CN117049078A - Conveying belt tearing detection system and detection method based on AI intelligent analysis - Google Patents
Conveying belt tearing detection system and detection method based on AI intelligent analysis Download PDFInfo
- Publication number
- CN117049078A CN117049078A CN202311274623.3A CN202311274623A CN117049078A CN 117049078 A CN117049078 A CN 117049078A CN 202311274623 A CN202311274623 A CN 202311274623A CN 117049078 A CN117049078 A CN 117049078A
- Authority
- CN
- China
- Prior art keywords
- module
- belt
- image
- unit
- motor
- 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.)
- Withdrawn
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 78
- 238000004458 analytical method Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 37
- 230000008569 process Effects 0.000 claims abstract description 32
- 230000007246 mechanism Effects 0.000 claims abstract description 22
- 238000013135 deep learning Methods 0.000 claims abstract description 20
- 230000005540 biological transmission Effects 0.000 claims description 50
- 238000004364 calculation method Methods 0.000 claims description 31
- 238000000605 extraction Methods 0.000 claims description 25
- 238000003860 storage Methods 0.000 claims description 12
- 230000033001 locomotion Effects 0.000 claims description 11
- 238000003708 edge detection Methods 0.000 claims description 8
- 230000001105 regulatory effect Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 11
- 230000009471 action Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 208000025865 Ulcer Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- -1 metallurgy Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 231100000397 ulcer Toxicity 0.000 description 1
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
- B65G23/00—Driving gear for endless conveyors; Belt- or chain-tensioning arrangements
- B65G23/24—Gearing between driving motor and belt- or chain-engaging elements
-
- 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
-
- 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
-
- 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
Abstract
A conveyor belt tearing detection system and detection method based on AI intelligent analysis belong to the technical field of belt detection, and are used for solving the problems that manual detection is complicated when a belt runs in high altitude, and a contact detection means has a certain detection error; according to the invention, the moving camera moves along the belt running direction on the moving truss through the driving mechanism in the process of belt running, the surface of the belt is shot in the moving process, the shot picture information is compared and analyzed through the AI deep learning machine and the image comparison and analysis module, whether the phenomena of cracks, fester and the like exist or not is judged, and alarming and live picture uploading are carried out, so that the detection in the moving process is realized, the detection efficiency is high, and the detection error is small.
Description
Technical Field
The invention relates to the technical field of belt detection, in particular to a conveying belt tearing detection system and method based on AI intelligent analysis.
Background
The belt conveyor is an important industrial continuous conveying device, is widely applied to the production of industries such as cement, metallurgy, chemical industry, steel and the like, and the belt deviation and tearing of the belt conveyor are belt transportation repair and replacement, so that the normal production of enterprises is greatly influenced, and even casualties can be caused.
At present, the common belt conveyor on the market relies on manual work and contact check out test set to detect the crackle and the ulcer on its surface, and the manual detection is comparatively loaded down with trivial details when partial belt is high-altitude operation, and the means of contact check out has certain detection error to the belt takes place the off tracking easily at the in-process of carrying, finally leads to the belt to drop goods and tumbles, finally leads to danger, and in addition the belt is easy to skid with the driving roller when carrying the heavy object, leads to the belt to cause wearing and tearing.
To solve the above problems. Therefore, a conveyor belt tearing detection system and a detection method based on AI intelligent analysis are provided.
Disclosure of Invention
The invention aims to provide a conveying belt tearing detection system and a detection method based on AI intelligent analysis, which solve the problems that in the background art, manual detection is complicated when a belt runs in high altitude, a contact detection means has a certain detection error, the belt is easy to deviate in the conveying process, finally, falling goods of the belt are overturned, danger is finally caused, and in addition, the belt is easy to slip between the belt and a driving roller when a heavy object is conveyed, so that the belt is worn.
