CN115027906A - Pipe belt machine, pipe belt machine detection device and detection method - Google Patents
Pipe belt machine, pipe belt machine detection device and detection method Download PDFInfo
- Publication number
- CN115027906A CN115027906A CN202210789165.6A CN202210789165A CN115027906A CN 115027906 A CN115027906 A CN 115027906A CN 202210789165 A CN202210789165 A CN 202210789165A CN 115027906 A CN115027906 A CN 115027906A
- Authority
- CN
- China
- Prior art keywords
- pipe
- image
- belt
- belt machine
- machine
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 68
- 238000007689 inspection Methods 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 20
- 230000009466 transformation Effects 0.000 claims description 9
- 238000004088 simulation Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 239000000049 pigment Substances 0.000 claims description 2
- 238000011897 real-time detection Methods 0.000 abstract description 3
- 239000000463 material Substances 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/02—Control devices, e.g. for safety, warning or fault-correcting detecting dangerous physical condition of load carriers, e.g. for interrupting the drive in the event of overheating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/02—Control or detection
- B65G2203/0266—Control or detection relating to the load carrier(s)
- B65G2203/0283—Position of the load carrier
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a pipe belt machine detection device, a detection method thereof and a pipe belt machine. Adopt as above structure, patrol and examine the robot and remove in pipe tape machine each place, gather the image of conveyer belt overlap joint position everywhere through image acquisition device, through judging whether have the torque tube phenomenon in this image, can real-time detection each conveyer belt appear the torque tube problem.
Description
Technical Field
The invention relates to the technical field of pipe belt machines, in particular to a pipe belt machine, a pipe belt machine detection device and a pipe belt machine detection method.
Background
A tubular belt conveyor is called a belt conveyor for short, and is a belt conveyor which bears and returns branched conveying belts to be curled into a tubular shape. Because the conveyer belt of pipe tape unit need be convoluteed for the tubulose with transported substance material, at long distance operation in-process, can have the condition of conveyer belt both sides overlap joint position skew normal position, take place the torque tube problem promptly, and when overlap joint position deviation volume is great, alright lead to the material in the conveyer belt to spill.
Therefore, it is an urgent technical problem to be solved by those skilled in the art to provide a tube belt machine detection device and method capable of detecting whether a twisting problem occurs in a conveyor belt.
Disclosure of Invention
The invention aims to provide a pipe belt conveyor detection device and a pipe belt conveyor detection method which can detect whether a pipe twisting problem occurs on a conveying belt.
In order to solve the technical problem, the pipe belt machine detection device comprises a plurality of movable frames and a plurality of inspection robots, wherein the movable frames and the inspection robots are arranged on the outer side of a pipe belt machine main body, each inspection robot can move along the corresponding movable frame, each inspection robot is provided with an image acquisition device and a transmission device, the pipe belt machine main body comprises a conveying belt, and the image acquisition device can acquire images at the lap joint positions of the conveying belt.
Adopt as above structure, patrol and examine the robot and remove in pipe tape machine each place, gather the image of conveyer belt overlap joint position everywhere through image acquisition device, through judging whether have the torque tube phenomenon in this image, can real-time detection each conveyer belt appear the torque tube problem.
Optionally, the conveying device further comprises a processing unit, the conveying device can transmit the image acquired by the image acquisition device to the processing unit, and the processing unit can judge whether the pipe twisting phenomenon exists on the conveying belt according to the image.
Optionally, at least part of the inspection robot is provided with a light source, and the light source can at least provide illumination for the overlapping position of the conveying belt.
The invention also provides a pipe belt machine, which comprises a pipe belt machine main body and a pipe belt machine detection device, wherein the pipe belt machine detection device is the pipe belt machine detection device described above.
Optionally, the pipe belt main part includes conveyer belt and a plurality of bearing roller, the conveyer belt is used for covering in the overlap joint both sides border outside at least the border is equipped with banded instruction strip.
Optionally, the edge is painted to form the indicator strip, and the color of the indicator strip is different from other parts of the conveying belt.
