CN114140733A - Belt running state detection method based on video - Google Patents

Belt running state detection method based on video Download PDF

Info

Publication number
CN114140733A
CN114140733A CN202111503515.XA CN202111503515A CN114140733A CN 114140733 A CN114140733 A CN 114140733A CN 202111503515 A CN202111503515 A CN 202111503515A CN 114140733 A CN114140733 A CN 114140733A
Authority
CN
China
Prior art keywords
video
belt
submodule
module
conveying device
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111503515.XA
Other languages
Chinese (zh)
Inventor
王乔晨
王飞
何丹
孙晓峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Brexia Information Technology Beijing Co ltd
China Building Materials Xinyun Zhilian Technology Co ltd
Cnbm Technology Corp ltd
Original Assignee
Brexia Information Technology Beijing Co ltd
China Building Materials Xinyun Zhilian Technology Co ltd
Cnbm Technology Corp ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Brexia Information Technology Beijing Co ltd, China Building Materials Xinyun Zhilian Technology Co ltd, Cnbm Technology Corp ltd filed Critical Brexia Information Technology Beijing Co ltd
Priority to CN202111503515.XA priority Critical patent/CN114140733A/en
Publication of CN114140733A publication Critical patent/CN114140733A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2134—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Control Of Conveyors (AREA)

Abstract

The invention relates to the technical field of belt conveyor maintenance, in particular to a method for detecting a belt running state based on videos. The method comprises the steps of arranging a camera module, a sensor and a computer component; building a system architecture and a detection system; monitoring the belt conveying device in real time; detecting and identifying the equipment running state and the abnormal fault condition of the belt conveying device based on the video data; judging the running state, and scoring the influence degree of the abnormal condition on the running safety performance of the equipment; setting a safety protection mechanism, executing safety protection measures when abnormal conditions occur, outputting alarm signals, carrying out maintenance scheduling and the like. The design of the invention is based on monitoring video, and the running state of the belt conveying device is detected and judged in real time; evaluating the influence degree of the abnormal condition, accurately evaluating the running state of the belt conveyor, improving the detection efficiency and reducing negligence and mistake and leakage; the potential safety hazard of production can be effectively reduced, the waste is reduced, and the safe operation of production is guaranteed.