In order to achieve the above purpose, the present invention provides the following technical solutions: the conveying belt tearing detection system based on AI intelligent analysis comprises a tearing detection system, an edge detection system, a stall detection system and a belt transmission device, wherein the tearing detection system comprises an AI learning unit, an AI processing unit and an alarm unit, the AI learning unit comprises an importing module and an AI deep learning machine, the importing module is used for importing an external picture, the AI deep learning machine is used for carrying out deep learning on the imported picture, giving labels such as fester and rupture to the imported picture, and extracting characteristics in the picture;
the belt transmission device comprises a transmission main body and a movement mechanism, wherein the transmission main body comprises a supporting frame, a transmission belt is arranged between the supporting frames, a driving motor is arranged below the supporting frame and connected with a transmission roller on the inner side of the transmission belt, the movement mechanism comprises a fixed plate arranged above the supporting frame, a speed sensor is arranged below the fixed plate, a speed regulating motor and a bracket are fixedly connected above the fixed plate, a driving disc and a transmission disc are rotatably connected on the bracket, the output end of the speed regulating motor extends into the bracket and is fixedly connected with the driving disc, a transmission belt is arranged on the driving disc and the transmission disc, a fixed block is fixedly connected on the outer wall of the transmission belt, a rotating rod is rotatably connected in the middle of the fixed block, a sliding rod is slidably connected on the rotating rod, a sliding block is fixedly connected on the sliding rod, and the sliding block is slidably connected at the top of the fixed plate;
the AI processing unit comprises an image acquisition module, wherein the image acquisition module is electrically connected with a moving camera, the moving camera is fixedly connected to the bottom of the sliding rod, the moving camera is used for shooting a conveying belt in moving, the image acquisition module is used for extracting photos shot by the moving camera, the AI processing unit further comprises an image and processing module and an image comparison and analysis module, the image and processing module is used for preprocessing the photos extracted by the image acquisition module and extracting the characteristics of the images, and the image comparison and analysis module is used for comparing and analyzing the processed photos with the photos imported by the importing module and analyzing the characteristics and the export results of the images.
Further, the alarm unit comprises an alarm grading module, an alarm module and an image uploading module, wherein the alarm grading module is used for grading the damage degree of the conveying belt, the alarm is not given when the damage degree is too low, the alarm is given through the alarm module after the damage degree is too high, and the image uploading module is used for uploading pictures of the damage position of the conveying belt.
Further, the edge detection system comprises an information extraction unit and an image operation unit, the information extraction unit comprises a video storage module and a picture information interception module, the belt transmission device further comprises an angle adjusting mechanism, the angle adjusting mechanism comprises a circular ring fixedly connected to a supporting frame, a fixing frame is fixedly connected between the supporting frames, a toothed ring is fixedly connected to the fixing frame, a sliding groove is formed in the inner side of the circular ring, a sliding block is slidably connected to the sliding groove, a speed reducing motor is fixedly connected to the bottom of the sliding block, an output end of the speed reducing motor is fixedly connected with a gear meshed with the toothed ring, an edge camera is mounted below the speed reducing motor, and the edge camera is electrically connected with the video storage module.
Further, the video of the operation process of the conveyor belt is shot through the edge camera, the shot video is stored through the video storage module, the picture information intercepting module is used for intercepting pictures in the shot video, and the time interval of intercepting the pictures by the picture information intercepting module is 15min each time.
Further, the image operation unit comprises a multi-image loading module, an image comparison module and a result display module, wherein the multi-image loading module is used for carrying out preloading processing on a plurality of groups of pictures intercepted by the picture information intercepting module.
Further, the image comparison module is used for comparing the processed pictures, comparing the latest extracted picture with the initial picture each time, finding out the offset angle of the conveyor belt, and displaying results through the result display module after the offset angle is overlarge.
Further, the stall detection system comprises a rotating speed calculation unit, a stall calculation unit and a feedback unit, wherein the rotating speed calculation unit comprises a motor rotating speed extraction unit and a belt rotating speed calculation module, a motor controller is arranged on the driving motor and is electrically connected with the motor rotating speed extraction unit through the motor controller, the motor rotating speed extraction unit is used for obtaining the rotating speed of the motor, and the belt rotating speed calculation module is used for calculating the theoretical rotating speed of the conveying belt.
Further, the stall calculating unit comprises a belt actual rotating speed detecting module and a data difference calculating module, the belt actual rotating speed detecting module is electrically connected with a signal receiver, a first signal transmitter and a second signal transmitter, the signal receiver is arranged on one side of the conveyor belt, and the first signal transmitter and the second signal transmitter are arranged above the supporting frame.
Further, pulse signals are continuously sent through the first signal emitter and the second signal emitter, after the signal receiver receives signals between the first signal emitter and the second signal emitter, time between the two signals and fixed distance between the first signal emitter and the second signal emitter are calculated, actual rotating speed of the conveying belt can be calculated through the belt actual rotating speed detection module, the difference value between the belt rotating speed calculation module and the belt actual rotating speed detection module can be calculated through the data difference calculation module, stall of the conveying belt can be finally obtained, and finally result feedback is carried out through the feedback unit.