The invention also provides a pipe belt machine detection method, which is based on the pipe belt machine described above and comprises the following specific steps:
s1, collecting the images of the conveying belt when the pipe belt machine works normally and the images of the conveying belt when the pipe twisting phenomenon occurs through an image collecting device of the inspection robot, and transmitting the images to a processing unit;
s2, the processing unit establishes a normal model and a torsion tube model through an algorithm based on the shape and the change of the indicator strip of the conveyor belt in the normal image and the torsion tube image to obtain a distinguishing algorithm parameter of the normal image and the torsion tube image;
and S4, starting the pipe belt machine and the inspection robots, and detecting the pipe belt machine in real time based on the distinguishing algorithm parameters in the step S2 to judge whether the pipe twisting phenomenon exists.
Optionally, before step S4, step S3 is further performed: performing simulation test on the pipe conveyor, collecting images of the conveyor belt through the inspection robot, uploading the images to the processing unit, judging whether the uploaded images are twisted pipe images or not based on the distinguishing algorithm parameters in the step S2, verifying the judgment result, and adjusting the distinguishing algorithm parameters based on the judgment result to obtain final algorithm parameters;
in step S4, the tape handler is detected in real time based on the final algorithm parameters in step S3 to determine whether there is a twisting phenomenon.
Optionally, the method further comprises the following steps:
s1.1, acquiring historical image data of the inspection robot on the pipe belt machine, and transmitting the historical image data to the processing unit;
s1.2, converting the historical image data into picture data;
and S1.3, classifying the picture data into a normal picture and a torsion tube picture through screening.
Optionally, the method further comprises the following steps:
s2.1, respectively randomly extracting normal pictures and torsion tube pictures with the number not less than a first number, and calculating a line segment length threshold value, a line segment direction variation range tolerance and a line segment width pixel parameter of the indication strip in the pictures through a Hough line transformation detection algorithm to obtain a first distinguishing algorithm parameter;
and S2.2, extracting normal pictures and torsion tube pictures with the number not less than a second number, wherein the second number is greater than the first number, and updating and iterating on the basis of the first distinguishing algorithm parameters through a Hough line transformation detection algorithm to obtain second distinguishing algorithm parameters.
Optionally, the method further comprises the following steps:
s3.1, judging and verifying the uploaded image based on a second distinguishing algorithm parameter through simulation test on the pipe belt machine, and extracting a twisted pipe image of wrong detection or missed detection of the second distinguishing algorithm parameter;
and S3.2, updating and iterating the second distinguishing algorithm parameters based on the torsion tube image subjected to error detection or missing detection through a Hough line transformation detection algorithm to obtain final algorithm parameters.
Optionally, the method further comprises the following steps:
s4.1, after the pipe belt conveyor normally runs, acquiring real-time video data of the conveying belt at each position of the pipe belt conveyor through the inspection robot, and uploading the real-time video data to the processing unit;
s4.2, converting the real-time video data into picture data;
and S4.3, detecting the picture data based on the final algorithm parameters, and judging whether the conveying belt in the real-time video data has a pipe twisting phenomenon.
Optionally, the method further comprises the following steps:
s4.2, converting the real-time video data with the interval of 0.02 second into picture data;
and S4.4, if the pipe twisting phenomenon of the conveying belt is judged, outputting corresponding real-time video data and giving a warning.
Drawings
Fig. 1 is a schematic structural diagram of a pipe belt machine according to an embodiment of the present invention;
FIG. 2 is a schematic structural view of the main body of the hose reel of FIG. 1 in normal operation;
fig. 3 is a flow chart of a pipe-in-pipe machine detection method provided by the invention.
The reference numerals in fig. 1-3 are illustrated as follows:
the pipe strap machine comprises a pipe strap machine body 1, a conveying belt 11, a 111 indicating strip, a 12 carrier roller, a moving frame 2, a 3 inspection robot and a 31 image acquisition device.
Detailed Description
In order to make the technical solutions of the present invention better understood, the present invention is further described in detail with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention provides a pipe belt machine detection device, and please refer to fig. 1-2, the pipe belt machine detection device comprises a plurality of movable frames 2 and a plurality of inspection robots 3 which are arranged on the outer side of a pipe belt machine main body 1, each inspection robot 3 can move along the corresponding movable frame 2, each inspection robot 3 is provided with an image acquisition device 31 and a transmission device, the pipe belt machine main body 1 comprises a conveying belt 11, and the image acquisition device 31 can acquire images at the lapping positions of the conveying belts 11.