Description

Belt running state detection method based on video
Technical Field
The invention relates to the technical field of belt conveyor maintenance, in particular to a method for detecting a belt running state based on videos.
Background
The belt conveyor is one of mechanical equipment used by many enterprises for transporting materials in a continuous mode through friction drive, is widely applied to the fields of metallurgy, mineral separation, petroleum, chemical industry, light industry, building materials, steel mills, ports and the like, and is increasingly developed towards high speed, large scale and ultra-long distance. In industries such as electric power, petrifaction, cement, smelting and processing, a large number of belt conveyors are equipped for conveying bulk materials. The conveying belt is an important component of a belt conveyor, the cost of the belt conveyor accounts for a high proportion of the whole belt conveyor, but the belt tearing accident happens, once the conveying belt with high value is longitudinally torn, conveyed materials invade an equipment mechanical system to cause equipment damage, even serious accidents such as personnel injury and the like, and huge economic loss are caused; meanwhile, in the transportation process of the belt conveyor, abnormal operation conditions such as driving motor faults, belt deviation, overload, no-load, sundry obstacles and the like not only affect the working efficiency of the belt conveyor and cause waste of materials and resources, but also possibly cause serious mechanical faults. Therefore, the normal operation of the belt conveyor apparatus is a key element of safe production.
However, in the prior art, the detection of the belt conveyor mainly relates to the aspects of equipment components or abnormal materials, and the monitoring of the running state of the equipment is mainly completed by means of manpower inspection, so that a large amount of manpower and time are consumed, the detection efficiency is low, and the belt conveyor is easy to neglect and miss, thereby greatly restricting the improvement of the operation efficiency and the dispatching automation level of the belt conveyor conveying system. Therefore, if video monitoring, image recognition and AI intelligent analysis techniques can be introduced, it is expected to improve the automation level of safety supervision of the belt conveyor. In view of this, we propose a video-based belt running state detection method.
Disclosure of Invention
The invention aims to provide a video-based belt running state detection method to solve the problems in the background technology.
In order to solve the above technical problem, an object of the present invention is to provide a video-based belt running state detection method, including the following steps:
s1, arranging corresponding video camera modules and various sensors near the belt of the belt conveying device, and arranging a video processing computer component at the near end or the far end of the belt conveying device;
s2, building a system framework of the running state of the belt by combining the arranged devices and sensors, configuring the running environment of the detection system, and building the running state detection system of the belt;
s3, starting a video-based belt running state detection device, and monitoring the running state of the belt conveying device in real time;
s4, detecting and identifying the running state and abnormal fault conditions of the belt conveying device based on the real-time recorded video data through an AI intelligent analysis technology, an image recognition technology and a neural network learning method;
s5, accurately judging the running state of the belt conveying device by combining the state parameters acquired by various sensors in real time, and scoring the influence degree of the judged abnormal conditions on the running safety performance of the equipment according to a preset scoring standard;
s6, setting a corresponding safety protection mechanism aiming at the abnormal belt running state which possibly occurs, when the belt conveying device has abnormal conditions, executing the measures of the safety protection mechanism according to a preset program, outputting an alarm signal in time, and scheduling and arranging aiming at the maintenance operation.
As a further improvement of the present invention, in S1, the video camera modules disposed near the belt conveyor include, but are not limited to: the high-definition camera covers the whole belt conveying device in the visual field, is arranged above the belt at a certain depression angle and is used for shooting the belt, is arranged near the driving motor and is used for shooting the driving motor and is provided with a recording function, and the like; various types of sensors deployed in the vicinity of the belt conveyor include, but are not limited to: the device comprises material flow detection devices respectively arranged at the head end and the tail end of the belt conveying device, speed sensors respectively arranged at the head end and the tail end of the belt conveying device, weighing sensors respectively arranged at the lower parts of bearing support rollers at the head end and the tail end of the belt conveying device, a voltage detection device electrically connected with a driving motor and the like; computer components include, but are not limited to: the system comprises a processor, a display, a network switch, a cloud server, a video/image recognition program module, an AI intelligent analysis terminal and the like.
As a further improvement of this solution, in S4, when the image is identified by the image identification technology, preprocessing such as dimension reduction, color binarization, and image segmentation is required to be performed on the target image, and the method and related algorithm adopted by the method are as follows:
the image dimensionality reduction adopts a PCA dimensionality reduction algorithm, and comprises the following steps:
inputting: training sample set
Figure 851679DEST_PATH_IMAGE001
Low dimensional space dimension
Figure 907972DEST_PATH_IMAGE002
；
The algorithm process is as follows:
step1, centralizing all samples, namely, performing a mean value removing operation:
Figure 215457DEST_PATH_IMAGE003
；
step2, calculating covariance matrix of samples
Figure 43735DEST_PATH_IMAGE004
；
Step3, covariance matrix
Figure 575211DEST_PATH_IMAGE004
Carrying out characteristic value decomposition;
step4, get maximum
Figure 121730DEST_PATH_IMAGE005
The characteristic vector corresponding to each characteristic value
Figure 232905DEST_PATH_IMAGE006
；
Step5, multiplying the original matrix by the projection matrix:
Figure 181270DEST_PATH_IMAGE007
i.e. reduced dimension data set
Figure 821330DEST_PATH_IMAGE008
Wherein
Figure 852215DEST_PATH_IMAGE009
Is composed of
Figure 501502DEST_PATH_IMAGE010
The ratio of vitamin to vitamin is,
Figure 304373DEST_PATH_IMAGE011
is vitamin A;
and (3) outputting: reducing the dimension of the data set;
the color binarization processing adopts an Otsu threshold value method, and the algorithm expression is as follows:
for images
Figure 380914DEST_PATH_IMAGE012
Prospect ofThe segmentation threshold of the (target) and background is denoted as T, and the proportion of the number of pixels belonging to the foreground in the whole image is denoted as
Figure 698762DEST_PATH_IMAGE013
Average gray scale of
Figure 620582DEST_PATH_IMAGE014
(ii) a The number of background pixels is in proportion to the whole image, and the average gray level is
Figure 543539DEST_PATH_IMAGE015
(ii) a The total average gray scale of the image is recorded as
Figure 587718DEST_PATH_IMAGE016
The inter-class variance is recorded as g;
assume that the background of the image is dark and the size of the image is
Figure 330546DEST_PATH_IMAGE017
The number of pixels in the image whose grey value is less than the threshold value T is recorded as
Figure 318706DEST_PATH_IMAGE018
The number of pixels having a pixel gray level greater than the threshold T is counted as
Figure 96169DEST_PATH_IMAGE019
Then, there are:
Figure 311250DEST_PATH_IMAGE020
；
Figure 541374DEST_PATH_IMAGE021
；
Figure 70576DEST_PATH_IMAGE022
；
Figure 702545DEST_PATH_IMAGE023
；
Figure 88527DEST_PATH_IMAGE024
；
Figure 71527DEST_PATH_IMAGE025
；
substituting formula (5) for formula (6) yields the equivalent formula:
Figure 138840DEST_PATH_IMAGE026
；
the formula (7) is the inter-class variance, and the threshold T with the maximum inter-class variance g is obtained by adopting a traversal method, namely the obtained threshold T is the solved threshold;
the image segmentation processing adopts a watershed algorithm, and the algorithm expression is as follows:
Figure 422054DEST_PATH_IMAGE027
；
Figure 468286DEST_PATH_IMAGE028
；
Figure 673003DEST_PATH_IMAGE029
；
the simulation flooding process from bottom to top is a recursion process, and the formula (1) belongs to the initial condition of the recursion process and enables the pixel point with the minimum gray value in the image I; formula (2) is a recursive process;
in the formula, h represents the range of gray scale values,
Figure 544007DEST_PATH_IMAGE030
is the minimum value of the gray value range,
Figure 681727DEST_PATH_IMAGE031
as a range of gray valuesA maximum value;
Figure 878353DEST_PATH_IMAGE032
is a gray scale value and an altitude of
Figure 570366DEST_PATH_IMAGE033
All of the pixel points of (a) above,
Figure 245061DEST_PATH_IMAGE034
indicating that this point belongs to the newly created basin minimum, i.e. at
Figure 909391DEST_PATH_IMAGE033
This altitude in turn creates a new basin;
Figure 539568DEST_PATH_IMAGE035
to represent
Figure 453298DEST_PATH_IMAGE032
Point and point
Figure 666104DEST_PATH_IMAGE036
The points are intersected with each other at the same time,
Figure 247258DEST_PATH_IMAGE037
is composed of
Figure 316846DEST_PATH_IMAGE036
The basin where the points are located, therefore
Figure 983450DEST_PATH_IMAGE038
Is characterized by
Figure 734369DEST_PATH_IMAGE032
Point and point
Figure 170029DEST_PATH_IMAGE036
Points that are co-located in a basin;
through the recursion process, all pixel points in the image I are divided into basins.
As a further improvement of the present invention, in S4, the abnormal failure condition of the belt conveying device includes but is not limited to: driving motor failure, belt deviation, belt tearing, bulk material obstacle, metal sundry abrasion and the like.
As a further improvement of the present technical solution, in S5, the operation state of the belt conveying device includes, but is not limited to: start/stop, no load, loaded, overloaded, material spread, too fast/too slow of a transport speed, material flow source/tail position change, loaded start, etc.
Another object of the present invention is to provide a video-based belt running state detecting system, which includes: the device comprises a video processing module, a monitoring detection module, an identification scoring module and a signal output module; the signal output end of the video processing module is connected with the signal input end of the monitoring detection module, the signal output end of the monitoring detection module is connected with the signal input end of the identification scoring module, and the signal output end of the identification scoring module is connected with the signal input end of the signal output module; wherein:
the video processing module is used for carrying out real-time video recording and storage on the whole of the belt conveying device and the running conditions of various parts such as a belt, a driving motor and the like;
the monitoring detection module is used for identifying the shot video and the image intercepted from the video, screening out the characteristic video with abnormal conditions and transmitting the characteristic video into the identification scoring module;
the judging and scoring module is used for judging and scoring the type of the abnormal condition through a neural network method according to the characteristic video of the abnormal condition and scoring and evaluating the influence degree of the abnormal type on the safety performance of the belt conveying device in the operation process according to a preset scoring rule;
the signal output module is used for outputting the detected abnormal conditions and the grading data thereof, executing a preset safety protection mechanism and outputting an alarm signal.
As a further improvement of the technical scheme, the video processing module further comprises a video acquisition sub-module, a video transmission sub-module and a video storage sub-module; the signal output end of the video acquisition submodule is connected with the signal input end of the video transmission submodule, and the signal output end of the video transmission submodule is connected with the signal input end of the video storage submodule; the video acquisition submodule is used for shooting and recording a video of the running state of the inner belt of the visual field of the belt conveyor in real time through a video shooting module arranged near the belt conveyor; the video transmission sub-module is used for transmitting the real-time recorded video to the processor for processing through a wired/wireless transmission technology; the video storage submodule is used for transmitting the original video data and the abnormal video identified by processing to the local/cloud storage for storage; the video storage submodule is used for local storage or cloud storage.
As a further improvement of the technical scheme, the monitoring and detecting module also comprises an AI intelligent analysis submodule, an image recognition submodule and a sensing data management submodule; the AI intelligent analysis submodule, the image recognition submodule and the sensing data management submodule are sequentially connected through network communication and run in parallel; the AI intelligent analysis submodule is used for analyzing the video stream through an AI intelligent analysis technology and detecting the video with abnormal conditions in the running state of the belt; the image identification submodule is used for intercepting the image in the video with abnormal conditions for further identification and judgment through an image identification technology; and the sensing data management submodule is used for acquiring the state parameters acquired by each sensor, and performing sorting, statistics, analysis and storage management on the sensing parameters.
As a further improvement of the technical scheme, the judgment and scoring module further comprises a neural network algorithm submodule, a state judgment submodule and a safety influence scoring submodule; the signal output end of the neural network algorithm submodule is connected with the signal input end of the state judgment and identification submodule, and the signal output end of the state judgment and identification submodule is connected with the signal input end of the safety influence scoring submodule; the neural network algorithm submodule is used for monitoring and judging the belt operation abnormal condition which can be identified by naked eyes in the video by adopting a neural network method; the state identification sub-module is used for identifying the running state of the belt conveying device by combining the sensing data at the same time point as the abnormal condition of the belt and roughly analyzing the reason of the abnormal condition of the belt; and the safety influence scoring submodule is used for evaluating and scoring the influence degree of the judged and identified belt abnormal condition on the running safety performance of the belt conveying device according to a preset scoring rule.
As a further improvement of the technical scheme, the signal output module further comprises a safety mechanism sub-module, an alarm signal sub-module and a maintenance scheduling sub-module; the safety mechanism submodule, the alarm signal submodule and the overhaul scheduling submodule are sequentially connected through network communication and run in parallel; the safety mechanism submodule is used for setting a corresponding safety protection mechanism including shutdown according to the possible abnormal type and the influence degree of the abnormal condition on the safety performance in the running process of the belt conveying device, and automatically executing a safety protection program when the preset condition is reached; the alarm signal sub-module is used for sending out alarm signals in various modes when detecting that the belt conveying device has abnormal operating conditions; and the overhaul scheduling submodule is used for scheduling overhaul and maintenance on the abnormal operating condition according to a certain rule or sequence.
The protection program of the security protection mechanism includes but is not limited to: stopping the machine (such as motor faults, severe belt tearing and the like), reducing the conveying speed (such as belt deviation, material scattering and the like), reducing the power of a driving motor (such as overhigh voltage of the driving motor), reducing the conveying capacity (such as slight belt tearing, material scattering, overload, loaded starting and the like) and the like.
Wherein, the alarm mode includes but not limited to: flashing, pop-up, buzzer, warning light, short message notification, etc.
Wherein, the rule or sequence according to which the maintenance scheduling is performed may be: time by time, safety impact degree by size, position by height/front and back, maintenance difficulty and the like.
It is a further object of the present invention to provide an operating apparatus of a video-based belt running state detecting system, which comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor is configured to implement any of the steps of the video-based belt running state detecting method when executing the computer program.
It is a fourth object of the present invention to provide a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of any of the above-described video-based belt running state detecting methods.
Compared with the prior art, the invention has the beneficial effects that:
1. the belt running state detection method based on the video comprises the steps of laying a video camera module and various sensors near a belt conveying device, building an automatic computer framework and a detection system, combining AI intelligent analysis and image recognition technologies, and detecting and judging the running state of the belt conveying device in real time on the basis of monitoring videos;
2. according to the belt running state detection method based on the video, the abnormal conditions existing in the running process of the belt conveyor are detected and judged through the neural network algorithm, and the influence degree of the abnormal conditions on the safety performance of the belt conveyor is evaluated according to a certain rule, so that the running state of the belt conveyor is accurately evaluated, manual inspection is not needed, a large amount of manpower and time are saved, the detection efficiency is improved, and negligence, mistakes and omissions are reduced;
3. according to the belt running state detection method based on the video, through the preset safety protection mechanism, when the system detects an abnormal condition, the system automatically executes and gives an alarm, so that the potential safety hazard of production can be effectively reduced, the waste of materials and resources is reduced, the maintenance and repair of the fault condition are facilitated in time, and the safe running of production is ensured.
Drawings
FIG. 1 is a flow chart of the overall process of the present invention;
FIG. 2 is an overall architecture diagram of the inspection side system of the present invention;
FIG. 3 is a block diagram of an exemplary electronic computer product device in accordance with the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in fig. 1 to 3, the present embodiment provides a video-based belt running state detection method, including the following steps:
s1, arranging corresponding video camera modules and various sensors near the belt of the belt conveying device, and arranging a video processing computer component at the near end or the far end of the belt conveying device;
s2, building a system framework of the running state of the belt by combining the arranged devices and sensors, configuring the running environment of the detection system, and building the running state detection system of the belt;
s3, starting a video-based belt running state detection device, and monitoring the running state of the belt conveying device in real time;
s4, detecting and identifying the running state and abnormal fault conditions of the belt conveying device based on the real-time recorded video data through an AI intelligent analysis technology, an image recognition technology and a neural network learning method;
s5, accurately judging the running state of the belt conveying device by combining the state parameters acquired by various sensors in real time, and scoring the influence degree of the judged abnormal conditions on the running safety performance of the equipment according to a preset scoring standard;
s6, setting a corresponding safety protection mechanism aiming at the abnormal belt running state which possibly occurs, when the belt conveying device has abnormal conditions, executing the measures of the safety protection mechanism according to a preset program, outputting an alarm signal in time, and scheduling and arranging aiming at the maintenance operation.
In this embodiment, in S1, the video camera modules disposed near the belt conveyor include, but are not limited to: the high-definition camera covers the whole belt conveying device in the visual field, is arranged above the belt at a certain depression angle and is used for shooting the belt, is arranged near the driving motor and is used for shooting the driving motor and is provided with a recording function, and the like; various types of sensors deployed in the vicinity of the belt conveyor include, but are not limited to: the device comprises material flow detection devices respectively arranged at the head end and the tail end of the belt conveying device, speed sensors respectively arranged at the head end and the tail end of the belt conveying device, weighing sensors respectively arranged at the lower parts of bearing support rollers at the head end and the tail end of the belt conveying device, a voltage detection device electrically connected with a driving motor and the like; computer components include, but are not limited to: the system comprises a processor, a display, a network switch, a cloud server, a video/image recognition program module, an AI intelligent analysis terminal and the like.
In this embodiment, in S4, when the image is identified by the image identification technique, preprocessing such as dimension reduction, color binarization, and image segmentation needs to be performed on the target image, and the method and the related algorithm used in the method are as follows:
the image dimensionality reduction adopts a PCA dimensionality reduction algorithm, and comprises the following steps:
inputting: training sample set
Figure 410518DEST_PATH_IMAGE001
Low dimensional space dimension
Figure 295909DEST_PATH_IMAGE002
；
The algorithm process is as follows:
step1, centralizing all samples, namely, performing a mean value removing operation:
Figure 116098DEST_PATH_IMAGE003
；
step2, calculating covariance matrix of samples
Figure 203003DEST_PATH_IMAGE004
；
Step3, covariance matrix
Figure 83234DEST_PATH_IMAGE004
Carrying out characteristic value decomposition;
step4, get maximum
Figure 193272DEST_PATH_IMAGE005
The characteristic vector corresponding to each characteristic value
Figure 348310DEST_PATH_IMAGE006
；
Step5, multiplying the original matrix by the projection matrix:
Figure 758563DEST_PATH_IMAGE007
i.e. reduced dimension data set
Figure 278537DEST_PATH_IMAGE008
Wherein
Figure 141451DEST_PATH_IMAGE009
Is composed of
Figure 97250DEST_PATH_IMAGE010
The ratio of vitamin to vitamin is,
Figure 362009DEST_PATH_IMAGE011
is composed of
Figure 318464DEST_PATH_IMAGE039
Maintaining;
and (3) outputting: reduced dimension data set
Figure 465411DEST_PATH_IMAGE008
；
The color binarization processing adopts an Otsu threshold value method, and the algorithm expression is as follows:
for images
Figure 165514DEST_PATH_IMAGE012
The segmentation threshold of foreground (target) and background is denoted as T, and the ratio of the number of pixels belonging to foreground to the whole image is denoted as
Figure 19201DEST_PATH_IMAGE013
Average gray scale of
Figure 412136DEST_PATH_IMAGE014
(ii) a The number of background pixels is in proportion to the whole image
Figure 46380DEST_PATH_IMAGE040
Having an average gray scale of
Figure 284594DEST_PATH_IMAGE015
(ii) a The total average gray scale of the image is recorded as
Figure 55104DEST_PATH_IMAGE016
The inter-class variance is recorded as g;
assume that the background of the image is dark and the size of the image is
Figure 616011DEST_PATH_IMAGE017
The number of pixels in the image whose grey value is less than the threshold value T is recorded as
Figure 675234DEST_PATH_IMAGE018
The number of pixels having a pixel gray level greater than the threshold T is counted as
Figure 717139DEST_PATH_IMAGE019
Then, there are:
Figure 607735DEST_PATH_IMAGE020
；
Figure 342472DEST_PATH_IMAGE021
；
Figure 623412DEST_PATH_IMAGE022
；
Figure 531325DEST_PATH_IMAGE023
；
Figure 479690DEST_PATH_IMAGE024
；
Figure 119750DEST_PATH_IMAGE025
；
substituting formula (5) for formula (6) yields the equivalent formula:
Figure 150635DEST_PATH_IMAGE026
；
the formula (7) is the inter-class variance, and the threshold T with the maximum inter-class variance g is obtained by adopting a traversal method, namely the obtained threshold T is the solved threshold;
the image segmentation processing adopts a watershed algorithm, and the algorithm expression is as follows:
Figure 331081DEST_PATH_IMAGE027
；
Figure 399531DEST_PATH_IMAGE028
；
Figure 210492DEST_PATH_IMAGE029
；
the simulation flooding process from bottom to top is a recursion process, and the formula (1) belongs to the initial condition of the recursion process and enables the pixel point with the minimum gray value in the image I; formula (2) is a recursive process;
in the formula, h represents the range of gray scale values,
Figure 731603DEST_PATH_IMAGE030
is the minimum value of the gray value range,
Figure 715740DEST_PATH_IMAGE031
is the maximum value of the gray value range;
Figure 373117DEST_PATH_IMAGE032
is a gray scale value and an altitude of
Figure 620559DEST_PATH_IMAGE033
All of the pixel points of (a) above,
Figure 425704DEST_PATH_IMAGE034
indicating that this point belongs to the newly created basin minimum, i.e. at
Figure 413864DEST_PATH_IMAGE033
This altitude in turn creates a new basin;
Figure 925748DEST_PATH_IMAGE035
to represent
Figure 140828DEST_PATH_IMAGE032
Point and point
Figure 370953DEST_PATH_IMAGE036
The points are intersected with each other at the same time,
Figure 165733DEST_PATH_IMAGE037
is composed of
Figure 532124DEST_PATH_IMAGE036
The basin where the points are located, therefore
Figure 121368DEST_PATH_IMAGE038
Is characterized by
Figure 901105DEST_PATH_IMAGE032
Point and point
Figure 968418DEST_PATH_IMAGE036
Points that are co-located in a basin;
through the recursion process, all pixel points in the image I are divided into basins.
In this embodiment, in S4, the abnormal failure condition of the belt conveying device includes, but is not limited to: driving motor failure, belt deviation, belt tearing, bulk material obstacle, metal sundry abrasion and the like.
In this embodiment, in S5, the operation state of the belt conveying device includes, but is not limited to: start/stop, no load, loaded, overloaded, material spread, too fast/too slow of a transport speed, material flow source/tail position change, loaded start, etc.
As shown in fig. 2, the present embodiment provides a video-based belt running state detection system, including: the device comprises a video processing module, a monitoring detection module, an identification scoring module and a signal output module; the signal output end of the video processing module is connected with the signal input end of the monitoring detection module, the signal output end of the monitoring detection module is connected with the signal input end of the identification scoring module, and the signal output end of the identification scoring module is connected with the signal input end of the signal output module; wherein:
the video processing module is used for carrying out real-time video recording and storage on the whole of the belt conveying device and the running conditions of various parts such as a belt, a driving motor and the like;
the monitoring detection module is used for identifying the shot video and the image intercepted from the video, screening out the characteristic video with abnormal conditions and transmitting the characteristic video into the identification scoring module;
the judging and scoring module is used for judging and scoring the type of the abnormal condition through a neural network method according to the characteristic video of the abnormal condition and scoring and evaluating the influence degree of the abnormal type on the safety performance of the belt conveying device in the operation process according to a preset scoring rule;
the signal output module is used for outputting the detected abnormal conditions and the grading data thereof, executing a preset safety protection mechanism and outputting an alarm signal.
In this embodiment, the video processing module further includes a video acquisition sub-module, a video transmission sub-module, and a video storage sub-module; the signal output end of the video acquisition submodule is connected with the signal input end of the video transmission submodule, and the signal output end of the video transmission submodule is connected with the signal input end of the video storage submodule; the video acquisition submodule is used for shooting and recording a video of the running state of the inner belt of the visual field of the belt conveyor in real time through a video shooting module arranged near the belt conveyor; the video transmission sub-module is used for transmitting the real-time recorded video to the processor for processing through a wired/wireless transmission technology; the video storage submodule is used for transmitting the original video data and the abnormal video identified by processing to the local/cloud storage for storage; the video storage submodule is used for local storage or cloud storage.
In this embodiment, the monitoring and detecting module further includes an AI intelligent analysis submodule, an image recognition submodule, and a sensing data management submodule; the AI intelligent analysis submodule, the image recognition submodule and the sensing data management submodule are sequentially connected through network communication and run in parallel; the AI intelligent analysis submodule is used for analyzing the video stream through an AI intelligent analysis technology and detecting the video with abnormal conditions in the running state of the belt; the image identification submodule is used for intercepting the image in the video with abnormal conditions for further identification and judgment through an image identification technology; and the sensing data management submodule is used for acquiring the state parameters acquired by each sensor, and performing sorting, statistics, analysis and storage management on the sensing parameters.
In this embodiment, the identification scoring module further comprises a neural network algorithm submodule, a state identification submodule and a safety influence scoring submodule; the signal output end of the neural network algorithm submodule is connected with the signal input end of the state judgment and identification submodule, and the signal output end of the state judgment and identification submodule is connected with the signal input end of the safety influence scoring submodule; the neural network algorithm submodule is used for monitoring and judging the belt operation abnormal condition which can be identified by naked eyes in the video by adopting a neural network method; the state identification sub-module is used for identifying the running state of the belt conveying device by combining the sensing data at the same time point as the abnormal condition of the belt and roughly analyzing the reason of the abnormal condition of the belt; and the safety influence scoring submodule is used for evaluating and scoring the influence degree of the judged and identified belt abnormal condition on the running safety performance of the belt conveying device according to a preset scoring rule.
The method comprises the following steps of combining sensing data at the same time point with the abnormal condition of the belt, judging the running state of the belt conveying device and roughly analyzing the reason of the abnormal condition of the belt, wherein possible reasons include but are not limited to: belt deviation caused by no-load/overload/loaded start, belt deviation caused by too high/too low conveying speed, belt tearing/material scattering caused by overload, belt deviation/driving motor fault caused by too low conveying speed/belt deviation/large material obstacle caused by large material obstacle, driving motor fault caused by too high voltage, belt deviation/large material obstacle caused by material flow source/tail position change, belt tearing caused by large material obstacle/metal sundry abrasion and the like.
In this embodiment, the signal output module further includes a safety mechanism sub-module, an alarm signal sub-module and an overhaul scheduling sub-module; the safety mechanism submodule, the alarm signal submodule and the overhaul scheduling submodule are sequentially connected through network communication and run in parallel; the safety mechanism submodule is used for setting a corresponding safety protection mechanism including shutdown according to the possible abnormal type and the influence degree of the abnormal condition on the safety performance in the running process of the belt conveying device, and automatically executing a safety protection program when the preset condition is reached; the alarm signal sub-module is used for sending out alarm signals in various modes when detecting that the belt conveying device has abnormal operating conditions; and the overhaul scheduling submodule is used for scheduling overhaul and maintenance on the abnormal operating condition according to a certain rule or sequence.
The protection program of the security protection mechanism includes but is not limited to: stopping the machine (such as motor faults, severe belt tearing and the like), reducing the conveying speed (such as belt deviation, material scattering and the like), reducing the power of a driving motor (such as overhigh voltage of the driving motor), reducing the conveying capacity (such as slight belt tearing, material scattering, overload, loaded starting and the like) and the like.
Wherein, the alarm mode includes but not limited to: flashing, pop-up, buzzer, warning light, short message notification, etc.
Wherein, the rule or sequence according to which the maintenance scheduling is performed may be: time by time, safety impact degree by size, position by height/front and back, maintenance difficulty and the like.
As shown in fig. 3, the present embodiment also provides an operating apparatus of a video-based belt running state detecting system, which includes a processor, a memory, and a computer program stored in the memory and running on the processor.
The processor comprises one or more processing cores, the processor is connected with the memory through the bus, the memory is used for storing program instructions, and the steps of the video-based belt running state detection method are realized when the processor executes the program instructions in the memory.
Alternatively, the memory may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
In addition, the present invention also provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of the video-based belt running state detection method are implemented.
Optionally, the present invention also provides a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps of the video-based belt running status detection method of the above aspects.
It will be understood by those skilled in the art that the processes for implementing all or part of the steps of the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (10)

1. A belt running state detection method based on videos is characterized by comprising the following steps: the method comprises the following steps:
s1, arranging corresponding video camera modules and various sensors near the belt of the belt conveying device, and arranging a video processing computer component at the near end or the far end of the belt conveying device;
s2, building a system framework of the running state of the belt by combining the arranged devices and sensors, configuring the running environment of the detection system, and building the running state detection system of the belt;
s3, starting a video-based belt running state detection device, and monitoring the running state of the belt conveying device in real time;
s4, detecting and identifying the running state and abnormal fault conditions of the belt conveying device based on the real-time recorded video data through an AI intelligent analysis technology, an image recognition technology and a neural network learning method;
s5, accurately judging the running state of the belt conveying device by combining the state parameters acquired by various sensors in real time, and scoring the influence degree of the judged abnormal conditions on the running safety performance of the equipment according to a preset scoring standard;
s6, setting a corresponding safety protection mechanism aiming at the abnormal belt running state which possibly occurs, when the belt conveying device has abnormal conditions, executing the measures of the safety protection mechanism according to a preset program, outputting an alarm signal in time, and scheduling and arranging aiming at the maintenance operation.
2. The video-based belt run status detection method of claim 1, wherein: in S1, the video camera modules disposed near the belt conveyor include, but are not limited to: the high-definition camera covers the whole belt conveying device in the visual field, is arranged above the belt at a certain depression angle and is used for shooting the belt, is arranged near the driving motor and is used for shooting the driving motor and is provided with a recording function, and the like; various types of sensors deployed in the vicinity of the belt conveyor include, but are not limited to: the device comprises material flow detection devices respectively arranged at the head end and the tail end of the belt conveying device, speed sensors respectively arranged at the head end and the tail end of the belt conveying device, weighing sensors respectively arranged at the lower parts of bearing support rollers at the head end and the tail end of the belt conveying device, a voltage detection device electrically connected with a driving motor and the like; computer components include, but are not limited to: the system comprises a processor, a display, a network switch, a cloud server, a video/image recognition program module, an AI intelligent analysis terminal and the like.
3. The video-based belt run status detection method of claim 1, wherein: in S2, the belt running state detecting system includes: the device comprises a video processing module, a monitoring detection module, an identification scoring module and a signal output module; the signal output end of the video processing module is connected with the signal input end of the monitoring detection module, the signal output end of the monitoring detection module is connected with the signal input end of the identification scoring module, and the signal output end of the identification scoring module is connected with the signal input end of the signal output module; wherein:
the video processing module is used for carrying out real-time video recording and storage on the whole of the belt conveying device and the running conditions of various parts such as a belt, a driving motor and the like;
the monitoring detection module is used for identifying the shot video and the image intercepted from the video, screening out the characteristic video with abnormal conditions and transmitting the characteristic video into the identification scoring module;
the judging and scoring module is used for judging and scoring the type of the abnormal condition through a neural network method according to the characteristic video of the abnormal condition and scoring and evaluating the influence degree of the abnormal type on the safety performance of the belt conveying device in the operation process according to a preset scoring rule;
the signal output module is used for outputting the detected abnormal conditions and the grading data thereof, executing a preset safety protection mechanism and outputting an alarm signal.
4. The video-based belt run status detection method of claim 3, wherein: the video processing module also comprises a video acquisition sub-module, a video transmission sub-module and a video storage sub-module; the signal output end of the video acquisition submodule is connected with the signal input end of the video transmission submodule, and the signal output end of the video transmission submodule is connected with the signal input end of the video storage submodule; the video acquisition submodule is used for shooting and recording a video of the running state of the inner belt of the visual field of the belt conveyor in real time through a video shooting module arranged near the belt conveyor; the video transmission sub-module is used for transmitting the real-time recorded video to the processor for processing through a wired/wireless transmission technology; the video storage submodule is used for transmitting the original video data and the abnormal video identified by processing to the local/cloud storage for storage; the video storage submodule is used for local storage or cloud storage.
5. The video-based belt run status detection method of claim 3, wherein: the monitoring detection module also comprises an AI intelligent analysis submodule, an image recognition submodule and a sensing data management submodule; the AI intelligent analysis submodule, the image recognition submodule and the sensing data management submodule are sequentially connected through network communication and run in parallel; the AI intelligent analysis submodule is used for analyzing the video stream through an AI intelligent analysis technology and detecting the video with abnormal conditions in the running state of the belt; the image identification submodule is used for intercepting the image in the video with abnormal conditions for further identification and judgment through an image identification technology; and the sensing data management submodule is used for acquiring the state parameters acquired by each sensor, and performing sorting, statistics, analysis and storage management on the sensing parameters.
