CN111242902A - Method, system and equipment for identifying and detecting parts based on convolutional neural network - Google Patents
Method, system and equipment for identifying and detecting parts based on convolutional neural network Download PDFInfo
- Publication number
- CN111242902A CN111242902A CN202010001493.6A CN202010001493A CN111242902A CN 111242902 A CN111242902 A CN 111242902A CN 202010001493 A CN202010001493 A CN 202010001493A CN 111242902 A CN111242902 A CN 111242902A
- Authority
- CN
- China
- Prior art keywords
- template
- detected
- detection
- neural network
- convolutional neural
- 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
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title abstract description 6
- 238000001514 detection method Methods 0.000 claims abstract description 76
- 238000004519 manufacturing process Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims 2
- 238000010168 coupling process Methods 0.000 claims 2
- 238000005859 coupling reaction Methods 0.000 claims 2
- 230000007547 defect Effects 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000005341 toughened glass Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010330 laser marking Methods 0.000 description 1
- 238000005496 tempering Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method, a system and equipment for identifying and detecting parts based on a convolutional neural network, which comprises the following steps: manufacturing standard templates for various parts to be detected to generate detection models; identifying a standard template of a part to be detected; scanning a front image of a part to be detected, and identifying and detecting a countersunk hole and a black covering hole in the front image of the part to be detected through a detection model; scanning the back image of the part to be detected, identifying label information and detecting; the invention compares the number, the type and the position of the label, the countersunk hole and the black covering hole of the part to be detected with the standard template through image recognition, judges whether the countersunk hole, the black covering hole and the label on the part meet the requirements or not, has high detection speed, provides a rapid digital detection means for a large number of small-size countersunk holes on the airplane part, has stable and reliable precision, greatly improves the detection efficiency and effectively reduces the workload of detection personnel.
Description
Technical Field
The invention relates to the technical field of part visual detection, in particular to a method, a system and equipment for identifying and detecting parts based on a convolutional neural network.
Background
The existing large civil aircraft is usually assembled by tens of thousands of parts, and in order to ensure the flight safety of the large civil aircraft, the requirements on various parameters of the parts are very high. The countersunk holes and the black covering holes are one of the most common structural characteristics in aircraft manufacturing engineering, exist on various aircraft parts such as frames, ribs, wall plates and skins in large quantity, are important factors influencing the service life and flight safety of the aircraft, and form great hidden danger to the safety of the aircraft due to assembly stress generated by forced assembly when the quality defects such as geometric deviation exist. The aircraft parts are large in size, complex in appearance and large in number of counter bores on the parts, so that detection of the counter bores and black covering hole positions on the aircraft parts becomes a technical difficulty, detection is troublesome by using a traditional measuring method, a large amount of time and labor are consumed, and working efficiency is reduced.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects in the prior art and provides a part identification and detection method, system and equipment based on a convolutional neural network.
The invention is realized by the following technical scheme:
a part identification and detection method based on a convolutional neural network is characterized by comprising the following steps: a. manufacturing standard templates for various parts to be detected to generate detection models; b. identifying a standard template of a part to be detected; c. placing the part to be detected at the original point position of a workbench; d. scanning the front image of the part to be detected, comparing the front image with the standard template, and identifying and detecting the countersunk hole and the black covering hole in the front image of the part to be detected through the detection model; e. scanning the back image of the part to be detected, comparing the back image with the standard template, identifying label information and detecting; f. and outputting a detection result.
According to the above technical solution, preferably, step a includes: placing the template part on a workbench and aligning the template part with an original point, and scanning the front image of the template part; marking the template part outline, the countersunk hole and the black covering hole in the front image of the template part; extracting and storing information of the counter bores and the black covering holes in the front image of the template part; carrying out classification sample training on the marked template part outline, the countersunk hole and the black covering hole by using a convolutional neural network, and generating a detection model; scanning the back image of the template part; and carrying out deep learning on the label in the image on the back side of the template part, and extracting and storing the position of the label.
According to the above technical solution, preferably, the counterbore information includes a counterbore size and a counterbore position, and the black covering hole information includes a black covering hole radius and a black covering hole position.
According to the above technical solution, preferably, step b includes: and reading the work order information on the part to be detected through a code scanning gun to obtain a standard template of the part to be detected.
According to the above technical solution, preferably, step d further includes: and correcting the front image of the part to be detected according to the standard template to obtain the offset of the part.
