CN110935651A - Bolt sorting method and system - Google Patents
Bolt sorting method and system Download PDFInfo
- Publication number
- CN110935651A CN110935651A CN201911193014.9A CN201911193014A CN110935651A CN 110935651 A CN110935651 A CN 110935651A CN 201911193014 A CN201911193014 A CN 201911193014A CN 110935651 A CN110935651 A CN 110935651A
- Authority
- CN
- China
- Prior art keywords
- bolt
- sorting
- image
- bolts
- images
- 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
Images
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
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- 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
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- 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
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- 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
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- 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
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/0009—Sorting of fasteners, e.g. screws, nuts, bolts
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a bolt sorting method, which comprises the following steps: acquiring an image of the bolt to be sorted to obtain a bolt image; classifying the bolts according to the bolt images to obtain a classification result; and controlling the sorting mechanism to act according to the sorting result to finish the bolt sorting. According to the bolt sorting device, the bolts to be sorted are subjected to image acquisition and classification, and sorting is controlled according to the classification result, so that the bolt sorting is completed, automatic sorting is realized, the workload of personnel is reduced, the sorting efficiency is improved, and manual sorting errors are avoided. The invention also discloses a bolt sorting system.
Description
Technical Field
The invention relates to the technical field of machine intelligence, in particular to a bolt sorting method and system.
Background
The accessories such as bolts are used in industrial production and life in a large number, the recovery and remanufacturing of a large number of waste bolts are necessary, and when the recovery or remanufacturing is carried out, the head type of the bolts directly influences the fixing method in processing. At present, the identification method of the screw head model is mainly a manual visual identification method, and the method has the advantages of high labor intensity, low efficiency, easy visual fatigue of detection personnel, frequent occurrence of wrong detection, potential quality hazard, and influence on the operation of maintenance and assembly personnel.
In view of the above-mentioned problem in the related art that the classification efficiency for the bolt head model is low, no effective solution has been proposed at present.
Disclosure of Invention
The invention provides a bolt sorting method and a bolt sorting system based on the problems
In view of the above, the present invention provides a bolt sorting method, which includes the following steps:
acquiring an image of the bolt to be sorted to obtain a bolt image;
classifying the bolts according to the bolt images to obtain a classification result;
and controlling the sorting mechanism to act according to the sorting result to finish the bolt sorting.
The invention also discloses a bolt sorting system, which comprises,
the image acquisition module is used for acquiring images of the bolts to be sorted to obtain bolt images;
the classification module is used for classifying the bolts according to the bolt images to obtain a classification result;
and the sorting module controls the sorting mechanism to act according to the sorting result so as to finish bolt sorting.
The invention has the beneficial effects that: through treating the sorting bolt and carrying out image acquisition and classification to control the letter sorting according to classification result, accomplish the bolt and relay, realized automatic letter sorting, reduced personnel's work load, improved letter sorting efficiency, avoided artifical letter sorting mistake.
Drawings
Fig. 1 shows a flowchart of a bolt sorting method according to an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the features of the embodiments of the present invention, i.e., the embodiments, may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
As shown in fig. 1, in this embodiment, a bolt sorting method includes the following steps:
acquiring an image of the bolt to be sorted to obtain a bolt image;
classifying the bolts according to the bolt images to obtain a classification result;
and controlling the sorting mechanism to act according to the sorting result to finish the bolt sorting.
Generally, the bolt has a hexagon shape, a cross shape, a straight shape and the like, and the image has certain regularity and identifiability.
In the above embodiment, through treating the sorting bolt and carry out image acquisition and classification to control the letter sorting according to classification result, accomplish the bolt and relay, realized automatic letter sorting, reduced personnel's work load, improved letter sorting efficiency, avoided artifical letter sorting mistake.
Optionally, the image acquisition of the bolt to be sorted is performed to obtain a bolt image, including,
and (5) carrying out image acquisition on the bolts to be sorted by using a CCD camera to obtain bolt images.
In the above embodiment, the CCD camera can be used for image acquisition, so that a better image effect can be obtained, the imaging quality is further improved, and the classification effect is improved. The model of the CCD camera may be XG 200H.
Optionally, before the step of acquiring an image of the bolt to be sorted by using the CCD camera to obtain the bolt image, the method further comprises,
and a coaxial light source is arranged on the left side or/and the right side of the CCD camera.