6. The video-based belt run status detection method of claim 3, wherein: the judgment and scoring module also comprises a neural network algorithm submodule, a state judgment and scoring submodule and a safety influence scoring submodule; the signal output end of the neural network algorithm submodule is connected with the signal input end of the state judgment and identification submodule, and the signal output end of the state judgment and identification submodule is connected with the signal input end of the safety influence scoring submodule; the neural network algorithm submodule is used for monitoring and judging the belt operation abnormal condition which can be identified by naked eyes in the video by adopting a neural network method; the state identification sub-module is used for identifying the running state of the belt conveying device by combining the sensing data at the same time point as the abnormal condition of the belt and roughly analyzing the reason of the abnormal condition of the belt; and the safety influence scoring submodule is used for evaluating and scoring the influence degree of the judged and identified belt abnormal condition on the running safety performance of the belt conveying device according to a preset scoring rule.
7. The video-based belt run status detection method of claim 3, wherein: the signal output module also comprises a safety mechanism submodule, an alarm signal submodule and a maintenance scheduling submodule; the safety mechanism submodule, the alarm signal submodule and the overhaul scheduling submodule are sequentially connected through network communication and run in parallel; the safety mechanism submodule is used for setting a corresponding safety protection mechanism including shutdown according to the possible abnormal type and the influence degree of the abnormal condition on the safety performance in the running process of the belt conveying device, and automatically executing a safety protection program when the preset condition is reached; the alarm signal sub-module is used for sending out alarm signals in various modes when detecting that the belt conveying device has abnormal operating conditions; and the overhaul scheduling submodule is used for scheduling overhaul and maintenance on the abnormal operating condition according to a certain rule or sequence.
8. The video-based belt run status detection method of claim 1, wherein: in S4, when the image is identified by the image identification technique, preprocessing such as dimension reduction, color binarization, and image segmentation is required to be performed on the target image, and the method and the related algorithm adopted by the method are as follows:
the image dimensionality reduction adopts a PCA dimensionality reduction algorithm, and comprises the following steps:
inputting: training sample set
Figure 740332DEST_PATH_IMAGE001
Low dimensional space dimension
Figure 731422DEST_PATH_IMAGE002
；
The algorithm process is as follows:
step1, Bing ChengCentering, namely, a mean value removing operation is carried out on samples:
Figure 243306DEST_PATH_IMAGE003
；
step2, calculating covariance matrix of samples
Figure 661649DEST_PATH_IMAGE004
；
Step3, covariance matrix
Figure 157353DEST_PATH_IMAGE004
Carrying out characteristic value decomposition;
step4, get maximum
Figure 483292DEST_PATH_IMAGE005
The characteristic vector corresponding to each characteristic value
Figure 112332DEST_PATH_IMAGE006
；
Step5, multiplying the original matrix by the projection matrix:
Figure 701576DEST_PATH_IMAGE007
i.e. reduced dimension data set
Figure 215734DEST_PATH_IMAGE008
Wherein
Figure 548626DEST_PATH_IMAGE009
Is composed of
Figure 35102DEST_PATH_IMAGE010
The ratio of vitamin to vitamin is,
Figure 795248DEST_PATH_IMAGE011
is composed of
Figure 796702DEST_PATH_IMAGE012
Maintaining;
and (3) outputting: reduced dimension data set
Figure 667706DEST_PATH_IMAGE008
；
The color binarization processing adopts an Otsu threshold value method, and the algorithm expression is as follows:
for images
Figure 274268DEST_PATH_IMAGE013
The segmentation threshold of foreground (target) and background is denoted as T, and the ratio of the number of pixels belonging to foreground to the whole image is denoted as
Figure 2052DEST_PATH_IMAGE014
Average gray scale of
Figure 691135DEST_PATH_IMAGE015
(ii) a The number of background pixels is in proportion to the whole image
Figure 100251DEST_PATH_IMAGE016
Having an average gray scale of
Figure 561319DEST_PATH_IMAGE017
(ii) a The total average gray scale of the image is recorded as
Figure 725584DEST_PATH_IMAGE018
The inter-class variance is recorded as g;
assume that the background of the image is dark and the size of the image is
Figure 904893DEST_PATH_IMAGE019
The number of pixels in the image whose grey value is less than the threshold value T is recorded as
Figure 117700DEST_PATH_IMAGE020
The number of pixels having a pixel gray level greater than the threshold T is counted as
Figure 698854DEST_PATH_IMAGE021
Then, there are:
Figure 706124DEST_PATH_IMAGE022
；
Figure 369799DEST_PATH_IMAGE023
；
Figure 183034DEST_PATH_IMAGE024
；
Figure 618695DEST_PATH_IMAGE025
；
Figure 62446DEST_PATH_IMAGE026
；
Figure 950767DEST_PATH_IMAGE027
；
substituting formula (5) for formula (6) yields the equivalent formula:
Figure 770956DEST_PATH_IMAGE028
；
the formula (7) is the inter-class variance, and the threshold T with the maximum inter-class variance g is obtained by adopting a traversal method, namely the obtained threshold T is the solved threshold;
the image segmentation processing adopts a watershed algorithm, and the algorithm expression is as follows:
Figure 61123DEST_PATH_IMAGE029
；
Figure 738092DEST_PATH_IMAGE030
；
Figure 848130DEST_PATH_IMAGE031
；
the simulation flooding process from bottom to top is a recursion process, and the formula (1) belongs to the initial condition of the recursion process and enables the pixel point with the minimum gray value in the image I; formula (2) is a recursive process;
in the formula, h represents the range of gray scale values,
Figure 203501DEST_PATH_IMAGE032
is the minimum value of the gray value range,
Figure 410491DEST_PATH_IMAGE033
is the maximum value of the gray value range;
Figure 461624DEST_PATH_IMAGE034
is a gray scale value and an altitude of
Figure 58958DEST_PATH_IMAGE035
All of the pixel points of (a) above,
Figure 220949DEST_PATH_IMAGE036
indicating that this point belongs to the newly created basin minimum, i.e. at
Figure 16867DEST_PATH_IMAGE035
This altitude in turn creates a new basin;
Figure 973322DEST_PATH_IMAGE037
to represent
Figure 323531DEST_PATH_IMAGE034
Point and point
Figure 85951DEST_PATH_IMAGE038
The points are intersected with each other at the same time,
Figure 205217DEST_PATH_IMAGE039
is composed of
Figure 87501DEST_PATH_IMAGE038
The basin where the points are located, therefore
Figure 925007DEST_PATH_IMAGE040
Is characterized by
Figure 225539DEST_PATH_IMAGE034
Point and point
Figure 464890DEST_PATH_IMAGE038
Points that are co-located in a basin;
through the recursion process, all pixel points in the image I are divided into basins.
9. The video-based belt run status detection method of claim 1, wherein: in S4, the abnormal fault condition of the belt conveying device includes, but is not limited to: driving motor failure, belt deviation, belt tearing, bulk material obstacle, metal sundry abrasion and the like.
10. The video-based belt run status detection method of claim 1, wherein: in S5, the operation state of the belt conveying device includes, but is not limited to: start/stop, no load, loaded, overloaded, material spread, too fast/too slow of a transport speed, material flow source/tail position change, loaded start, etc.
CN202111503515.XA 2021-12-10 2021-12-10 Belt running state detection method based on video Pending CN114140733A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111503515.XA CN114140733A (en) 2021-12-10 2021-12-10 Belt running state detection method based on video

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111503515.XA CN114140733A (en) 2021-12-10 2021-12-10 Belt running state detection method based on video

Publications (1)

Publication Number Publication Date
CN114140733A true CN114140733A (en) 2022-03-04

Family

ID=80385839

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111503515.XA Pending CN114140733A (en) 2021-12-10 2021-12-10 Belt running state detection method based on video

Country Status (1)

Country Link
CN (1) CN114140733A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115909177A (en) * 2023-02-22 2023-04-04 江苏甬金金属科技有限公司 Intelligent monitoring method and system for surface of conveying rolling strip
CN116038424A (en) * 2023-02-14 2023-05-02 广东热浪新材料科技有限公司 Maintenance monitoring method and maintenance system for star basin processing equipment based on sensor
CN116142723A (en) * 2023-03-20 2023-05-23 淮南市万维机电有限公司 Belt feeder intelligent protection early warning system based on chip intelligent control
CN117622810A (en) * 2024-01-25 2024-03-01 山西戴德测控技术股份有限公司 Conveyor belt monitoring method, device, equipment and computer storage medium

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116038424A (en) * 2023-02-14 2023-05-02 广东热浪新材料科技有限公司 Maintenance monitoring method and maintenance system for star basin processing equipment based on sensor
CN116038424B (en) * 2023-02-14 2023-08-15 广东热浪新材料科技有限公司 Maintenance monitoring method and maintenance system for star basin processing equipment based on sensor
CN115909177A (en) * 2023-02-22 2023-04-04 江苏甬金金属科技有限公司 Intelligent monitoring method and system for surface of conveying rolling strip
CN115909177B (en) * 2023-02-22 2023-08-22 江苏甬金金属科技有限公司 Intelligent surface monitoring method and system for conveying rolling belt
CN116142723A (en) * 2023-03-20 2023-05-23 淮南市万维机电有限公司 Belt feeder intelligent protection early warning system based on chip intelligent control
CN116142723B (en) * 2023-03-20 2023-08-08 淮南市万维机电有限公司 Belt feeder intelligent protection early warning system based on chip intelligent control
CN117622810A (en) * 2024-01-25 2024-03-01 山西戴德测控技术股份有限公司 Conveyor belt monitoring method, device, equipment and computer storage medium
CN117622810B (en) * 2024-01-25 2024-04-19 山西戴德测控技术股份有限公司 Conveyor belt monitoring method, device, equipment and computer storage medium

Similar Documents

Publication Publication Date Title
CN114140733A (en) Belt running state detection method based on video
Xianguo et al. Laser-based on-line machine vision detection for longitudinal rip of conveyor belt
CN104535356A (en) Method and system for monitoring rope arrangement faults of drum steel wire rope on basis of machine vision
WO2015129879A1 (en) Monitoring device, monitoring method, and program
CN102275723A (en) Machine-vision-based online monitoring system and method for conveyer belt
CN102602681A (en) Machine vision based online deviation fault detecting method for conveying belts
CN110015553B (en) Foreign matter detection and protection method for conveyor belt system based on video analysis
Zhang et al. A deep learning-based method for deviation status detection in intelligent conveyor belt system
Szkilnyk et al. Vision based fault detection of automated assembly equipment
CN115272980B (en) Conveyor belt surface detection method and system based on machine vision
CN103213823B (en) Visual inspection and pre-warning system for longitudinal tear of conveying belt and application method of conveying belt
CN103630221A (en) Method for remotely monitoring vehicle weighing cheating by using video analyzing
CN109635823B (en) Method and device for identifying winding disorder rope and engineering machinery
CN114140684A (en) Method, device and equipment for detecting coal blockage and coal leakage and storage medium
Qiao et al. Research on visible light and infrared vision real‐time detection system for conveyor belt longitudinal tear
CN110519566B (en) Belt motion state monitoring method based on video processing
CN113378648A (en) Artificial intelligence port and wharf monitoring method
CN114740086A (en) Monorail crane track defect detection method
CN113184483B (en) Conveyer belt tearing prevention system and early warning method
Li et al. Intelligent monitoring system of coal conveyor belt based on computer vision technology
US20230316489A1 (en) Scrap discrimination system and scrap discrimination method
Phelawan et al. A new technique for distance measurement of between vehicles to vehicles by plate car using image processing
CN117315593A (en) Recognition method for foreign matter invasion of underground coal mine transportation system
CN115504187B (en) Intelligent speed regulation and protection system and control method for mining belt
CN105512633A (en) Power system dangerous object identification method and apparatus

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication