CN114261713A - Belt deviation early warning system and method based on visual perception - Google Patents
Belt deviation early warning system and method based on visual perception Download PDFInfo
- Publication number
- CN114261713A CN114261713A CN202210110541.4A CN202210110541A CN114261713A CN 114261713 A CN114261713 A CN 114261713A CN 202210110541 A CN202210110541 A CN 202210110541A CN 114261713 A CN114261713 A CN 114261713A
- Authority
- CN
- China
- Prior art keywords
- roller
- belt
- exposed area
- visual perception
- camera
- 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
- 230000016776 visual perception Effects 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 title claims description 29
- 230000003287 optical effect Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 230000001678 irradiating effect Effects 0.000 claims description 3
- 230000004438 eyesight Effects 0.000 claims description 2
- 230000008447 perception Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 10
- 238000007689 inspection Methods 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 description 6
- 239000000463 material Substances 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000006870 function Effects 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
- 238000011897 real-time detection Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a belt deviation early warning system based on visual perception, wherein cameras are fixed at two ends of a roller driving a belt to rotate, the two cameras shoot image information of exposed areas, not covered by the belt, at the two ends of the roller, the two cameras are connected with and output image information to an image module, and the image module is connected with and outputs the processed image information to an industrial control computer. The invention solves the problem of blind areas of manual point inspection, realizes 24-hour uninterrupted monitoring of all point inspection contents of the belt conveyor, forms an equipment state prediction prejudgment and fault intelligent analysis result, and guides operation and maintenance personnel to purposefully and planned develop operation and maintenance work, thereby reducing labor intensity and improving work efficiency.
Description
Technical Field
The invention relates to industrial conveyor belt deviation detection, in particular to a belt deviation early warning system and method based on visual perception.
Background
The raw fuel belt conveying system is complex and various in equipment, at present, the equipment mainly adopts an off-line monitoring mode, and equipment fault equipment is identified and diagnosed mainly through on-site manual point inspection operation and maintenance. In order to more conveniently, quickly and effectively master the operation condition of equipment, eliminate faults in a sprouting state, improve the maintenance level of the equipment and promote safe production, the remote monitoring and fault diagnosis of the equipment of a belt conveyor system are necessary to be innovated.
The belt can replace manpower to transport the material in all kinds of equipment, because its conveying bearing capacity is big, the distance is far away and advantage such as fast, has obtained extensive application in industry, agriculture scene. However, after a period of operation, the belt inevitably deviates due to uneven material stacking, deformation of the rollers and other reasons, and further causes unpredictable damage to industrial and agricultural fields. Therefore, the method has important significance in researching the real-time and accurate belt deviation early warning method.
In the prior art, chinese patent document (CN105197537A) discloses a belt off-tracking detection system and method based on color detection, however, the method of this patent that utilizes color bands to enhance the surface characteristics of the belt is not reliable, and the color bands are worn after long-time operation because the belt needs to continuously transport materials. In addition, part industrial field dust is great, leads to the typewriter ribbon colour to change colour, and then influences follow-up belt skew and detect the accuracy.
Chinese patent document (CN110902315A) discloses a method and a system for detecting belt deviation state, however, the method for extracting belt edge straight line features by using hough transform in the patent has poor real-time performance, and cannot generate belt deviation diagnosis information in time.
Disclosure of Invention
The invention solves the problem of real-time detection of the running state of the belt conveying equipment, eliminates the point inspection blind area, changes accident maintenance into state maintenance and improves the maintenance efficiency.
In order to achieve the purpose, the invention adopts the technical scheme that: the utility model provides a belt skew early warning system based on vision perception, drive belt pivoted gyro wheel both ends are fixed with the camera, two the camera shoots the exposed regional image information that the gyro wheel both ends do not cover the belt, two the camera all connects and output image information to image module, image module connects and outputs the image information after handling to industrial control computer.
The image module and the industrial control computer are internally provided with wireless communication modules, and are communicated with each other through the communication modules and transmit the processed signals to the industrial control computer.