By arranging the coaxial light source, the light intensity is further enhanced, and the imaging quality is improved.
Optionally, before the classifying the bolt according to the bolt image to obtain the classification result, further comprising,
and preprocessing the bolt image.
In the embodiment, the classification accuracy and speed are improved by preprocessing the bolt image.
Optionally, the bolt image is subjected to graying processing, image enhancement, image filtering and image binarization processing, and then edge detection is performed.
Image filtering, which can be performed using the following formula,
taking σ as 1.5, wherein x and y respectively represent horizontal and vertical coordinates of image pixel points. The weight matrix is
And (3) binary processing, namely performing binary processing on the image by adopting a Gaussian filtering method according to the following formula:
wherein T is determined by a histogram bimodal method, and T is 60 in the invention.
Optionally, the graying process comprises, including,
and processing each pixel point in the bolt image as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)，
wherein (x, y) is the coordinates of the pixel points in the bolt image, wherein f (x, y) is the gray value of the bolt image at the pixel points of the coordinates (x, y), and R (x, y), G (x, y) and B (x, y) are the color values of the bolt image at R, G and B channels, respectively.
Optionally, the enhancement process includes, including,
and processing each pixel point in the bolt image as follows:
f(x，y)*＝k·f(x，y)+b
wherein k is 1, b is 16, f (x, y) is the gray value of the bolt image at the pixel point of the coordinate (x, y) before the enhancement processing, and f (x, y)*The gray value of the bolt image at the coordinate (x, y) pixel point after the enhancement processing is carried out.
Optionally, the classifying the bolts according to the bolt images to obtain a classification result includes performing deep learning on an identification system based on a convolutional neural network in advance;
and comparing the bolt image with a preset type in the identification system by using the identification system, and taking a result with the highest contact ratio as the classification result.
A Convolutional Neural Network (CNN) is a feed-forward neural network for image processing, which includes convolution calculation and has a depth structure, and is widely used for image classification, image recognition, and the like. The method has the advantages of mature algorithm and stable classification result. The identification system based on the convolutional neural network can be realized by adopting a library function of python language.
In the above embodiment, by using the recognition system based on the convolutional neural network, the classification accuracy and stability are further improved, so as to reduce the sorting error rate.
Optionally, the sorting mechanism comprises a preset number of channels and steering engines, the sorting mechanism is controlled to act according to the classification result to complete bolt sorting, and the method comprises the following steps,
and the steering engine rotates to an angle corresponding to the channel according to the classification result, and pushes the bolt into the corresponding channel.
The sorting mechanism can be controlled by a PLC controller.
In the above embodiment, through selecting for use steering wheel and passageway, according to the classification result, carry out different angle rotations, push the passageway with different bolts to accomplish the letter sorting, simple structure has reduced routine maintenance's work load.
The embodiment of the invention also discloses a bolt sorting system, which comprises,
the image acquisition module is used for acquiring images of the bolts to be sorted to obtain bolt images;
the classification module is used for classifying the bolts according to the bolt images to obtain a classification result;
and the sorting module controls the sorting mechanism to act according to the sorting result so as to finish bolt sorting.
In the above embodiment, through treating the sorting bolt and carry out image acquisition and classification to control the letter sorting according to classification result, accomplish the bolt and relay, realized automatic letter sorting, reduced personnel's work load, improved letter sorting efficiency, avoided artifical letter sorting mistake.
Hereinafter, the operation of the embodiment of the present invention will be briefly described.
The bolts sequentially move along the conveying track of the automatic feeding mechanism until the position to be detected touches the limit switch, and the movement is stopped. The CCD coaxial light source is started, photographing is started, then preprocessing is carried out on the image, classification is carried out through an intelligent recognition system classification algorithm, the intelligent recognition system carries out deep learning based on a convolutional neural network, the detected image is compared with the existing type in a system library, and the result with the highest coincidence degree is transmitted out; the steering wheel carries out the classification result that intelligent recognition system judged, carries out first angle, second angle, third angle, the rotation of fourth angle, installs a telescopic electro-magnet on the steering wheel, after rotatory certain angle, is fixed in the telescopic electro-magnet on the steering wheel axle and will wait to examine bolt propelling movement to different passageways to accomplish the letter sorting.