The invention provides another technical scheme that: the detection method of the conveyor belt tearing detection system based on AI intelligent analysis comprises the following steps:
s1: in the process of belt operation, a driving mechanism is used for enabling a moving camera to move along the belt operation direction on a moving truss, the surface of the belt is shot in the moving process, the shot picture information is compared and analyzed through an AI deep learning machine and an image comparison and analysis module, whether the phenomena of cracks, fester and the like exist or not is judged, and an alarm and live picture uploading are carried out;
s2: carrying out real-time video recording on the belt through an edge camera, acquiring a first comparison chart through a picture information intercepting module in the early recording stage, extracting pictures every fifteen minutes in the recording process, carrying out image comparison with the first comparison chart, and finally deriving a comparison offset result;
s3: in the process of belt operation, the motor speed extraction unit is matched with the motor controller to obtain the actual speed of the motor, the theoretical speed of the conveying belt is calculated according to the sizes of the motor and the conveying belt, signals are sent through the first signal transmitter and the second signal transmitter, and the signal receiver is used for receiving the signals;
s4: the time between the two received signals is calculated, the time length of the conveying belt used between the first signal emitter and the second signal emitter can be calculated, the actual transmission speed is calculated finally, the stall of the conveying belt is calculated through the data difference calculation module, and finally feedback is carried out.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the conveying belt tearing detection system and the conveying belt tearing detection method based on the AI intelligent analysis, the ulcerated, fluffed and broken conveying belt pictures are imported through the importing module, then the imported pictures are subjected to feature extraction analysis and deep learning through the AI deep learning module, the moving camera moves along with the transmission of the conveying belt, the conveying belt is shot in the moving process, the image acquisition module acquires the shot pictures and then performs image preprocessing through the image preprocessing module, the image comparison analysis module is used for finally comparing the shot pictures with the AI deep learning module, the picture features are determined, the types and the grades of the damaged conveying belt are judged, then the alarm classification module is used for carrying out alarm classification, the alarm module is used for giving an alarm with small damage degree, the image uploading module is used for uploading the picture live condition, the detection in the moving process is realized, the detection efficiency is high, and the detection error is small.
2. According to the conveyor belt tearing detection system and the conveyor belt tearing detection method based on the AI intelligent analysis, the position and the angle of the edge camera are adjusted, the edge camera shoots a video in the running process of the conveyor belt, the shot video is stored through the video storage module, then the picture information intercepting module is used for intercepting pictures in the shot video, the time interval of intercepting the pictures by the picture information intercepting module is 15min each time, then the image comparison module compares the processed pictures, the latest extracted pictures are compared with the initial pictures each time, the offset angle of the conveyor belt is found, the result is displayed through the result display module after the offset angle is overlarge, the probability of deviation of the conveyor belt in the conveying process is reduced, dangers caused by falling goods of the conveyor belt are prevented, and the safety is improved.
3. According to the conveyor belt tearing detection system and the conveyor belt tearing detection method based on AI intelligent analysis, the actual rotating speed of the motor is obtained through the motor rotating speed extraction unit matched with the motor controller in the process of belt operation, the theoretical rotating speed of the conveyor belt is calculated according to the sizes of the motor and the conveyor belt, signals are sent through the first signal emitter and the second signal emitter, the signal receiver is used for receiving the signals, pulse signals are continuously sent through the first signal emitter and the second signal emitter, when the signal receiver receives the signals between the first signal emitter and the second signal emitter, the time between the signals is calculated, the fixed distance between the first signal emitter and the second signal emitter is calculated, the actual rotating speed of the conveyor belt can be calculated through the belt actual rotating speed detection module, the difference value between the belt rotating speed calculation module and the belt actual rotating speed detection module can be calculated, the stall of the conveyor belt can be finally obtained, and finally, the result feedback is carried out through the feedback unit.
Drawings
FIG. 1 is a schematic diagram of a detection system module according to the present invention;
FIG. 2 is a schematic diagram of a belt drive of the present invention;
FIG. 3 is a schematic diagram of a tear detection system module according to the present invention;
FIG. 4 is a schematic diagram of the AI learning unit, AI processing unit and alarm unit module of the invention;
FIG. 5 is a schematic view of the structure of the transmission body of the present invention;
FIG. 6 is a schematic diagram of a movement mechanism according to the present invention;
FIG. 7 is a structural exploded view of the movement mechanism of the present invention;
FIG. 8 is a schematic view of a portion of a turning lever according to the present invention
FIG. 9 is a schematic diagram of an edge detection system module according to the present invention;
FIG. 10 is a schematic diagram of an information extraction unit and an image computation unit according to the present invention;
FIG. 11 is a schematic view of an angle adjusting mechanism according to the present invention
FIG. 12 is a schematic diagram of a stall detection system module of the present invention;
FIG. 13 is a schematic diagram of a rotational speed calculation unit and a stall calculation unit module of the present invention;
FIG. 14 is a schematic diagram of a belt actual speed detection module according to the present invention;
FIG. 15 is a schematic view of a motion camera and edge detection camera mounting structure of the present invention;
FIG. 16 is a step diagram of the overall inspection method of the present invention.