The invention also discloses a part identification and detection system based on the convolutional neural network, which comprises the following components: the training unit is used for manufacturing standard templates for various parts to be detected and generating detection models; the acquisition unit is used for identifying a standard template of the part to be detected; the front part detection unit is used for placing the part to be detected at the original point position of the workbench, scanning the front image of the part to be detected, comparing the front image with a standard template, and identifying and detecting a countersunk hole and a black covering hole in the front image of the part to be detected through a detection model; the back part detection unit is used for scanning the back image of the part to be detected, comparing the back image with a standard template, identifying label information and detecting the label information; and the output unit is used for outputting the detection result.
According to the above technical solution, preferably, the training unit includes: the front information extraction module is used for placing the template part on the workbench and aligning the template part with the original point, scanning the front image of the template part, marking the template part outline, the countersunk hole and the black covering hole in the front image of the template part, extracting and storing the countersunk hole information and the black covering hole information in the front image of the template part, performing classification sample training on the marked template part outline, the countersunk hole and the black covering hole by using a convolutional neural network, and generating a detection model; and the back information extraction module is used for scanning the back image of the template part, deeply learning the label in the back image of the template part, extracting the position of the label and storing the position of the label.
According to the above technical solution, preferably, the obtaining unit includes: and the code scanning module is used for reading the work order information on the part to be detected through the code scanning gun to obtain the standard template of the part to be detected.
According to the above technical solution, preferably, the front part detecting unit includes: and the correction module corrects the front image of the part to be detected according to the standard template to obtain the offset of the part.
The invention also discloses a part identification and detection device based on the convolutional neural network, which comprises a workbench, an upper image acquisition mechanism arranged above the workbench and a lower image acquisition mechanism arranged below the workbench, wherein the upper image acquisition mechanism comprises a slide rail arranged horizontally, a plurality of mounting frames connected with the slide rail in a sliding manner and first cameras fixedly connected with the mounting frames, and the lower image acquisition mechanism comprises two first guide rails arranged oppositely, a second guide rail connected between the two first guide rails in a sliding manner, a positioning frame connected with the second guide rail in a sliding manner and second cameras fixedly connected with the positioning frame.
The invention has the beneficial effects that:
to wait to detect the part and put on the workstation, will wait to detect the label of part through image recognition, the quantity in counter bore and black covering hole, kind and position and standard template contrast, judge the counter bore on the part, whether black covering hole and label meet the requirements, it is fast to detect, a large amount of small-size counter bores for aircraft part on provide the detection means of quick digitization, high durability and convenient use, the precision is reliable and stable, the efficiency of detection has been improved by a wide margin, effectively reduced detection personnel's work load.
Drawings
FIG. 1 is a schematic workflow diagram of the present invention.
Fig. 2 is a schematic front view of the present invention.
In the figure: 1. a slide rail; 2. a mounting frame; 3. a first camera; 4. tempering the glass; 5. a color-changeable film; 6. a work table; 7. a positioning frame; 8. a second camera; 9. a second guide rail.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and preferred embodiments.
As shown in the figure, the invention comprises the following steps: a. manufacturing standard templates for various parts to be detected to generate detection models; b. identifying a standard template of a part to be detected; c. placing the part to be detected at the original point position of a workbench 6; d. scanning the front image of the part to be detected, comparing the front image with the standard template, and identifying and detecting the countersunk hole and the black covering hole in the front image of the part to be detected through the detection model; e. scanning the back image of the part to be detected, comparing the back image with the standard template, identifying label information and detecting; f. and outputting a detection result, wherein in the example, when the detection result is output, the correct counter bores are marked by green, the wrong counter bores are marked by red, the bottom label is correctly identified and correspondingly displayed on a screen, if the radius of the covering hole exceeds a preset length by more than a preset range, an alarm prompt is required, and in addition, detection data of the parts, such as detection pictures, part numbers, work order numbers, detection time, detection results and other information, are stored and an electronic report is automatically generated. To wait to detect the part and put on workstation 6, will wait to detect the label of part through image recognition, the quantity in counter bore and black covering hole, kind and position and standard template contrast, judge the counter bore on the part, whether black covering hole and label meet the requirements, detection speed is fast, a large amount of small-size counter bores for aircraft part on provide quick digital detection means, high durability and convenient use, the precision is reliable and stable, the efficiency of detection has been improved by a wide margin, the effectual work load that has reduced the testing personnel.
According to the above embodiment, preferably, step a includes: placing the template part on a workbench 6 and aligning the template part with an original point, and scanning the front image of the template part; marking the template part outline, the countersunk hole and the black covering hole in the front image of the template part; extracting and storing information of the counter bores and the black covering holes in the front image of the template part; carrying out classification sample training on the marked template part contour, the countersunk hole and the black covered hole by using a convolutional neural network, and generating a detection model, wherein the marked template part contour, the countersunk hole and the black covered hole can be subjected to classification sample training by using a network such as frcnn, yolo and the like; scanning the back image of the template part; and carrying out deep learning on the label in the image on the back side of the template part, and extracting and storing the position of the label. In the process of training the counter sink, multiple deformation holes need to be collected in advance for training, the counter sink with the problem avoided being judged is caused by different deformations caused by photographing at different angles, and the detection precision is effectively improved.
According to the above embodiment, preferably, the counterbore information includes a counterbore size and a counterbore position, and the black cover hole information includes a black cover hole radius and a black cover hole position. Aligning one corner of the part with the original point of the workbench 6, determining the position coordinates of the countersunk hole and the black covering hole by the coordinate system relationship between the most basic physical coordinates of the construction platform and the image pixel coordinates, comparing the countersunk hole and the black covering hole to be detected with a standard template, and if the tolerance of the two corresponding positions is greater than the tolerance recorded in the template, marking the position as a suspicious position in the algorithm; in addition, after the diameter width of the black covering hole on the image is obtained by extracting coordinates, the diameter size is obtained according to a coordinate system and an image scale.
According to the above embodiment, preferably, step b includes: and reading the work order information on the part to be detected through a code scanning gun to obtain a standard template of the part to be detected. The work order information of each part to be detected is read through the code scanning gun, so that the standard template of the part can be conveniently extracted, meanwhile, the detection data of the part and the corresponding part can be bound, and an electronic report can be automatically generated.
According to the above embodiment, preferably, step d further includes: and correcting the front image of the part to be detected according to the standard template to obtain the offset of the part. The part to be detected is corrected according to the standard template through an algorithm to reach a position almost matched with the standard template on the image, so that the position coordinates of the countersunk hole and the black covering hole can be accurately determined.
The invention also discloses a part identification and detection system based on the convolutional neural network, which comprises the following components: the training unit is used for manufacturing standard templates for various parts to be detected and generating detection models; the acquisition unit is used for identifying a standard template of the part to be detected; the front part detection unit is used for placing the part to be detected at the original point position of the workbench 6, scanning the front image of the part to be detected, comparing the front image with a standard template, and identifying and detecting a countersunk hole and a black covering hole in the front image of the part to be detected through a detection model; the back part detection unit is used for scanning the back image of the part to be detected, comparing the back image with a standard template, identifying label information and detecting the label information; and the output unit is used for outputting the detection result.
According to the above embodiment, preferably, the training unit includes: the front information extraction module is used for placing the template part on the workbench 6 and aligning the template part with the original point, scanning the front image of the template part, marking the template part outline, the countersunk hole and the black covering hole in the front image of the template part, extracting and storing the countersunk hole information and the black covering hole information in the front image of the template part, performing classification sample training on the marked template part outline, the countersunk hole and the black covering hole by using a convolutional neural network, and generating a detection model; and the back information extraction module is used for scanning the back image of the template part, deeply learning the label in the back image of the template part, extracting the position of the label and storing the position of the label.
According to the above embodiment, preferably, the acquiring unit includes: and the code scanning module is used for reading the work order information on the part to be detected through the code scanning gun to obtain the standard template of the part to be detected.
According to the above embodiment, preferably, the front part detecting unit includes: and the correction module corrects the front image of the part to be detected according to the standard template to obtain the offset of the part.
The invention also discloses a part identification and detection device based on a convolutional neural network, which comprises a workbench 6, an upper image acquisition mechanism arranged above the workbench 6 and a lower image acquisition mechanism arranged below the workbench 6, wherein in the embodiment, the surface of the workbench 6 is toughened glass 4, a color-changeable film 5 is coated on the surface of the toughened glass 4, the color-changeable film 5 is semitransparent in dark color when being electrified and almost colorless and transparent when being powered off, the function of simultaneously detecting the front and the back of the part can be realized by the arrangement, the part does not need to be turned over manually during detection, the upper image acquisition mechanism comprises a sliding rail 1 which is horizontally arranged, a plurality of mounting frames 2 which are connected with the sliding rail 1 in a sliding way and a first camera 3 which is fixedly connected with the mounting frames 2, the number of the first cameras 3 which need to be used is determined according to the size of the part, the first camera 3 horizontally moves along the sliding rail 1, the moving distance is, the camera operating frequency is 40KHz, the maximum imaging time is about 0.6 second, the lower image acquisition mechanism comprises two first guide rails which are oppositely arranged, a second guide rail 9 which is connected between the two first guide rails in a sliding way, a positioning frame 7 which is connected with the second guide rail 9 in a sliding way and a second camera 8 which is fixedly connected with the positioning frame 7, the second camera 8 can move along the x axis and the y axis and is mainly used for acquiring a label which is labeled below a part and can automatically extract, correct and identify the label in a picture intercepted from the back of the airplane part, the vertical projection of the first guide rail is perpendicular to that of the sliding rail 1, the vertical projection of the second guide rail 9 is parallel to that of the sliding rail 1, the cameras are driven to move through the servo motor in the embodiment, and the laser marking mirror vibrating mechanism is further arranged in the embodiment and drives the two mirrors through the two steering gears to adjust the laser direction to the defect position. The first camera 3 and the second camera 8 respectively scan front and back images of the part to be detected, the front and back images are transmitted to a GPU industrial personal computer, the number, the types and the positions of the label, the countersunk hole and the black covering hole of the part to be detected are compared with a standard template through image recognition, and a detection result is transmitted to a display to automatically generate an electronic report.
To wait to detect the part and put on workstation 6, will wait to detect the label of part through image recognition, the quantity in counter bore and black covering hole, kind and position and standard template contrast, judge the counter bore on the part, whether black covering hole and label meet the requirements, detection speed is fast, a large amount of small-size counter bores for aircraft part on provide quick digital detection means, high durability and convenient use, the precision is reliable and stable, the efficiency of detection has been improved by a wide margin, the effectual work load that has reduced the testing personnel.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A part identification and detection method based on a convolutional neural network is characterized by comprising the following steps: a. manufacturing standard templates for various parts to be detected to generate detection models; b. identifying a standard template of a part to be detected; c. placing the part to be detected at the original point position of a workbench; d. scanning the front image of the part to be detected, comparing the front image with the standard template, and identifying and detecting the countersunk hole and the black covering hole in the front image of the part to be detected through the detection model; e. scanning the back image of the part to be detected, comparing the back image with the standard template, identifying label information and detecting; f. and outputting a detection result.
2. The convolutional neural network-based part identification and detection method as claimed in claim 1, wherein step a comprises: placing the template part on a workbench and aligning the template part with an original point, and scanning the front image of the template part; marking the template part outline, the countersunk hole and the black covering hole in the front image of the template part; extracting and storing information of the counter bores and the black covering holes in the front image of the template part; carrying out classification sample training on the marked template part outline, the countersunk hole and the black covering hole by using a convolutional neural network, and generating a detection model; scanning the back image of the template part; and carrying out deep learning on the label in the image on the back side of the template part, and extracting and storing the position of the label.
3. The convolutional neural network-based part identification and detection method as claimed in claim 2, wherein the counterbore information comprises counterbore size and counterbore position, and the black mask hole information comprises black mask hole radius and black mask hole position.
4. The convolutional neural network-based part identification and detection method as claimed in claim 1 or 3, wherein step b comprises: and reading the work order information on the part to be detected through a code scanning gun to obtain a standard template of the part to be detected.
5. The convolutional neural network-based part identification and detection method as claimed in claim 4, wherein step d further comprises: and correcting the front image of the part to be detected according to the standard template to obtain the offset of the part.
6. A component identification and detection system based on a convolutional neural network, the component identification and detection method based on the convolutional neural network is based on claim 1 or 4, and the component identification and detection method based on the convolutional neural network is characterized by comprising the following steps:
the training unit is used for manufacturing standard templates for various parts to be detected and generating detection models;
the acquisition unit is used for identifying a standard template of the part to be detected;
the front part detection unit is used for placing the part to be detected at the original point position of the workbench, scanning the front image of the part to be detected, comparing the front image with a standard template, and identifying and detecting a countersunk hole and a black covering hole in the front image of the part to be detected through a detection model;
the back part detection unit is used for scanning the back image of the part to be detected, comparing the back image with a standard template, identifying label information and detecting the label information;
and the output unit is used for outputting the detection result.
7. The convolutional neural network-based part identification and detection system of claim 6, wherein the training unit comprises: the front information extraction module is used for placing the template part on the workbench and aligning the template part with the original point, scanning the front image of the template part, marking the template part outline, the countersunk hole and the black covering hole in the front image of the template part, extracting and storing the countersunk hole information and the black covering hole information in the front image of the template part, performing classification sample training on the marked template part outline, the countersunk hole and the black covering hole by using a convolutional neural network, and generating a detection model; and the back information extraction module is used for scanning the back image of the template part, deeply learning the label in the back image of the template part, extracting the position of the label and storing the position of the label.
8. The convolutional neural network-based part identification and detection system as claimed in claim 7, wherein said obtaining unit comprises: and the code scanning module is used for reading the work order information on the part to be detected through the code scanning gun to obtain the standard template of the part to be detected.
9. The convolutional neural network-based part identification and detection system as claimed in claim 8, wherein said front part detection unit comprises: and the correction module corrects the front image of the part to be detected according to the standard template to obtain the offset of the part.
10. The utility model provides a part discernment and check out test set based on convolutional neural network, based on claim 1 or 4 a part discernment and detection method based on convolutional neural network, which is characterized in that, including the workstation, locate the last image acquisition mechanism of workstation top and locate the lower image acquisition mechanism of workstation below, go up image acquisition mechanism including the slide rail that the level set up, with a plurality of mounting brackets of slide rail sliding connection and with the first camera of mounting bracket rigid coupling, lower image acquisition mechanism is including setting up two first guide rails relatively, sliding connection second guide rail between two first guide rails, with second guide rail sliding connection's locating rack and with the second camera of locating rack rigid coupling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001493.6A CN111242902A (en) | 2020-01-02 | 2020-01-02 | Method, system and equipment for identifying and detecting parts based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001493.6A CN111242902A (en) | 2020-01-02 | 2020-01-02 | Method, system and equipment for identifying and detecting parts based on convolutional neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111242902A true CN111242902A (en) | 2020-06-05 |
Family
ID=70877665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010001493.6A Pending CN111242902A (en) | 2020-01-02 | 2020-01-02 | Method, system and equipment for identifying and detecting parts based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242902A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112067555A (en) * | 2020-11-12 | 2020-12-11 | 山东海德智能科技有限公司 | Part detection system capable of automatically visually identifying part types |
| CN113344913A (en) * | 2021-07-06 | 2021-09-03 | 常州宏大智能装备产业发展研究院有限公司 | Fabric flaw detection method |
| CN113706501A (en) * | 2021-08-26 | 2021-11-26 | 成都飞机工业（集团）有限责任公司 | Intelligent monitoring method for airplane assembly |
| CN114723748A (en) * | 2022-06-06 | 2022-07-08 | 深圳硅山技术有限公司 | Detection method, device and equipment of motor controller and storage medium |
| CN115661161A (en) * | 2022-12-29 | 2023-01-31 | 成都数联云算科技有限公司 | Method, device, storage medium, equipment and program product for detecting defects of parts |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699055A (en) * | 2013-12-24 | 2014-04-02 | 沈阳飞机工业（集团）有限公司 | Intelligent numerical control machining programming system and intelligent numerical control machining programming method for aircraft structural parts |
| CN106872488A (en) * | 2017-04-20 | 2017-06-20 | 广东振华科技股份有限公司 | A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device |
| CN107168269A (en) * | 2017-07-04 | 2017-09-15 | 中国科学院重庆绿色智能技术研究院 | A kind of MES system that detection is assembled for engine sprocket room housing |
| CN109142371A (en) * | 2018-07-31 | 2019-01-04 | 华南理工大学 | High density flexible exterior substrate defect detecting system and method based on deep learning |
| CN110009617A (en) * | 2019-04-02 | 2019-07-12 | 浙江大学 | A kind of shaft forgings online quality control method |
-
2020
- 2020-01-02 CN CN202010001493.6A patent/CN111242902A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699055A (en) * | 2013-12-24 | 2014-04-02 | 沈阳飞机工业（集团）有限公司 | Intelligent numerical control machining programming system and intelligent numerical control machining programming method for aircraft structural parts |
| CN106872488A (en) * | 2017-04-20 | 2017-06-20 | 广东振华科技股份有限公司 | A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device |
| CN107168269A (en) * | 2017-07-04 | 2017-09-15 | 中国科学院重庆绿色智能技术研究院 | A kind of MES system that detection is assembled for engine sprocket room housing |
| CN109142371A (en) * | 2018-07-31 | 2019-01-04 | 华南理工大学 | High density flexible exterior substrate defect detecting system and method based on deep learning |
| CN110009617A (en) * | 2019-04-02 | 2019-07-12 | 浙江大学 | A kind of shaft forgings online quality control method |
Non-Patent Citations (1)
| Title |
|---|
| 徐超 等: "基于视觉测量的沉头孔垂直度检测方法", 《浙江大学学报(工学刊)》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112067555A (en) * | 2020-11-12 | 2020-12-11 | 山东海德智能科技有限公司 | Part detection system capable of automatically visually identifying part types |
| CN113344913A (en) * | 2021-07-06 | 2021-09-03 | 常州宏大智能装备产业发展研究院有限公司 | Fabric flaw detection method |
| CN113706501A (en) * | 2021-08-26 | 2021-11-26 | 成都飞机工业（集团）有限责任公司 | Intelligent monitoring method for airplane assembly |
| CN113706501B (en) * | 2021-08-26 | 2024-03-19 | 成都飞机工业（集团）有限责任公司 | Intelligent monitoring method for aircraft assembly |
| CN114723748A (en) * | 2022-06-06 | 2022-07-08 | 深圳硅山技术有限公司 | Detection method, device and equipment of motor controller and storage medium |
| CN114723748B (en) * | 2022-06-06 | 2022-09-02 | 深圳硅山技术有限公司 | Detection method, device and equipment of motor controller and storage medium |
| CN115661161A (en) * | 2022-12-29 | 2023-01-31 | 成都数联云算科技有限公司 | Method, device, storage medium, equipment and program product for detecting defects of parts |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242902A (en) | Method, system and equipment for identifying and detecting parts based on convolutional neural network | |
| US10664992B2 (en) | Non-contact visual detection method for mark positioning of mobile phone touch screen | |
| CN111091538B (en) | Automatic identification and defect detection method and device for pipeline welding seams | |
| CN109357630A (en) | A kind of polymorphic type batch workpiece vision measurement system and method | |
| CN109142383B (en) | Character defect detection method based on morphology | |
| CN109429473A (en) | Automatic check method and device with polarity electronic component in circuit board | |
| CN107945184A (en) | A kind of mount components detection method positioned based on color images and gradient projection | |
| CN114705120A (en) | Mask information-based size measurement method and scoring system | |
| CN111982921A (en) | Hole defect detection method and device, conveying platform and storage medium | |
| CN110853018B (en) | Computer vision-based vibration table fatigue crack online detection system and detection method | |
| CN109253722A (en) | Merge monocular range-measurement system, method, equipment and the storage medium of semantic segmentation | |
| CN107507174A (en) | Power plant's instrument equipment drawing based on hand-held intelligent inspection is as recognition methods and system | |
| CN110118777A (en) | A kind of control system system integration Smart Verify platform | |
| CN110940670B (en) | Machine vision-based flexographic printing label printing first manuscript detection system and implementation method thereof | |
| CN208366871U (en) | Detection system | |
| JP2014134470A (en) | Wall surface diagnosis result recording system, wall surface diagnosis result recording method and wall surface diagnosis result recording program | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| EP4195142A1 (en) | System for detecting the defects of the wooden boards and their classification into quality classes | |
| CN111223081A (en) | Part hole opening recognition and detection method and system based on deep learning | |
| CN112505663A (en) | Calibration method for multi-line laser radar and camera combined calibration | |
| CN112333443A (en) | Lens performance detection system and method | |
| CN115980012A (en) | Medical detection circuit board gluing multi-angle detection system and detection method thereof | |
| CN201653911U (en) | Medical print visual detection device | |
| CN110658215B (en) | PCB automatic splicing detection method and device based on machine vision | |
| CN112763496A (en) | Mobile phone battery surface defect detection device and detection method thereof |
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: 20200605 |
|
| RJ01 | Rejection of invention patent application after publication |