In the sorting process, the sorting is carried out according to the recognition result through the recognition based on the convolutional neural network, the manual intervention is not needed, the automation degree is high, the workload of personnel is reduced, the sorting efficiency is improved, and the manual sorting error is avoided.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A bolt sorting method is characterized by comprising the following steps:
acquiring an image of the bolt to be sorted to obtain a bolt image;
classifying the bolts according to the bolt images to obtain a classification result;
and controlling the sorting mechanism to act according to the sorting result to finish the bolt sorting.
2. The bolt sorting method according to claim 1, wherein the bolt to be sorted is subjected to image acquisition to obtain a bolt image, comprising,
and (5) carrying out image acquisition on the bolts to be sorted by using a CCD camera to obtain bolt images.
3. The method for sorting bolts according to claim 2, wherein before the step of acquiring the image of the bolt to be sorted by the CCD camera to obtain the bolt image, further comprising,
and a coaxial light source is arranged on the left side or/and the right side of the CCD camera.
4. The method for sorting bolts according to claim 3, further comprising, before said classifying bolts according to said bolt images to obtain classification results,
and preprocessing the bolt image.
5. The bolt sorting method according to claim 4, wherein the preprocessing the bolt image comprises,
and carrying out graying processing, image enhancement, image filtering and image binarization processing on the bolt image, and then carrying out edge detection.
6. The method for sorting bolts according to claim 5, wherein the graying process comprises,
and processing each pixel point in the bolt image as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)，
wherein (x, y) is the coordinates of the pixel points in the bolt image, wherein f (x, y) is the gray value of the bolt image at the pixel points of the coordinates (x, y), and R (x, y), G (x, y) and B (x, y) are the color values of the bolt image at R, G and B channels, respectively.
7. The method of sorting bolts according to claim 5, wherein said enhancing process comprises,
and processing each pixel point in the bolt image as follows:
f(x,y)*＝k·f(x,y)+b
wherein k is 1, b is 16,f (x, y) is the gray value of the bolt image at the pixel point of the coordinate (x, y) before the enhancement processing, and f (x, y)*The gray value of the bolt image at the coordinate (x, y) pixel point after the enhancement processing is carried out.
8. The method for sorting bolts according to claim 1, wherein said classifying bolts according to said bolt images to obtain classification results comprises,
carrying out deep learning on a recognition system based on a convolutional neural network in advance;
and comparing the bolt image with a preset type in the identification system by using the identification system, and taking a result with the highest contact ratio as the classification result.
9. The bolt sorting method according to claim 1, wherein the sorting mechanism comprises a preset number of channels and steering engines, the sorting mechanism is controlled to act according to the sorting result to complete the bolt sorting, and the method comprises the steps of,
and the steering engine controls the steering engine to rotate to an angle corresponding to the channel according to the classification result, and the bolt is pushed into the corresponding channel.
10. A bolt sorting system is characterized by comprising,
the image acquisition module is used for acquiring images of the bolts to be sorted to obtain bolt images;
the classification module is used for classifying the bolts according to the bolt images to obtain a classification result;
and the sorting module controls the sorting mechanism to act according to the sorting result so as to finish bolt sorting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911193014.9A CN110935651A (en) | 2019-11-28 | 2019-11-28 | Bolt sorting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911193014.9A CN110935651A (en) | 2019-11-28 | 2019-11-28 | Bolt sorting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110935651A true CN110935651A (en) | 2020-03-31 |
Family
ID=69908889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911193014.9A Pending CN110935651A (en) | 2019-11-28 | 2019-11-28 | Bolt sorting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110935651A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103658055A (en) * | 2013-11-21 | 2014-03-26 | 南通高盛机械制造有限公司 | Automatic bolt detection and sorting machine |
| KR20170090697A (en) * | 2016-01-29 | 2017-08-08 | 신안산대학교 산학협력단 | Rotary falling type bolt sorting apparatus including bolt side vision inspector |
| CN107230205A (en) * | 2017-05-27 | 2017-10-03 | 国网上海市电力公司 | A kind of transmission line of electricity bolt detection method based on convolutional neural networks |
| CN107824479A (en) * | 2017-11-27 | 2018-03-23 | 海盐县奕涵标准件厂 | A kind of bolt sorting unit |
| CN207385969U (en) * | 2017-10-12 | 2018-05-22 | 宁波时代紧固件制造有限公司 | A kind of bolt detection device |
| CN207563288U (en) * | 2017-11-24 | 2018-07-03 | 山东高强紧固件有限公司 | A kind of bolt detection device |
| CN108269249A (en) * | 2017-12-11 | 2018-07-10 | 深圳市智能机器人研究院 | A kind of bolt detecting system and its implementation |
| KR101918192B1 (en) * | 2018-05-31 | 2018-11-13 | 양태용 | Apparatus for simultaneously detecting fault of various kinds of bolts |
| CN109433631A (en) * | 2018-09-06 | 2019-03-08 | 国营芜湖机械厂 | The integrated device that more sized bolt degree of injury detect and classify automatically |
-
2019
- 2019-11-28 CN CN201911193014.9A patent/CN110935651A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103658055A (en) * | 2013-11-21 | 2014-03-26 | 南通高盛机械制造有限公司 | Automatic bolt detection and sorting machine |
| KR20170090697A (en) * | 2016-01-29 | 2017-08-08 | 신안산대학교 산학협력단 | Rotary falling type bolt sorting apparatus including bolt side vision inspector |
| CN107230205A (en) * | 2017-05-27 | 2017-10-03 | 国网上海市电力公司 | A kind of transmission line of electricity bolt detection method based on convolutional neural networks |
| CN207385969U (en) * | 2017-10-12 | 2018-05-22 | 宁波时代紧固件制造有限公司 | A kind of bolt detection device |
| CN207563288U (en) * | 2017-11-24 | 2018-07-03 | 山东高强紧固件有限公司 | A kind of bolt detection device |
| CN107824479A (en) * | 2017-11-27 | 2018-03-23 | 海盐县奕涵标准件厂 | A kind of bolt sorting unit |
| CN108269249A (en) * | 2017-12-11 | 2018-07-10 | 深圳市智能机器人研究院 | A kind of bolt detecting system and its implementation |
| KR101918192B1 (en) * | 2018-05-31 | 2018-11-13 | 양태용 | Apparatus for simultaneously detecting fault of various kinds of bolts |
| CN109433631A (en) * | 2018-09-06 | 2019-03-08 | 国营芜湖机械厂 | The integrated device that more sized bolt degree of injury detect and classify automatically |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3740897B1 (en) | License plate reader using optical character recognition on plural detected regions | |
| CN109365318B (en) | Multi-robot cooperation sorting method and system | |
| EP2417561B1 (en) | Two-dimensional code and method | |
| CN111266304A (en) | Coal briquette identification, detection and sorting system | |
| CN104992449A (en) | Information identification and surface defect on-line detection method based on machine visual sense | |
| CN208574964U (en) | A kind of automatic identification and sorting cigarette case device based on machine vision | |
| CN113822840A (en) | Vehicle bottom inspection system and method | |
| US20240005148A1 (en) | System and method for finding and classifying patterns in an image with a vision system | |
| CN109693140A (en) | A kind of intelligent flexible production line and its working method | |
| CN113146172A (en) | Multi-vision-based detection and assembly system and method | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN111179233A (en) | Self-adaptive deviation rectifying method based on laser cutting of two-dimensional parts | |
| CN112070117A (en) | Belt tearing detection method and device and storage medium | |
| Jia et al. | A novel algorithm for character segmentation of degraded license plate based on prior knowledge | |
| CN116337887A (en) | Method and system for detecting defects on upper surface of casting cylinder body | |
| CN113487538B (en) | Multi-target segmentation defect detection method and device and computer storage medium thereof | |
| DE212022000040U1 (en) | Logistics management system based on a two-dimensional code | |
| CN114438548A (en) | Additive abnormity monitoring method and system in electrolytic production | |
| CN110935651A (en) | Bolt sorting method and system | |
| CN114029941A (en) | Robot grabbing method and device, electronic equipment and computer medium | |
| CN107516309B (en) | Visual inspection method for defects of printing panel | |
| CN109993763B (en) | Detector positioning method and system based on image recognition and force feedback fusion | |
| CN116109633A (en) | Window detection method and device for bearing retainer | |
| CN113658135B (en) | Fuzzy PID-based self-adaptive dimming belt foreign matter detection method and system | |
| CN113808206B (en) | Typesetting system and method based on vision tracking 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: 20200331 |
|
| RJ01 | Rejection of invention patent application after publication |