In the figure: 1. a tear detection system; 11. an AI learning unit; 111. an import module; 112. an AI deep learning machine; 12. an AI processing unit; 121. an image acquisition module; 1211. a motion camera; 122. an image and processing module; 123. an image comparison and analysis module; 13. an alarm unit; 131. an alarm classification module; 132. an alarm module; 133. an image uploading module; 2. an edge detection system; 21. an information extraction unit; 211. a video storage module; 2111. an edge camera; 212. a picture information intercepting module; 22. an image operation unit; 221. a multiple image loading module; 222. an image comparison module; 223. a result display module; 3. a stall detection system; 31. a rotation speed calculation unit; 311. a motor rotation speed extraction unit; 312. a belt rotation speed calculation module; 32. a stall calculation unit; 321. the actual rotation speed detection module of the belt; 3211. a signal receiver; 3212. a first signal transmitter; 3213. a second signal transmitter; 322. a data difference calculation module; 33. a feedback unit; 4. a belt drive; 41. a transmission main body; 411. a support frame; 412. a conveyor belt; 413. a driving motor; 42. a movement mechanism; 421. a fixing plate; 422. a speed sensor; 423. a speed regulating motor; 424. a bracket; 4241. a driving disk; 4242. a drive plate; 4243. a transmission belt; 4244. a fixed block; 425. a rotating lever; 426. a slide bar; 427. a slide block; 43. an angle adjusting mechanism; 431. a circular ring; 432. a chute; 433. a sliding block; 434. a speed reducing motor; 435. a gear; 436. a fixing frame; 437. a toothed ring.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the technical problems that the manual detection is complicated when the belt runs in the high air, and the means of contact detection has a certain detection error, as shown in fig. 1-8, the following preferable technical scheme is provided:
the conveyor belt tearing detection system based on AI intelligent analysis comprises a tearing detection system 1, an edge detection system 2, a stall detection system 3 and a belt transmission device 4, wherein the tearing detection system 1 comprises an AI learning unit 11, an AI processing unit 12 and an alarm unit 13, the AI learning unit 11 comprises an importing module 111 and an AI deep learning machine 112, the importing module 111 is used for importing an external picture, the AI deep learning machine 112 is used for carrying out deep learning on the imported picture, giving labels such as fester and rupture to the imported picture, and extracting characteristics in the picture;
the belt transmission device 4 comprises a transmission main body 41 and a movement mechanism 42, the transmission main body 41 comprises a supporting frame 411, a transmission belt 412 is arranged between the supporting frames 411, a driving motor 413 is arranged below the supporting frames 411, the driving motor 413 is connected with a transmission roller on the inner side of the transmission belt 412, the movement mechanism 42 comprises a fixed plate 421 arranged above the supporting frames 411, a speed sensor 422 is arranged below the fixed plate 421, a speed regulating motor 423 and a bracket 424 are fixedly connected above the fixed plate 421, a driving disk 4241 and a transmission disk 4242 are rotatably connected on the bracket 424, the output end of the speed regulating motor 423 extends into the bracket 424 and is fixedly connected with the driving disk 4241, a transmission belt 4243 is arranged on the driving disk 4241 and the transmission disk 4242, a fixed block 4244 is fixedly connected on the outer wall of the transmission belt 4243, a rotating rod 425 is connected in the middle of the fixed block 4244, a sliding rod 426 is connected on the sliding rod 425, a sliding block 427 is fixedly connected with the sliding rod 427, the sliding rod 427 is connected to the top of the fixed plate 421, the speed sensor 422 detects the speed of the transmission belt 412 through the speed sensor 422, and then the speed of the motor of the transmission belt 412 is controlled to enable the speed regulating motor to rotate, so that the transmission belt 4241 and the transmission belt 4243 can rotate along with the transmission belt 4243 in a reciprocating mode, and the transmission belt 4243 can rotate along with the transmission belt 4243 in a reciprocating mode.
The AI processing unit 12 includes an image acquisition module 121, the image acquisition module 121 is electrically connected with a moving camera 1211, the moving camera 1211 is fixedly connected to the bottom of the sliding rod 426, the moving camera 1211 is used for shooting a conveying belt in moving, the image acquisition module 121 is used for extracting a photo shot by the moving camera 1211, a moving truss is installed on an outer frame of the conveying belt, the moving camera 1211 is movably arranged below the moving truss and can drive the moving camera 1211 to move on the moving truss through a driving mechanism, the AI processing unit 12 further includes an image and processing module 122 and an image comparison and analysis module 123, the image and processing module 122 is used for preprocessing the photo extracted by the image acquisition module 121 and extracting characteristics thereof, and the image comparison and analysis module 123 is used for comparing the processed photo with the photo imported by the importing module 111 and analyzing characteristics and exporting results thereof.
The alarm unit 13 includes alarm classifying module 131, alarm module 132 and image uploading module 133, and alarm classifying module 131 is used for classifying the degree of conveyor belt damage, does not give an alarm when the degree of damage is too low, reports to the police through alarm module 132 after the degree of damage is too high, and image uploading module 133 is used for uploading conveyor belt damage department picture.
Specifically, the ulcerated, fluffed and broken conveying belt pictures are imported through the importing module 111, then the imported pictures are subjected to feature extraction analysis through the AI deep learning machine 112 and are subjected to deep learning, the moving camera 1211 moves along with the transmission of the conveying belt, the conveying belt is shot in the moving process, the image acquisition module 121 acquires the shot pictures and then performs image preprocessing through the image and processing module 122, finally the shot pictures are matched with the AI deep learning machine 112 through the image comparison analysis module 123 to carry out comparison analysis, the picture features are determined, the types and grades of the damaged conveying belt are judged, then the alarm classification module 131 is used for carrying out alarm classification, the damage degree is small, the alarm module 132 is used for carrying out alarm, the image uploading module 133 is used for uploading the pictures live, the detection in the moving process is realized, the detection efficiency is high, and the detection error is small.
In order to solve the technical problems that the belt is easy to deviate in the conveying process, the falling of the belt and the tipping of goods are finally caused, and the danger is finally caused, as shown in fig. 9-11, the following preferable technical scheme is provided:
the edge detection system 2 comprises an information extraction unit 21 and an image operation unit 22, the information extraction unit 21 comprises a video storage module 211 and a picture information interception module 212, the belt transmission device 4 further comprises an angle adjusting mechanism 43, the angle adjusting mechanism 43 comprises a circular ring 431 fixedly connected to a supporting frame 411, a fixing frame 436 is fixedly connected between the supporting frames 411, a toothed ring 437 is fixedly connected to the fixing frame 436, a sliding groove 432 is formed in the inner side of the circular ring 431, a sliding block 433 is slidably connected to the inner side of the sliding groove 432, a speed reducing motor 434 is fixedly connected to the bottom of the sliding block 433, a gear 435 meshed with the toothed ring 437 is fixedly connected to the output end of the speed reducing motor 434, an edge camera 2111 is mounted below the speed reducing motor 434, the edge camera 2111 is electrically connected with the video storage module 211, the speed reducing motor 434 drives the gear 435 to mesh with the toothed ring, the sliding block 433 moves in the sliding groove 432, finally, the angle of the edge camera 2111 facing the conveying belt 412 is changed, and the conveying belt 412 is convenient to photograph better.
The video of the operation process of the conveyor belt is shot through the edge camera 2111, the shot video is stored through the video storage module 211, the picture information intercepting module 212 is used for intercepting pictures in the shot video, and the time interval of intercepting the pictures by the picture information intercepting module 212 is 15min each time.
The image operation unit 22 includes a multi-image loading module 221, an image comparing module 222, and a result display module 223, where the multi-image loading module 221 is configured to perform preloading processing on the multiple groups of pictures intercepted by the picture information intercepting module 212.
The image comparison module 222 is configured to compare the processed image with the initial image, find an offset angle of the conveyor belt, and display a result through the result display module 223 when the offset angle is too large.
Specifically, the edge camera 2111 is used for shooting a video of the running process of the conveyor belt, the video storage module 211 is used for storing the shot video, then the picture information intercepting module 212 is used for intercepting pictures in the shot video, the time interval for intercepting the pictures by the picture information intercepting module 212 is 15min each time, then the image comparison module 222 is used for comparing and analyzing the processed pictures, the latest extracted pictures and the initial pictures each time are compared, the offset angle of the conveyor belt is found, and when the offset angle is overlarge, the result display module 223 is used for displaying the result, so that the probability of deviation of the conveyor belt in the conveying process is reduced, dangers caused by falling goods of the conveyor belt are prevented, and the safety is improved.
In order to solve the technical problem that the belt is easy to slip between the belt and the driving roller when the heavy objects are conveyed, and the belt is worn, as shown in fig. 12-16, the following preferable technical scheme is provided:
the stall detection system 3 comprises a rotation speed calculation unit 31, a stall calculation unit 32 and a feedback unit 33, wherein the rotation speed calculation unit 31 comprises a motor rotation speed extraction unit 311 and a belt rotation speed calculation module 312, a motor controller is arranged on a driving motor 413 and is electrically connected with the motor rotation speed extraction unit 311 through the motor controller, the motor rotation speed extraction unit 311 is used for obtaining the rotation speed of a motor, and the belt rotation speed calculation module 312 is used for calculating the theoretical rotation speed of a conveying belt.
The stall calculating unit 32 comprises a belt actual rotating speed detecting module 321 and a data difference calculating module 322, wherein the belt actual rotating speed detecting module 321 is electrically connected with a signal receiver 3211, a first signal transmitter 3212 and a second signal transmitter 3213, the signal receiver 3211 is arranged on one side of a conveying belt, and the first signal transmitter 3212 and the second signal transmitter 3213 are arranged above a conveying belt frame.