Adopt as above structure, patrol and examine robot 3 and remove everywhere at the pipe tape machine, gather the image of 11 overlap joint positions of conveyer belt everywhere through image acquisition device 31, through judging whether have the torque tube phenomenon in this image, can real-time detection everywhere conveyer belt 11 appear the torque tube problem.
As shown in fig. 1 in particular, the two sides of the tubular belt machine body 1 in this embodiment are provided with the moving frames 2, the two moving frames 2 extend along the running direction of the tubular belt machine, and the inspection robots 3 are mounted below the moving frames 2 and can move along the moving frames 2.
The arrangement position of the movable frame 2 at least comprises a conveying section of the pipe belt machine, namely the position of the conveying belt 11 when the conveying belt is wound into a pipe shape, so that the image acquisition range of each inspection robot 3 can completely cover the conveying belt 11 in the winding state; the specific structure of the moving frame 2 and the way of carrying the inspection robot 3 on the moving frame 2 may be determined according to actual conditions, and the two moving ways may be a hanging rail type structure, a wheel type structure, a crawler type structure and the like, and the invention is not limited to this, for example, the moving frame 2 may be hanging rails arranged on both sides of a pipe belt conveyor, the inspection robot 3 is provided with hanging wheels corresponding to the hanging rails and a driving device, and the driving device can drive the hanging wheels to rotate so as to drive the inspection robot 3 to move along the hanging rails.
The image capturing device 31 may be a visible light camera, and the like, and the wireless transmission device may be a wireless network-based transmitting device, and the invention is not limited to this.
Further, this embodiment still includes the processing unit, and transmission device can transmit the image transmission that image acquisition device 31 gathered to the processing unit, and the processing unit can judge whether there is the torque tube phenomenon in conveyer belt 11 according to this image, so can realize real-time automated inspection torque tube problem.
At least part of the inspection robot 3 in this embodiment is provided with a light source which can provide illumination at least for the overlapping position of the conveyor belt 11. So set up the overlap joint position illumination that can prevent conveyer belt 11 not enough, lead to image acquisition device 31 can't gather corresponding image, also can provide the collection condition for detecting night.
The embodiment of the present invention further provides a pipe belt machine, which includes a pipe belt machine main body 1 and a pipe belt machine detection device, where the pipe belt machine detection device is the pipe belt machine detection device described above, and since the pipe belt machine detection device has the above technical effects, the pipe belt machine including the pipe belt machine detection device should also have the same technical effects, and therefore, the description thereof is omitted here.
The pipe belt machine main body 1 in this embodiment includes a conveying belt 11 and a plurality of carrier rollers 12, and a strip-shaped indication strip 111 is provided on at least the edge covering the outside of the two side edges of the conveying belt 11 for overlapping.
Referring to fig. 2, when the pipe belt machine is in normal operation, the conveying belt 11 is wound into a pipe shape by each carrier roller 12, and the two side edges of the conveying belt 11 are crosswise lapped on the top end of the pipe structure to prevent the materials in the pipe belt machine from spilling; the edges at least covering the outer side in the edges of the two sides of the conveying belt 11 are provided with strip-shaped indicating strips 111, the indicating strips 111 are strip-shaped parts with colors obviously different from other parts of the conveying belt 11, the strip-shaped parts extend along the edges of the two sides of the conveying belt 11, the width of the strip-shaped parts can be set to be a fixed value, the strip-shaped parts at least cover the lap joint position of the conveying belt 11, and the indicating strips 111 are formed by spraying relatively striking pigments and the like in a certain width of the edges of the two sides of the conveying belt 11.
In addition, besides being capable of being used for processing unit analysis algorithm and automatic detection of detecting the problem of the twisted tube, the indication strip 111 can also be convenient for manual inspection, and due to the fact that colors of the indication strip 111 are obviously different, when the problem of the twisted tube occurs on the conveying belt 11, the problem can be quickly found through manual inspection, and the efficiency of manual inspection is effectively improved.
The invention further provides a pipe belt machine detection method, based on the pipe belt machine described above, please refer to fig. 3, which includes the following specific steps:
s1, collecting the images of the conveyer belt 11 when the pipe belt machine normally works and the images of the conveyer belt 11 when the pipe twisting phenomenon occurs through the image collecting device 31 of the inspection robot 3, and transmitting the images to the processing unit;
s2, the processing unit establishes a normal model and a torsion tube model through an algorithm based on the shape and the change of the indicator strip 111 of the conveyor belt 11 in the normal image and the torsion tube image to obtain a distinguishing algorithm parameter of the normal image and the torsion tube image;
and S4, starting the pipe belt conveyor and the inspection robots 3, and detecting the pipe belt conveyor in real time based on the distinguishing algorithm parameters in the step S2 to judge whether the pipe twisting phenomenon exists.
By adopting the method, the images of the conveying belts 11 at all positions can be collected by the inspection robot 3 and analyzed by the processing unit to judge whether the pipe twisting problem occurs on the conveying belts 11.
It should be noted that the main purpose of the image acquisition device 31 of the inspection robot 3 to acquire the image of the conveyor belt 11 is to acquire the image of the same-angle indicator 111, because the indicator 111 has a color different from that of other parts of the conveyor belt 11, and the indicator 111 is the overlapping part of the conveyor belt 11, in the acquired image, the overlapping part of the conveyor belt 11 is a line segment with a specific color and a specific width, when the conveyor belt 11 is running normally, the line segment is a straight line, and when the conveyor belt 11 has a problem of pipe twisting, the line segment is inclined or bent, and according to the above characteristics, the processing unit can determine whether the conveyor belt 11 has the problem of pipe twisting in the image by analyzing parameters such as the length, the width, and the angle of the line segment with the specific color in a plurality of images.
In this embodiment, the processing unit analyzes the image through a hough transform straight line detection algorithm, hough transform is an existing feature extraction technology, and is used for distinguishing features, particularly lines, in an object, and is capable of counting polar coordinate parameters corresponding to each point of a target line segment, integrating a group of points with the largest number of spatial intersections into the line segment, wherein the line segment is a distinguishing algorithm parameter, continuously comparing the line segment with parameters such as line length, line width and position information of a randomly extracted acquired image, removing a false detection part to obtain a final algorithm parameter, and judging the position of the indicator 111 by using the final algorithm parameter, so as to judge whether the pipe twisting phenomenon exists on the conveyor belt 11.
Before step S4, the method further proceeds to step S3: performing simulation test on the pipe strap machine, collecting the images of the conveying belt 11 through the inspection robot 3, uploading the images to the processing unit, judging whether the uploaded images are pipe twisting images or not based on the distinguishing algorithm parameters in the step S2, verifying the judgment result, and adjusting the distinguishing algorithm parameters based on the judgment result to obtain final algorithm parameters;
in step S4, the pipe bending machine is detected in real time based on the final algorithm parameters in step S3 to determine whether pipe twisting occurs.
Compared with the algorithm parameter distinguishing method, the final algorithm parameter obtained through simulation test is higher in accuracy and robustness, and false detection can be effectively reduced.
The method may further comprise the steps of:
s1.1, acquiring historical image data of the inspection robot 3 on the hose machine, and transmitting the historical image data to a processing unit;
s1.2, converting the historical image data into picture data;
and S1.3, classifying the picture data into a normal picture and a torsion tube picture through screening.
Converting and screening the historical image data of the pipe belt conveyor to obtain an image (a normal picture) of the conveying belt 11 when the pipe belt conveyor normally works and an image (a pipe twisting picture) of the conveying belt 11 when the pipe twisting phenomenon occurs in the step S1; in this embodiment, the historical image data is converted by using an open-source computer vision library, specifically, the open-source computer vision library in this embodiment is OpenCV, and OpenCV is a cross-platform computer vision and machine learning software library, which has a fast processing speed for real-time application in the real world.
The method may further comprise the steps of:
s2.1, respectively and randomly extracting normal pictures and torsion tube pictures with the quantity not less than a first quantity, and calculating a line segment length threshold value, a line segment direction variation range tolerance and a line segment width pixel parameter of an indication strip 111 in the pictures through a Hough line transformation detection algorithm to obtain a first distinguishing algorithm parameter;
and S2.2, extracting normal pictures and torsion tube pictures with the number not less than a second number, wherein the second number is greater than the first number, and updating and iterating on the basis of the first distinguishing algorithm parameters through a Hough line transformation detection algorithm to obtain second distinguishing algorithm parameters.
Through the steps of S2.1 and S2.2, the detection accuracy of the algorithm parameters can be further improved, the false detection is reduced, and the algorithm is easier to adjust and update iteratively during simulation test; in the present embodiment, the first number is not less than 20, and the second number is not less than 50.
The method can also comprise the following steps:
s3.1, performing simulation test on the pipe-twisting machine, judging and verifying the uploaded image based on a second distinguishing algorithm parameter, and extracting a twisted pipe image with the second distinguishing algorithm parameter subjected to false detection or missed detection;
and S3.2, updating and iterating the second distinguishing algorithm parameters based on the torsion tube image subjected to error detection or missing detection through a Hough line transformation detection algorithm to obtain final algorithm parameters.
The updating and iteration of the distinguishing algorithm parameters refers to the optimization of the line segment length threshold, the line width pixel parameters and the line segment direction variation range tolerance, so that the missing detection and the error detection of the images can be correctly detected, the robustness of the algorithm is improved, and the final algorithm parameters with high detection accuracy are obtained.
The method can also comprise the following steps:
s4.1, after the pipe belt conveyor normally runs, acquiring real-time video data of the conveying belt 11 at each position of the pipe belt conveyor through the inspection robot 3, and uploading the real-time video data to the processing unit;
s4.2, converting the real-time video data into picture data;
and S4.3, detecting the picture data based on the final algorithm parameters, and judging whether the pipe twisting phenomenon exists on the conveying belt 11 in the real-time video data.
As shown in fig. 3, S4.1 to S4.3 are inspection methods of the tube band machine after the final algorithm parameters are obtained, and the tube twisting phenomenon of the conveyor belt 11 at each position of the tube band machine can be detected and warned through the inspection methods.
The method can also comprise the following steps:
s4.2, converting the real-time video data with the interval of 0.02 second into picture data;
and S4.4, if the pipe twisting phenomenon of the conveying belt 11 is judged, outputting the corresponding real-time video data and giving a warning.
After warning is sent out to pipe tape unit detection device, the staff can be through looking over the real-time video data of output in S4.4, confirms the torque tube position of conveyer belt 11 fast to in time solve the torque tube problem, effectively improve the torque tube problem and deal with efficiency.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that it is obvious to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and these modifications and improvements should also be considered as the protection scope of the present invention.
Claims (13)
1. The utility model provides a pipe tape unit detection device which characterized in that: including setting up in a plurality of moving frame (2) and a plurality of robot (3) of patrolling and examining in the pipe tape unit main part (1) outside, each it can follow the correspondence to patrol and examine robot (3) moving frame (2) remove, each it is equipped with image acquisition device (31) and transmission device to patrol and examine robot (3), pipe tape unit main part (1) includes conveyer belt (11), image acquisition device (31) can gather the image of conveyer belt (11) overlap joint position.
2. The pipe belt machine detection device of claim 1, wherein: the device further comprises a processing unit, the transmission device can transmit the image collected by the image collecting device (31) to the processing unit, and the processing unit can judge whether the conveying belt (11) has a pipe twisting phenomenon according to the image.
3. The pipe belt machine detection device according to claim 1 or 2, characterized in that: at least part patrol and examine robot (3) and be equipped with the light source, the light source can be at least for the overlap joint position of conveyer belt (11) provides the illumination.
4. A pipe belt machine is characterized in that: the pipe belt machine detection device comprises a pipe belt machine main body (1) and a pipe belt machine detection device, wherein the pipe belt machine detection device is the pipe belt machine detection device in any one of claims 1-3.
5. The pipe tape machine of claim 4, wherein: the pipe belt machine main part (1) comprises a conveying belt (11) and a plurality of carrier rollers (12), wherein the conveying belt (11) is used for covering at least the outer side of the edges of the two overlapped sides, and the edges are provided with strip-shaped indicating strips (111).
6. The pipe tape machine of claim 5, wherein: the edge is sprayed with pigment to form the indicating strip (111), and the color of the indicating strip (111) is different from other parts of the conveying belt (11).
7. A pipe belt machine detection method is based on the pipe belt machine of claim 5, and is characterized in that: the method comprises the following specific steps:
s1, acquiring images of the conveying belt (11) when the pipe belt machine normally works and images of the conveying belt (11) when a pipe twisting phenomenon occurs through an image acquisition device (31) of the inspection robot (3), and transmitting the images to a processing unit;
s2, the processing unit establishes a normal model and a torsion tube model through an algorithm based on the shape and the change of the indication strip (111) of the conveying belt (11) in the normal image and the torsion tube image to obtain a distinguishing algorithm parameter of the normal image and the torsion tube image;
and S4, starting the pipe belt machine and each inspection robot (3), and detecting the pipe belt machine in real time based on the distinguishing algorithm parameters in the step S2 to judge whether the pipe twisting phenomenon exists or not.
8. The pipe belt machine detection method according to claim 7, characterized in that: before step S4, step S3 is also performed: performing simulation test on the pipe belt conveyor, collecting the image of the conveying belt (11) through the inspection robot (3), uploading the image to the processing unit, judging whether the uploaded image is a pipe twisting image or not based on the distinguishing algorithm parameters in the step S2, verifying the judgment result, and adjusting the distinguishing algorithm parameters based on the judgment result to obtain final algorithm parameters;
in step S4, the pipe belt machine is detected in real time based on the final algorithm parameters in step S3 to determine whether a pipe twisting phenomenon exists.
9. The pipe-in-pipe machine inspection method of claim 8, wherein: also comprises the following steps:
s1.1, acquiring historical image data of the inspection robot (3) on the pipe belt machine, and transmitting the historical image data to the processing unit;
s1.2, converting the historical image data into picture data;
and S1.3, classifying the picture data into a normal picture and a torsion tube picture through screening.
10. The pipe belt machine detection method according to claim 9, characterized in that: also comprises the following steps:
s2.1, respectively randomly extracting normal pictures and torsion tube pictures which are not less than a first number, and calculating a line segment length threshold value, a line segment direction variation range tolerance and a line segment width pixel parameter of the indication strip (111) in the pictures through a Hough line transformation detection algorithm to obtain a first distinguishing algorithm parameter;
s2.2, extracting normal pictures and torsion tube pictures with the number not less than a second number, wherein the second number is larger than the first number, and updating and iterating on the basis of the first distinguishing algorithm parameters through a Hough line transformation detection algorithm to obtain second distinguishing algorithm parameters.
11. The pipe belt machine detection method according to claim 10, characterized in that: also comprises the following steps:
s3.1, judging and verifying the uploaded image based on a second distinguishing algorithm parameter through simulation test on the pipe belt machine, and extracting a twisted pipe image of wrong detection or missed detection of the second distinguishing algorithm parameter;
and S3.2, updating and iterating the second distinguishing algorithm parameters based on the torsion tube image subjected to error detection or missing detection through a Hough line transformation detection algorithm to obtain final algorithm parameters.
12. The pipe-in-pipe machine inspection method of claim 8, wherein: also comprises the following steps:
s4.1, after the pipe belt conveyor normally runs, acquiring real-time video data of the conveying belt (11) at each position of the pipe belt conveyor through the inspection robot (3), and uploading the real-time video data to the processing unit;
s4.2, converting the real-time video data into picture data;
and S4.3, detecting the picture data based on the final algorithm parameters, and judging whether the conveying belt (11) in the real-time video data has the pipe twisting phenomenon.
13. The pipe belt machine detection method according to claim 12, characterized in that: also comprises the following steps:
s4.2, converting the real-time video data with the interval of 0.02 second into picture data;
and S4.4, if the pipe twisting phenomenon of the conveying belt (11) is judged, outputting the corresponding real-time video data and giving a warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210789165.6A CN115027906B (en) | 2022-07-06 | 2022-07-06 | Pipe belt machine, pipe belt machine detection device and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210789165.6A CN115027906B (en) | 2022-07-06 | 2022-07-06 | Pipe belt machine, pipe belt machine detection device and detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115027906A true CN115027906A (en) | 2022-09-09 |
| CN115027906B CN115027906B (en) | 2024-03-08 |
Family
ID=83128492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210789165.6A Active CN115027906B (en) | 2022-07-06 | 2022-07-06 | Pipe belt machine, pipe belt machine detection device and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115027906B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111232591A (en) * | 2020-01-19 | 2020-06-05 | 山东钢铁股份有限公司 | Pipe belt monitoring device and method |
| CN112357454A (en) * | 2020-11-30 | 2021-02-12 | 华电重工股份有限公司 | Device and method for detecting overlapping position of rubber belt of tubular belt conveyor |
| CN112499164A (en) * | 2020-12-06 | 2021-03-16 | 无锡圆方软件科技有限公司 | Automatic inspection device and system for pipe belt machine |
| CN214297715U (en) * | 2020-11-28 | 2021-09-28 | 日照港机工程有限公司 | Pipe belt machine torsion detection device |
| CN215923546U (en) * | 2021-06-17 | 2022-03-01 | 福建龙净环保股份有限公司 | Patrol robot, pipe tape machine patrol device and pipe tape machine |
| CN216036925U (en) * | 2021-08-03 | 2022-03-15 | 交通运输部水运科学研究所 | Automatic detection device for running state of long-distance conveying equipment |
-
2022
- 2022-07-06 CN CN202210789165.6A patent/CN115027906B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111232591A (en) * | 2020-01-19 | 2020-06-05 | 山东钢铁股份有限公司 | Pipe belt monitoring device and method |
| CN214297715U (en) * | 2020-11-28 | 2021-09-28 | 日照港机工程有限公司 | Pipe belt machine torsion detection device |
| CN112357454A (en) * | 2020-11-30 | 2021-02-12 | 华电重工股份有限公司 | Device and method for detecting overlapping position of rubber belt of tubular belt conveyor |
| CN112499164A (en) * | 2020-12-06 | 2021-03-16 | 无锡圆方软件科技有限公司 | Automatic inspection device and system for pipe belt machine |
| CN215923546U (en) * | 2021-06-17 | 2022-03-01 | 福建龙净环保股份有限公司 | Patrol robot, pipe tape machine patrol device and pipe tape machine |
| CN216036925U (en) * | 2021-08-03 | 2022-03-15 | 交通运输部水运科学研究所 | Automatic detection device for running state of long-distance conveying equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115027906B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109941700B (en) | Intelligent unmanned inspection system of coal conveying system | |
| CN103512888B (en) | A kind of cigarette packet seal defect detecting system based on image recognition technology | |
| CN107703148A (en) | A kind of cable strand quality detecting system and its detection method based on machine vision | |
| CN114104653A (en) | Intelligent inspection detection method for coal belt conveyor in coal conveying bin area | |
| CN204679431U (en) | The detection system of tyre wire cord fabric surface imperfection | |
| EP2735433B1 (en) | Bead filler testing device, program for bead filler testing, and bead filler testing method | |
| CN105139397B (en) | PCB detection method and device | |
| CN104792796A (en) | On-line monitoring system for mining adhesive tape operation condition based on machine vision | |
| CN110954554A (en) | Online burr detecting system | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN104729426A (en) | Automatic angle iron online detecting system and method based on machine vision | |
| CN110053941A (en) | A kind of carrier roller of belt conveyer monitoring abnormal state system and method based on velocity measuring | |
| CN115171051B (en) | Online detection method and system for tearing of edge of conveying belt | |
| CN107436304A (en) | A kind of surface of concrete structure detection means | |
| CN115027906A (en) | Pipe belt machine, pipe belt machine detection device and detection method | |
| CN105738376B (en) | A kind of automatic cloth inspecting machine using contact-type image sensor | |
| CN105699386A (en) | Automatic cloth inspection marking method adopting contact image sensor | |
| CN117049066A (en) | Device and method for detecting deviation of conveying rubber belt pipe of pipe belt conveyor | |
| CN105973903B (en) | A kind of Oral liquid bottle lid detection method | |
| CN112556581B (en) | Carbon plate detection system based on machine vision and detection method thereof | |
| CN111311636A (en) | Belt speed detection method of belt conveyor based on target tracking | |
| CN113077414B (en) | Steel plate surface defect detection method and system | |
| CN115457330A (en) | Method, device and equipment for identifying broken wire state of packing wire and storage medium | |
| CN107941816A (en) | Portable appearance delection device and appearance detecting method | |
| CN205471557U (en) | Can intelligent snatch robot of work piece |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |