an original image of the motor rotor, a coordinate positioning module 11 is arranged on the vision sensor 1, the coordinate positioning module 11 is used for obtaining a cross center point by taking four vertex cross points in the length direction of the original image of the motor rotor, the coordinate positioning module 11 takes the cross center point as an original point and takes the width direction of the original image of the electronic rotor as a direction axis to establish a rotor coordinate system and capture position data of each vertex of the motor rotor to form data to be compared; the motor rotor enters a visual range of the visual sensor 1 along with the conveying device, the visual sensor 1 intercepts an electronic rotor image and generates an original image, a coordinate positioning module 11 obtains a cross center point according to four vertex cross points in the length direction of the motor rotor in the original image intercepted by the visual sensor 1, a rotor coordinate system is established by taking the width direction of the original image as an x axis and the length direction as a y axis and taking the vertical direction of the y axis as a z axis, and position vertex coordinates of a rotating shaft, a rotor core, a three-phase rotor winding, a rotor winding outlet head, a commutator and the like of the motor rotor are captured to generate data to be compared.
The image preprocessing module 2 is electrically connected with a detection information database 21, and the detection information database 21 is used for prestoring comparison reference data of various motor rotors; the detection information database 21 prestores various important data of various motor rotors: the motor rotor self-coordinate system, the motor rotor self-gray level and the perfect coordinates of each position of the motor rotor.
The image preprocessing module 2 is used for comparing the gray level of the original image with a preset value in the comparison reference data and classifying the gray level; the image preprocessing module 2 matches the gray level in the original image with a preset gray level prestored in the comparison reference data, and classifies the original image in one step, so that the subsequent comparison amount is reduced, and the system comparison workload is reduced.
The feature extraction module 3 can extract the distance between feature vertexes in the data to be compared and form a feature vector;
the data processing module 4 is connected with the detection information database 21, and the data processing module 4 compares the feature vectors extracted by the feature extraction module 3 with comparison reference data to form comparison data and generates a corresponding output network mode; the feature extraction module 3 generates feature vectors from the vertexes captured and generated in the vision sensor 1 and the adjacent vertexes, and the data processing module 4 compares the feature vectors with pre-stored feature vectors of comparison reference data to determine whether the distance between the vertexes meets the specification. Whether the two sides of the wound coil are straight or not can be determined according to the vector value in the z direction, whether the size of the inner diameter and the outer diameter of the rotating shaft is within the range meeting the standard or not is determined, whether the wound coil has a crossing phenomenon or not is determined according to the numerical value of the vector, whether the thickness of the electromagnetic wire is uniform or not is determined according to the vector value in the x direction, and whether the lengths of the two ends extending out of the notches are consistent or not and whether the notches are high or not is determined according.
The neural network monitoring module 5 is used for identifying and classifying the output network modes. The output network patterns transmitted to the neural network monitoring module 5 are identified, the output network patterns meeting the specification are classified into one type, and the output network patterns not meeting the specification are classified into another type.
The invention has the advantages that: the motor rotor is classified in the first step through the gray level, the comparison amount is reduced, the subsequent comparison efficiency is improved, the motor rotor is coordinated, the vertex coordinates of each point are captured from a rotor coordinate system, the feature vector is generated according to each vertex coordinate, the comparison speed is accelerated and the comparison accuracy is improved through vectorization comparison.
The neural network monitoring module 5 is internally provided with a marking module 51, and the marking module 51 is used for generating and storing an electronic tag for the qualified motor rotor. The marking module 51 generates a corresponding electronic tag for the motor rotor meeting the specification, and then stores the electronic tag, thereby reducing the workload in the subsequent sorting and packaging processes.
The neural network monitoring module 5 is electrically connected with a palletizing robot 52, and the palletizing robot 52 is used for palletizing a motor rotor which is not marked with an electronic tag to a designated area. The robot palletizer 52 palletizes the motor rotor which is not in accordance with the specification and does not have the electronic tag according to the motor tag. Then, the maintenance and the detection are carried out again, and whether the electronic tag is produced or not is judged.
The palletizing robot 52 is respectively connected with the feature extraction module 3 and the detection information database 21 and is configured to receive a rotor coordinate system and a preset coordinate system in the comparison reference data, the vision sensor 1 is disposed on the palletizing robot 52, and the palletizing robot 52 can control the vision sensor 1 to rotate, so that the rotor coordinate system is aligned with the preset coordinate system in the comparison reference data. The vision sensor 1 is arranged on the palletizing robot 52, the rotor coordinate system is transmitted into the palletizing robot 52 while the rotor coordinate system is generated, and the rotor coordinate system is aligned with the preset coordinate system through the first-step rotation of the palletizing robot 52, so that the situation that the subsequent generated vectors are floated in numerical value due to deviation of the placing angle when the motor rotor is placed is prevented.
The data processing module 4 compares the data of the vertex position of the rotor coordinate system with the data of the vertex position of the preset coordinate system to form coincidence comparison data, generates a corresponding input network mode and transmits the coincidence comparison data to the neural network monitoring module 5. And under the condition that the rotor coordinate system is aligned with the preset coordinate system, comparing each vertex coordinate in the data to be compared with each vertex in the comparison reference data to form coincidence comparison data, comparing whether the coincidence comparison data meets the standard or not, and when the coincidence degrees of all the captured vertex coordinates meet the specification, determining the motor rotor with the coincident eigenvector as a final qualified product.
The marking module 51 can generate a coincidence degree label according to the coincidence comparison data, and the palletizing robot 52 palletizes the motor rotor which does not accord with the set coincidence degree to a designated area according to the coincidence degree label. Marking the motor rotor with preset contact ratio according to the obtained labels with different contact ratios and classifying the motor rotor into grades with different grades; and the palletizing robot 52 palletizes the motor rotor without the coincidence degree label according to whether the motor rotor has the coincidence degree label.
The image preprocessing module 2 comprises a filtering module 22, the filtering module 22 is provided with a conveying device model, the filtering module 22 captures a filtering area in the data to be compared according to the conveying device model, the filtering area comprises the conveying device model in the data to be compared, and the filtering module 22 deletes the data in the filtering area from the data to be compared to form filtered data to be compared. The filter module 22 is capable of excluding the transport device, so that there is only a motor rotor when capturing the generated original image, and the influence of the gray level of the transport device on the gray level of the motor rotor is avoided when the image preprocessing module 2 performs gray level classification.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (2)
1. A visual detection system suitable for a palletizing motor rotor is characterized by comprising a visual sensor (1), an image preprocessing module (2), a feature extraction module (3), a data processing module (4) and a neural network monitoring module (5) which are sequentially connected;
the vision sensor (1) is used for obtaining an original image of the motor rotor, a coordinate positioning module (11) is arranged on the vision sensor (1), the coordinate positioning module (11) is used for obtaining a cross center point by taking four vertex cross points in the length direction of the original image of the motor rotor, the coordinate positioning module (11) takes the cross center point as an original point and takes the width direction of the original image of the electronic rotor as a direction axis to establish a rotor coordinate system and captures position data of each vertex of the motor rotor to form data to be compared;
the image preprocessing module (2) is electrically connected with a detection information database (21), and the detection information database (21) is used for prestoring comparison reference data of various motor rotors;
the image preprocessing module (2) is used for comparing the gray level of the original image with a preset value in comparison reference data and classifying the gray level;
the characteristic extraction module (3) can extract the distance between characteristic vertexes in the data to be compared and form a characteristic vector;
the data processing module (4) is connected with the detection information database (21), and the data processing module (4) compares the feature vectors extracted by the feature extraction module (3) with comparison reference data to form comparison data and generates a corresponding output network mode;
the neural network monitoring module (5) is used for identifying and classifying output network modes;
a marking module (51) is arranged in the neural network monitoring module (5), and the marking module (51) is used for generating and storing an electronic tag for the motor rotor with a qualified detection result;
the neural network monitoring module (5) is electrically connected with a palletizing robot (52), and the palletizing robot (52) is used for palletizing a motor rotor which is not marked with an electronic tag to a designated area;
the palletizing robot (52) is respectively connected with the characteristic extraction module (3) and the detection information database (21) and is used for receiving a rotor coordinate system and a preset coordinate system in comparison reference data, the visual sensor (1) is arranged on the palletizing robot (52) and the palletizing robot (52) can control the visual sensor (1) to rotate so as to align the rotor coordinate system with the preset coordinate system in the comparison reference data;
the data processing module (4) compares the data of each vertex position in the rotor coordinate system with the data of each vertex position in the preset coordinate system to form coincidence comparison data, generates a corresponding input network mode and transmits the coincidence comparison data to the neural network monitoring module (5);
the marking module (51) can generate a coincidence degree label according to coincidence comparison data, and the palletizing robot (52) palletizes the motor rotor which does not accord with the set coincidence degree to an appointed area according to the coincidence degree label.
2. The visual inspection system of claim 1 for a palletiser motor rotor, wherein: the image preprocessing module (2) comprises a filtering module (22), the filtering module (22) is provided with a conveying device model, the filtering module (22) captures a filtering area in the data to be compared according to the conveying device model, the filtering area comprises the conveying device model in the data to be compared, and the filtering module (22) deletes the data in the filtering area from the data to be compared to form the data to be compared.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010053352.9A CN111251296B (en) | 2020-01-17 | 2020-01-17 | Visual detection system suitable for pile up neatly electric motor rotor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010053352.9A CN111251296B (en) | 2020-01-17 | 2020-01-17 | Visual detection system suitable for pile up neatly electric motor rotor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111251296A CN111251296A (en) | 2020-06-09 |
| CN111251296B true CN111251296B (en) | 2021-05-18 |
Family
ID=70954213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010053352.9A Active CN111251296B (en) | 2020-01-17 | 2020-01-17 | Visual detection system suitable for pile up neatly electric motor rotor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111251296B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112591356A (en) * | 2020-12-04 | 2021-04-02 | 佛山隆深机器人有限公司 | Stacking visual detection system in closed or semi-closed limited space |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004050390A (en) * | 2002-07-24 | 2004-02-19 | Fanuc Ltd | Work taking out device |
| CN103383730A (en) * | 2013-06-03 | 2013-11-06 | 上海索广映像有限公司 | Automatic BNC terminal detecting machine and work method thereof |
| CN105772407A (en) * | 2016-01-26 | 2016-07-20 | 耿春茂 | Waste classification robot based on image recognition technology |
| CN106568783A (en) * | 2016-11-08 | 2017-04-19 | 广东工业大学 | Hardware part defect detecting system and method |
| CN106997590A (en) * | 2017-04-12 | 2017-08-01 | 浙江硕和机器人科技有限公司 | A kind of image procossing and detecting system based on detection product performance |
| CN207181307U (en) * | 2017-04-12 | 2018-04-03 | 浙江硕和机器人科技有限公司 | A kind of stereoscopic image acquisition device |
| US10269108B2 (en) * | 2017-09-01 | 2019-04-23 | Midea Group Co., Ltd. | Methods and systems for improved quality inspection of products using a robot |
| CN109909998A (en) * | 2017-12-12 | 2019-06-21 | 北京猎户星空科技有限公司 | A kind of method and device controlling manipulator motion |
| CN110116415A (en) * | 2019-06-12 | 2019-08-13 | 中北大学 | A kind of Bottle & Can class rubbish identification sorting machine people based on deep learning |
| CN110458798A (en) * | 2019-06-20 | 2019-11-15 | 长沙理工大学 | Damper defective vision detection method, system and medium based on critical point detection |
-
2020
- 2020-01-17 CN CN202010053352.9A patent/CN111251296B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004050390A (en) * | 2002-07-24 | 2004-02-19 | Fanuc Ltd | Work taking out device |
| CN103383730A (en) * | 2013-06-03 | 2013-11-06 | 上海索广映像有限公司 | Automatic BNC terminal detecting machine and work method thereof |
| CN105772407A (en) * | 2016-01-26 | 2016-07-20 | 耿春茂 | Waste classification robot based on image recognition technology |
| CN106568783A (en) * | 2016-11-08 | 2017-04-19 | 广东工业大学 | Hardware part defect detecting system and method |
| CN106997590A (en) * | 2017-04-12 | 2017-08-01 | 浙江硕和机器人科技有限公司 | A kind of image procossing and detecting system based on detection product performance |
| CN207181307U (en) * | 2017-04-12 | 2018-04-03 | 浙江硕和机器人科技有限公司 | A kind of stereoscopic image acquisition device |
| US10269108B2 (en) * | 2017-09-01 | 2019-04-23 | Midea Group Co., Ltd. | Methods and systems for improved quality inspection of products using a robot |
| CN109909998A (en) * | 2017-12-12 | 2019-06-21 | 北京猎户星空科技有限公司 | A kind of method and device controlling manipulator motion |
| CN110116415A (en) * | 2019-06-12 | 2019-08-13 | 中北大学 | A kind of Bottle & Can class rubbish identification sorting machine people based on deep learning |
| CN110458798A (en) * | 2019-06-20 | 2019-11-15 | 长沙理工大学 | Damper defective vision detection method, system and medium based on critical point detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111251296A (en) | 2020-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109785317B (en) | Automatic pile up neatly truss robot's vision system | |
| CN109974582B (en) | Device and method for non-contact visual detection of core wire size of automobile wire harness | |
| CN109013405A (en) | It is a kind of independently detected with cast(ing) surface and substandard products sorting function robot system | |
| Xia et al. | Workpieces sorting system based on industrial robot of machine vision | |
| CN113877836B (en) | Intelligent identification sorting system based on visual detection system | |
| CN207238542U (en) | A kind of thin bamboo strip defect on-line detecting system based on machine vision | |
| CN105478529B (en) | Full-automatic stamping line products surface quality on-line detecting system and method | |
| Bellandi et al. | Roboscan: a combined 2D and 3D vision system for improved speed and flexibility in pick-and-place operation | |
| CN112497219B (en) | Columnar workpiece classifying and positioning method based on target detection and machine vision | |
| CN109003911A (en) | A kind of method of semiconductor chip pin forming defects detection | |
| CN111645111A (en) | Intelligent manufacturing system and method based on industrial robot | |
| CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
| CN111251296B (en) | Visual detection system suitable for pile up neatly electric motor rotor | |
| CN113012098B (en) | Iron tower angle steel punching defect detection method based on BP neural network | |
| CN107598775A (en) | It is a kind of by laser detect the method that simultaneously multi-axis robot is polished | |
| CN112150439A (en) | Automatic sorting equipment and sorting method for injection molding parts | |
| CN109397072A (en) | Work piece processing method and system of processing | |
| CN112847321A (en) | Industrial robot visual image recognition system based on artificial intelligence | |
| CN105945953A (en) | Visual identification system for robot | |
| CN114913346A (en) | Intelligent sorting system and method based on product color and shape recognition | |
| CN111168674A (en) | Test card assembling method based on CCD positioning system | |
| CN111136011A (en) | Material sorting method based on machine vision recognition system | |
| CN108957384B (en) | Method and device for distinguishing direction of turnover box and electric energy metering equipment | |
| Qian et al. | The autonomous detection of sheet metal parts using imageprocessing | |
| CN116175542B (en) | Method, device, electronic equipment and storage medium for determining clamp grabbing sequence |
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 |