Pulse signals are continuously sent through the first signal emitter 3212 and the second signal emitter 3213, after the signal receiver 3211 receives signals between the first signal emitter 3212 and the second signal emitter 3213, time between the two signals is calculated, and a fixed distance between the first signal emitter 3212 and the second signal emitter 3213 can be calculated through the belt actual rotating speed detection module 321, the actual rotating speed of the conveying belt can be calculated through the data difference calculation module 322, the difference between the belt rotating speed calculation module 312 and the belt actual rotating speed detection module 321 can be finally calculated, and finally, the stall of the conveying belt can be obtained through the feedback unit 33 for result feedback.
Specifically, in the process of belt running, the motor rotation speed extracting unit 311 cooperates with the motor controller to obtain the actual rotation speed of the motor, the theoretical rotation speed of the conveying belt is calculated according to the motor and the size of the conveying belt, the first signal emitter 3212 and the second signal emitter 3213 are used for sending signals, the signal receiver 3211 is used for receiving signals, the first signal emitter 3212 and the second signal emitter 3213 are used for continuously sending pulse signals, when the signal receiver 3211 receives signals between the first signal emitter 3212 and the second signal emitter 3213, the time between the two signals is calculated, and the fixed distance between the first signal emitter 3212 and the second signal emitter 3213 is calculated, the actual rotation speed of the conveying belt can be calculated through the belt actual rotation speed detecting module 321, the difference between the belt rotation speed calculating module 312 and the belt actual rotation speed detecting module 321 can be calculated through the data difference calculating module 322, and finally the stall of the conveying belt can be obtained through the feedback unit 33.
In order to further better explain the above examples, the present invention also provides an embodiment of a detection method of a conveyor belt tear detection system based on AI intelligent analysis, which includes the following steps:
step one: the moving camera 1211 is enabled to move along the belt running direction on the moving truss through the driving mechanism in the process of the belt running, the surface of the belt is shot in the moving process, the shot picture information is compared and analyzed through the AI deep learning machine 112 and the image comparison and analysis module 123, whether the phenomena of cracks, fester and the like exist or not is judged, and an alarm and live picture uploading are carried out;
step two: real-time video recording is carried out on the belt through the edge camera 2111, a first comparison chart is obtained through the picture information intercepting module 212 in the early recording stage, picture extraction is carried out once every fifteen minutes in the recording process, image comparison is carried out on the first comparison chart, and a comparison offset result is finally derived;
step three: in the process of belt running, the motor rotating speed extracting unit 311 is matched with the motor controller to obtain the actual rotating speed of the motor, the theoretical rotating speed of the conveying belt is calculated according to the sizes of the motor and the conveying belt, signals are sent through the first signal transmitter 3212 and the second signal transmitter 3213, and the signal receiver 3211 is used for receiving the signals;
step four: the time between the two received signals is calculated, so that the time length of the conveying belt used between the first signal emitter 3212 and the second signal emitter 3213 can be calculated, the actual transmission speed is calculated finally, the stall of the conveying belt is calculated through the data difference calculation module 322, and finally feedback is carried out.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should be covered by the protection scope of the present invention by making equivalents and modifications to the technical solution and the inventive concept thereof.
Claims (9)
1. Conveying belt tears detecting system based on AI intelligent analysis, including tearing detecting system (1), edge detecting system (2), stall detecting system (3) and belt drive (4), its characterized in that: the tearing detection system (1) comprises an AI learning unit (11), an AI processing unit (12) and an alarm unit (13), wherein the AI learning unit (11) comprises an importing module (111) and an AI deep learning machine (112), the importing module (111) is used for importing an external picture, the AI deep learning machine (112) is used for carrying out deep learning on the imported picture, giving tags such as fester and rupture to the imported picture, and extracting characteristics in the picture;
the belt transmission device (4) comprises a transmission main body (41) and a movement mechanism (42), the transmission main body (41) comprises a supporting frame (411), a transmission belt (412) is arranged between the supporting frames (411), a driving motor (413) is arranged below the supporting frames (411), the driving motor (413) is connected with a transmission roller on the inner side of the transmission belt (412), the movement mechanism (42) comprises a fixed plate (421) arranged above the supporting frames (411), a speed sensor (422) is arranged below the fixed plate (421), a speed regulating motor (423) and a bracket (424) are fixedly connected above the fixed plate (421), a driving disk (4241) and a transmission disk (4242) are rotatably connected on the bracket (424), the output end of the speed regulating motor (423) extends into the bracket (424) and is fixedly connected with the driving disk (4241), a transmission belt (4243) is arranged on the driving disk (4241) and the transmission disk (4242), a fixed block (4244) is fixedly connected on the outer wall of the transmission belt (4243), a middle rotary connecting rod (425) is rotatably connected with a sliding rod (426), a sliding rod (426) is fixedly connected with the sliding rod (425), and the sliding block (427) is connected to the top of the fixed plate (421) in a sliding way;
the AI processing unit (12) comprises an image acquisition module (121), wherein the image acquisition module (121) is electrically connected with a moving camera (1211), the moving camera (1211) is fixedly connected to the bottom of the sliding rod (426), the moving camera (1211) is used for shooting a conveying belt in moving, the image acquisition module (121) is used for extracting pictures shot by the moving camera (1211), the AI processing unit (12) further comprises an image and processing module (122) and an image comparison analysis module (123), the image and processing module (122) is used for preprocessing the pictures extracted by the image acquisition module (121) and extracting characteristics thereof, and the image comparison analysis module (123) is used for comparing the processed pictures with the pictures imported by the importing module (111) and analyzing characteristics and export results thereof; the edge detection system (2) comprises an information extraction unit (21) and an image operation unit (22), the information extraction unit (21) comprises a video storage module (211) and a picture information interception module (212), the belt transmission device (4) further comprises an angle adjustment mechanism (43), the angle adjustment mechanism (43) comprises a circular ring (431) fixedly connected to a supporting frame (411), a fixing frame (436) is fixedly connected between the supporting frames (411), a toothed ring (437) is fixedly connected to the fixing frame (436), a sliding groove (432) is formed in the inner side of the circular ring (431), a sliding block (433) is connected to the inner side of the sliding groove (432) in a sliding mode, a gear (435) meshed with the toothed ring (437) is fixedly connected to the bottom of the sliding block (433), an edge camera (2111) is mounted below the gear (434), and the edge camera (2111) is electrically connected with the video storage module (211).
2. The AI-intelligent analysis-based conveyor belt tear detection system of claim 1, wherein: the alarm unit (13) comprises an alarm grading module (131), an alarm module (132) and an image uploading module (133), wherein the alarm grading module (131) is used for grading the damage degree of the conveying belt, the alarm is not given when the damage degree is too low, the alarm is given through the alarm module (132) after the damage degree is too high, and the image uploading module (133) is used for uploading pictures of damaged positions of the conveying belt.
3. The AI-intelligent analysis-based conveyor belt tear detection system of claim 2, wherein: the video of the operation process of the conveyor belt is shot through an edge camera (2111), the shot video is stored through a video storage module (211), a picture information intercepting module (212) is used for intercepting pictures in the shot video, and the time interval of intercepting the pictures by the picture information intercepting module (212) is 15min each time.
4. The AI-intelligent analysis-based conveyor belt tear detection system of claim 6, wherein: the image operation unit (22) comprises a multi-image loading module (221), an image comparison module (222) and a result display module (223), wherein the multi-image loading module (221) is used for carrying out preloading processing on a plurality of groups of pictures intercepted by the picture information intercepting module (212).
5. The AI-intelligent analysis-based conveyor belt tear detection system of claim 4, wherein: the image comparison module (222) is used for comparing and analyzing the processed pictures, comparing the latest picture extracted each time with the initial picture, finding out the offset angle of the conveyor belt, and displaying results through the result display module (223) after the offset angle is overlarge.
6. The AI-intelligent analysis-based conveyor belt tear detection system of claim 5, wherein: stall detecting system (3) are including rotational speed calculation unit (31), stall calculation unit (32) and feedback unit (33), and rotational speed calculation unit (31) are including motor rotational speed extraction unit (311) and belt rotational speed calculation module (312), install motor controller on driving motor (413), through motor controller and motor rotational speed extraction unit (311) electric connection, and motor rotational speed extraction unit (311) are used for obtaining the rotational speed of motor, and belt rotational speed calculation module (312) are used for calculating the theoretical rotational speed of conveyer belt.
7. The AI-intelligent analysis-based conveyor belt tear detection system of claim 6, wherein: the stall calculating unit (32) comprises a belt actual rotating speed detecting module (321) and a data difference calculating module (322), a signal receiver (3211), a first signal transmitter (3212) and a second signal transmitter (3213) are electrically connected to the belt actual rotating speed detecting module (321), the signal receiver (3211) is installed on one side of the conveying belt (412), and the first signal transmitter (3212) and the second signal transmitter (3213) are installed above the supporting frame (411).
8. The AI-intelligent analysis-based conveyor belt tear detection system of claim 7, wherein: pulse signals are continuously sent through the first signal emitter (3212) and the second signal emitter (3213), after the signal receiver (3211) receives signals between the first signal emitter (3212) and the second signal emitter (3213), time between the signals is calculated, and a fixed distance between the first signal emitter (3212) and the second signal emitter (3213), the actual rotating speed of the conveying belt can be calculated through the belt actual rotating speed detection module (321), the difference value between the belt rotating speed calculation module (312) and the belt actual rotating speed detection module (321) can be calculated through the data difference calculation module (322), stall of the conveying belt can be finally obtained, and finally result feedback is carried out through the feedback unit (33).
9. The detection method of the conveyor belt tear detection system based on AI intelligent analysis of claim 8, comprising the steps of:
s1: in the process of belt running, a driving mechanism is used for enabling a moving camera (1211) to move along the direction of belt running on a moving truss, the surface of the belt is photographed in the process of moving, the photographed picture information is compared and analyzed through an AI deep learning machine (112) and an image comparison and analysis module (123), whether phenomena such as cracks and fester exist or not is judged, and alarming and live picture uploading are carried out;
s2: real-time video recording is carried out on the belt through an edge camera (2111), a first comparison chart is obtained through a picture information intercepting module (212) in the early recording stage, picture extraction is carried out once every fifteen minutes in the recording process, image comparison is carried out on the first comparison chart, and finally a comparison offset result is derived;
s3: in the process of belt operation, the actual rotation speed of the motor is obtained through the motor rotation speed extraction unit (311) matched with the motor controller, the theoretical rotation speed of the conveying belt is calculated according to the sizes of the motor and the conveying belt, signals are sent through the first signal transmitter (3212) and the second signal transmitter (3213), and the signal receiver (3211) is used for receiving the signals;
s4: the time between the two received signals is calculated, so that the time length of the conveying belt used between the first signal transmitter (3212) and the second signal transmitter (3213) can be calculated, the actual transmission speed is calculated finally, the stall of the conveying belt is calculated through the data difference calculation module (322), and finally feedback is carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311274623.3A CN117049078A (en) | 2023-09-28 | 2023-09-28 | Conveying belt tearing detection system and detection method based on AI intelligent analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311274623.3A CN117049078A (en) | 2023-09-28 | 2023-09-28 | Conveying belt tearing detection system and detection method based on AI intelligent analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117049078A true CN117049078A (en) | 2023-11-14 |
Family
ID=88659330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311274623.3A Withdrawn CN117049078A (en) | 2023-09-28 | 2023-09-28 | Conveying belt tearing detection system and detection method based on AI intelligent analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117049078A (en) |
-
2023
- 2023-09-28 CN CN202311274623.3A patent/CN117049078A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110902315B (en) | Belt deviation state detection method and system | |
| CN108706308B (en) | Fault identification method, device and system for conveyor | |
| EP2553661B1 (en) | A method and a system to detect and to determine geometrical, dimensional and positional features of products transported by a continuous conveyor, particularly of raw, roughly shaped, roughed or half-finished steel products | |
| CN103323457A (en) | Fruit appearance defect real-time on-line detection system and detection method | |
| CN111992512A (en) | Intelligence steel band visual detection equipment | |
| CN111185398A (en) | Online omnibearing intelligent detection system and detection method for vacuum blood collection tube | |
| CN114104653A (en) | Intelligent inspection detection method for coal belt conveyor in coal conveying bin area | |
| CN111672773A (en) | Product surface defect detection system and method based on machine vision | |
| CN104483329A (en) | Aluminum foil needle hole online detection system and detection method thereof | |
| CN111175248B (en) | Intelligent meat quality online detection method and detection system | |
| CN114252452A (en) | Online detection device and method for appearance defects and contour dimension of small-sized revolving body | |
| CN114180268A (en) | Rubber belt conveyor monitoring system and method based on machine vision | |
| CN117049078A (en) | Conveying belt tearing detection system and detection method based on AI intelligent analysis | |
| CN208771900U (en) | CCD automatic sorting device | |
| CN112950549B (en) | Goods shelf deformation detection system and detection method based on machine vision | |
| CN110082365B (en) | Robot for detecting quality of edge of steel coil based on machine vision | |
| CN112744540A (en) | Conveying belt tearing monitoring device, conveying line with tearing monitoring device and monitoring method of conveying line | |
| US20190294917A1 (en) | Debris detection system and method | |
| CN113916127A (en) | Visual inspection system and method for appearance of valve guide pipe finished product | |
| CN206847938U (en) | A kind of chain framework and Short Item detection device | |
| CN113344965A (en) | Safety management system based on image acquisition | |
| CN105973903A (en) | System and method for detecting oral solution bottle caps | |
| CN111311636A (en) | Belt speed detection method of belt conveyor based on target tracking | |
| CN112700179A (en) | Parcel tracking method, device and system and parcel detection method and device | |
| CN115494074A (en) | Online detection method for surface defects of continuous casting slab |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20231114 |
|
| WW01 | Invention patent application withdrawn after publication |