The camera is provided with a light source irradiating the roller, and the output end of the industrial computer is connected with an alarm.
A belt deviation early warning method based on visual perception comprises the following steps:
step 1, preprocessing a video frame;
step 2, extracting an exposed area of the roller according to the set fixed size square frame;
step 3, calculating the outline area of the exposed area;
step 4, searching the outline with the largest area;
step 5, calculating the pixel width of the exposed area of the roller;
step 6, measuring the distance from the exposed area of the roller to the optical center;
step 7, calculating the actual width of the exposed area of the roller;
step 8, mutually verifying the actual widths of the exposed areas of the left and right rollers;
and 9, alarming if the actual width of the exposed area of the roller is larger than a set value.
In the step 2, the contour in the coarse positioning area is extracted by using a maximum inter-class variance method, and then the exposed area of the roller is extracted by using an optical flow method
In the step 4, sorting the area values by using a bubble sorting method, wherein the contour with the largest area value is regarded as the contour of the exposed area at the end part of the roller, and the rest contours are defined as interference filtering.
The steps areIn step 5, the minimum circumscribed rectangle of the convex set of the outline of the exposed area at the end of the roller is calculated, the width value of the rectangle is taken as the pixel width of the outline of the exposed area of the left wheel, and is set as a variable w1。
In the step 6, the actual distance s between the lens surface of the camera and the exposed area of the side roller where the camera is located and the focal length f of the camera are known during system installation, the distance between the lens surface of the camera and the optical center is consulted and added with s to generate the object distance u, and the image distance v is calculated through a Gaussian imaging formula.
In the step 7, the width w of the exposed area of the roller2＝w1*(u/v)。
The invention solves the problem of blind areas of manual point inspection, realizes 24-hour uninterrupted monitoring of all point inspection contents of the belt conveyor, forms an equipment state prediction prejudgment and fault intelligent analysis result, and guides operation and maintenance personnel to purposefully and planned develop operation and maintenance work, thereby reducing labor intensity and improving work efficiency.
Drawings
The following is a brief description of the contents of each figure in the description of the present invention:
FIG. 1 is a schematic diagram of a belt deviation warning system based on visual perception;
FIG. 2 is a flow chart of a belt deviation warning method based on visual perception.
Detailed Description
The following description of the embodiments with reference to the drawings is provided to describe the embodiments of the present invention, and the embodiments of the present invention, such as the shapes and configurations of the components, the mutual positions and connection relationships of the components, the functions and working principles of the components, the manufacturing processes and the operation and use methods, etc., will be further described in detail to help those skilled in the art to more completely, accurately and deeply understand the inventive concept and technical solutions of the present invention.
The belt deviation early warning system based on visual perception can monitor the running state of the belt on the industrial and agricultural fields in real time. When the belt shifts, alarm information can be sent out in time to remind workers to carry out maintenance work. The belt running state is guaranteed to be good, and meanwhile the deployment difficulty and the equipment cost are reduced.
The two ends of the roller of the driving belt are provided with exposed parts not covered by the belt, as shown in fig. 1, two cameras are arranged right ahead of the exposed area of the roller, the image information of the exposed area of the roller not covered by the belt is collected, the two cameras are connected with the image transmission module, the image transmission module is connected with the industrial control computer, the industrial control computer and the image transmission module are preferably provided with built-in wireless communication modules, wireless communication can be facilitated, and wiring troubles are avoided. The industrial control computer is arranged inside the central control room; the alarm is connected with industrial control and is calculated, and visual condition is installed inside the belt conveying field or the central control room, and in addition, the camera can be provided with a light source for irradiating the roller, so that the shooting definition of the camera is ensured.
The camera is used for collecting real-time images transmitted by the belt, and the number of the cameras can be increased or reduced according to field requirements. Two camera mounted position are fixed, are located the dead ahead in two exposed regions of gyro wheel respectively, and camera model and shooting mode also can be selected according to the on-the-spot demand.
The belt deviation early warning method based on visual perception comprises the following steps:
step 1, a camera collects a belt transmission video in real time, an image module preprocesses a video frame, and then the image transmission module sends the processed video to an internal storage of an industrial control computer
And 2, after the installation position of the camera is fixed, the positions of the left and right roller exposed areas in the image are also fixed, the roller exposed areas in the video frame are roughly positioned by setting a square frame with a fixed size, and the outline in the roughly positioned area is extracted by using a maximum inter-class variance method.
Step 3, calculating the area of each contour, and sequencing the area values by using a bubble sequencing method, wherein the contour with the largest area value is regarded as the contour of the exposed area at the end part of the roller, and the rest contours are regarded as interference filtering;
step 4, calculating the pixel width of the outline of the exposed area of the roller wheel, specifically, firstly calculating the minimum circumscribed rectangle of the convex set of the outline of the exposed area of the roller wheel, and regarding the width value of the rectangle as the pixel width of the outline of the exposed area of the roller wheelDegree is set as variable w1；
Step 5, calculating the pixel width of the exposed area of the roller;
step 6, measuring the distance from the exposed area of the roller to the optical center; constructor measures the actual distance of camera mirror surface and the exposed regional of gyro wheel, consults the camera mirror surface to the distance between the optical center, and both add and generate object distance u, because focus f is known, and image distance v is calculated to accessible gaussian imaging formula, and the formula is as follows:
step 7, calculating the actual width of the exposed area of the roller; the upper left corner of the image plane and the lower right corner of the object plane are on the same straight line, the lower left corner of the image plane and the upper right corner of the object plane are on the same straight line, and the four corner points form two similar triangles. The width w of the exposed area of the roller can be calculated according to the similar triangle principle2As follows:
step 8, mutually verifying the actual widths of the exposed areas of the left and right rollers; if the belt deviates rightward, the width value of the left roller exposed area is increased, and conversely, the width value of the right roller exposed area is decreased, so that the accuracy of calculating the width value of the left roller exposed area can be verified by using the decrease of the width value of the right roller exposed area, and vice versa.
Step 9, alarming if the actual width of the exposed area of the roller is larger than a set value, regarding the width of the exposed area of the left roller as the offset distance of the belt, comparing the distance value with a historical experience value, and generating alarm information and recording the current time if the distance value is larger than the historical experience value; otherwise, no alarm information is generated.
The current offset can be stored in a background database, and a new historical experience value is generated by combining the service life of the belt and the material conveying amount and is used for the next-stage alarm judgment. Compared with the prior art, the belt deviation early warning system and method based on visual perception are designed by taking visual perception and measurement as technical schemes. Compared with the method for directly detecting the belt area in the prior art, the method for detecting the exposed area of the roller is easier to implement and more reliable, namely: the more exposed areas of the rollers indicate greater belt deflection. Whether the belt deviates in the transmission process is inferred through the exposed area of the roller, and an alarm is given according to the situation.
The invention has been described above with reference to the accompanying drawings, it is obvious that the invention is not limited to the specific implementation in the above-described manner, and it is within the scope of the invention to apply the inventive concept and solution to other applications without substantial modification.
Claims (9)
1. The utility model provides a belt skew early warning system based on vision perception which characterized in that: the drive belt pivoted gyro wheel both ends are fixed with the camera, two the camera shoots the exposed regional image information that the gyro wheel both ends do not cover the belt, two the camera all connects and output image information to image module, image module connects and output image information after handling to the industrial control computer.
2. The visual perception-based belt deviation warning system of claim 1, wherein: the image module and the industrial control computer are internally provided with wireless communication modules, and are communicated with each other through the communication modules and transmit the processed signals to the industrial control computer.
3. The visual perception-based belt deviation warning system of claim 1 or 2, wherein: the camera is provided with a light source irradiating the roller, and the output end of the industrial computer is connected with an alarm.
4. A belt deviation early warning method based on visual perception is characterized by comprising the following steps:
step 1, preprocessing a video frame;
step 2, extracting an exposed area of the roller according to the set fixed size square frame;
step 3, calculating the outline area of the exposed area;
step 4, searching the outline with the largest area;
step 5, calculating the pixel width of the exposed area of the roller;
step 6, measuring the distance from the exposed area of the roller to the optical center;
step 7, calculating the actual width of the exposed area of the roller;
step 8, mutually verifying the actual widths of the exposed areas of the left and right rollers;
and 9, alarming if the actual width of the exposed area of the roller is larger than a set value.
5. The belt deviation warning method based on visual perception according to claim 4, characterized in that: in the step 2, the outline in the coarse positioning area is extracted by using a maximum inter-class variance method, and then the exposed area of the roller is extracted by using an optical flow method.
6. The belt deviation warning method based on visual perception according to claim 5, characterized in that: in the step 4, sorting the area values by using a bubble sorting method, wherein the contour with the largest area value is regarded as the contour of the exposed area at the end part of the roller, and the rest contours are defined as interference filtering.
7. The belt deviation warning method based on visual perception according to claim 4, 5 or 6, wherein: in the step 5, firstly, the minimum circumscribed rectangle of the convex set of the outline of the exposed area at the end part of the roller is calculated, the width value of the rectangle is regarded as the pixel width of the outline of the exposed area of the left wheel, and the pixel width is set as a variable w1。
8. The belt deviation warning method based on visual perception according to claim 7, characterized in that: in the step 6, the actual distance s between the lens surface of the camera and the exposed area of the side roller where the camera is located and the focal length f of the camera are known during system installation, the distance between the lens surface of the camera and the optical center is consulted and added with s to generate the object distance u, and the image distance v is calculated through a Gaussian imaging formula.
9. The belt deviation warning method based on visual perception according to claim 8, wherein: in the step 7, the width w of the exposed area of the roller2＝w1*(u/v)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210110541.4A CN114261713A (en) | 2022-01-29 | 2022-01-29 | Belt deviation early warning system and method based on visual perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210110541.4A CN114261713A (en) | 2022-01-29 | 2022-01-29 | Belt deviation early warning system and method based on visual perception |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114261713A true CN114261713A (en) | 2022-04-01 |
Family
ID=80833490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210110541.4A Pending CN114261713A (en) | 2022-01-29 | 2022-01-29 | Belt deviation early warning system and method based on visual perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114261713A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0912172A (en) * | 1995-06-29 | 1997-01-14 | Canon Inc | Endless belt deviation preventing mechanism |
| CN105627939A (en) * | 2015-12-17 | 2016-06-01 | 广东正业科技股份有限公司 | Device, method and system for detecting micro gap based on industrial equipment |
| CN107816943A (en) * | 2017-10-23 | 2018-03-20 | 广东工业大学 | A kind of box for material circulation volume weight measuring system and its implementation |
| CN108615321A (en) * | 2018-06-07 | 2018-10-02 | 湖南安隆软件有限公司 | Security pre-warning system and method based on radar detecting and video image behavioural analysis |
| CN109035293A (en) * | 2018-05-22 | 2018-12-18 | 安徽大学 | Method suitable for segmenting remarkable human body example in video image |
| CN110838142A (en) * | 2019-11-05 | 2020-02-25 | 沈阳民航东北凯亚有限公司 | Luggage size identification method and device based on depth image |
| CN111104913A (en) * | 2019-12-23 | 2020-05-05 | 福州大学 | Video PPT extraction method based on structure and similarity |
| CN112419250A (en) * | 2020-11-13 | 2021-02-26 | 湖北工业大学 | Pavement crack digital image extraction, crack repair and crack parameter calculation method |
| CN113744267A (en) * | 2021-11-04 | 2021-12-03 | 智洋创新科技股份有限公司 | Method for detecting icing and estimating thickness of transmission conductor based on deep learning |
| CN113928824A (en) * | 2021-10-25 | 2022-01-14 | 三一汽车制造有限公司 | Belt deviation detection method and device and mixing station |
-
2022
- 2022-01-29 CN CN202210110541.4A patent/CN114261713A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0912172A (en) * | 1995-06-29 | 1997-01-14 | Canon Inc | Endless belt deviation preventing mechanism |
| CN105627939A (en) * | 2015-12-17 | 2016-06-01 | 广东正业科技股份有限公司 | Device, method and system for detecting micro gap based on industrial equipment |
| CN107816943A (en) * | 2017-10-23 | 2018-03-20 | 广东工业大学 | A kind of box for material circulation volume weight measuring system and its implementation |
| CN109035293A (en) * | 2018-05-22 | 2018-12-18 | 安徽大学 | Method suitable for segmenting remarkable human body example in video image |
| CN108615321A (en) * | 2018-06-07 | 2018-10-02 | 湖南安隆软件有限公司 | Security pre-warning system and method based on radar detecting and video image behavioural analysis |
| CN110838142A (en) * | 2019-11-05 | 2020-02-25 | 沈阳民航东北凯亚有限公司 | Luggage size identification method and device based on depth image |
| CN111104913A (en) * | 2019-12-23 | 2020-05-05 | 福州大学 | Video PPT extraction method based on structure and similarity |
| CN112419250A (en) * | 2020-11-13 | 2021-02-26 | 湖北工业大学 | Pavement crack digital image extraction, crack repair and crack parameter calculation method |
| CN113928824A (en) * | 2021-10-25 | 2022-01-14 | 三一汽车制造有限公司 | Belt deviation detection method and device and mixing station |
| CN113744267A (en) * | 2021-11-04 | 2021-12-03 | 智洋创新科技股份有限公司 | Method for detecting icing and estimating thickness of transmission conductor based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109969736B (en) | Intelligent detection method for deviation fault of large carrying belt | |
| CN203124215U (en) | Frame sealant coating machine | |
| CN107052086A (en) | Stamping parts surface defect detection apparatus and detection method based on 3D vision | |
| CN104458749A (en) | Real-time aluminum profile surface defect detection system based on machine vision | |
| CN209657151U (en) | A kind of intelligent track crusing robot | |
| CN206981462U (en) | Stamping parts surface defect detection apparatus based on 3D vision | |
| CN105479786A (en) | Embryo molding part lamination detecting device and method | |
| CN203489844U (en) | System for measuring size of outer profile of vehicle based on machine vision and laser light screen | |
| CN112215825A (en) | Quality analysis method and system based on machine vision in new energy battery manufacturing | |
| CN111157537A (en) | Strip steel defect detection device and system based on bionic machine vision | |
| CN102252859A (en) | Road train straight-line running transverse stability automatic identification system | |
| CN112529880A (en) | Dam image crack detection device and method based on binocular vision | |
| CN113371028A (en) | Intelligent inspection system and method for electric bus-mounted track | |
| CN115604550A (en) | High-speed accurate fixed-distance photographing device and method | |
| CN104976959A (en) | Machine-vision-based spring size online measurement system and method thereof | |
| CN111352412A (en) | Intelligent track inspection robot | |
| CN114261713A (en) | Belt deviation early warning system and method based on visual perception | |
| CN112241949A (en) | Concrete placement mould intelligent monitoring device that fuses computer vision technique | |
| CN117197412A (en) | AR-based intelligent highway disease inspection system and method | |
| CN219455965U (en) | Visual identification mechanism for part characteristic defects | |
| CN204373688U (en) | A kind of electroplating assembly line outward appearance and dimension control equipment | |
| CN207730156U (en) | A kind of automobile tube beam measuring device | |
| CN218995107U (en) | New energy automobile battery defect visual inspection device | |
| CN214627122U (en) | Shooting mechanism on intelligent detection device | |
| CN214894918U (en) | Belted steel defect detecting device based on bionical machine vision |
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 |