CN112862817A - Roller rope disorder detection method and device based on machine vision - Google Patents
Roller rope disorder detection method and device based on machine vision Download PDFInfo
- Publication number
- CN112862817A CN112862817A CN202110282982.8A CN202110282982A CN112862817A CN 112862817 A CN112862817 A CN 112862817A CN 202110282982 A CN202110282982 A CN 202110282982A CN 112862817 A CN112862817 A CN 112862817A
- Authority
- CN
- China
- Prior art keywords
- roller
- image
- alarm
- ropes
- messy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000003709 image segmentation Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 7
- 230000002159 abnormal effect Effects 0.000 abstract description 6
- 229910000831 Steel Inorganic materials 0.000 description 26
- 239000010959 steel Substances 0.000 description 26
- 238000010586 diagram Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000002085 persistent effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 230000005484 gravity Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003707 image sharpening Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The disclosure relates to a roller rope disorder detection method and device based on machine vision. The method comprises the following steps: acquiring an image of a roller area; judging whether the roller is in a rotating state according to the image; if the roller is in a rotating state, identifying the roller side and a bouncer boundary frame in the image by using a pre-trained image identification model; counting the number of the messy ropes with the distance from the boundary frame of the roller side not within a preset range; and if the number of the messy ropes exceeds the set number, giving an alarm. The scheme provided by the disclosure can realize intelligent sensing of abnormal phenomena of the messy ropes of the roller and send out an alarm in real time, so that the shutdown processing is carried out in time, and the reliability of equipment operation is greatly improved.
Description
Technical Field
The disclosure relates to the field of machine vision and equipment detection, in particular to a method and a device for detecting a roller rope disorder based on machine vision.
Background
The hoisting rope is a steel wire rope for connecting the hoisting container and transmitting the power of the hoist. It is an important component of a wire rope hoisting device. The steel wire rope is the most important connecting part as a vertical shaft elevator, and once the phenomena of rope disorder, rope biting and the like occur, the abrasion and the deformation of the steel wire rope can be accelerated, so that the steel wire rope loses the stable lifting and traction functions, the normal completion condition of a production task is influenced, huge economic loss is caused, and even the life safety of personnel can be concerned. Therefore, in the production process, the rope disorder phenomenon is found in time, corresponding correct operations such as speed reduction, stopping, replacement and maintenance can be carried out according to the frequency of abnormal occurrence such as the rope disorder, and meanwhile, the service condition and the current quality of the steel wire rope can be obtained.
At present, in the market, for monitoring and overhauling a steel wire rope of a vertical shaft elevator, a plurality of corresponding methods are provided, weight sensing is utilized, whether the gravity borne by the tail end of the steel wire rope is consistent with the current tension is judged, if the gravity is inconsistent with the current tension, the possibility of abnormality (overlarge tension or no stress on the steel wire rope) is shown, whether the movement speed of the steel wire rope is consistent with the rotation speed of a roller is also judged, and whether the angle of a steel wire rope roller at a rope outlet position (rope inlet position) is within a certain threshold range is also observed.
Disclosure of Invention
In order to overcome the problems in the related art, the disclosure provides a method and a device for detecting the disorder of the drum rope based on machine vision, which can timely find out the disorder of the drum steel wire rope and send out an alarm, thereby reducing the shutdown caused by the disorder of the rope.
According to a first aspect of the embodiments of the present disclosure, there is provided a machine vision-based roller roping detection method, including:
acquiring an image of a roller area;
judging whether the roller is in a rotating state according to the image;
if the roller is in a rotating state, identifying the roller side and a bouncer boundary frame in the image by using a pre-trained image identification model;
counting the number of the messy ropes with the distance from the boundary frame of the roller side not within a preset range;
and if the number of the messy ropes exceeds the set number, giving an alarm.
Further, the determining whether the drum is in a rotating state according to the image specifically includes:
and judging whether the roller is in a rotating state or not according to a comparison result of a difference value between two frames of images separated by a preset time length and a preset threshold value.
Further, the image recognition model adopts a target detection algorithm or an image segmentation algorithm.
Further, the method also includes:
calculating the duration of the rope disorder when the distance between the first rope disorder and the boundary frame of the roller side is not within a preset range;
and if the duration time of the messy ropes exceeds the set time and the roller is in a stop state, giving an alarm.
According to a second aspect of the embodiments of the present disclosure, there is provided a machine vision-based drum roping detection apparatus, including:
the image acquisition module is used for acquiring an image of the roller area;
the state judgment module is used for judging whether the roller is in a rotating state according to the image;
the image recognition module is used for recognizing the roller side and the disordered rope boundary frame in the image by using a pre-trained image recognition model if the roller is judged to be in a rotating state by the state judgment module;
the quantity counting module is used for counting the quantity of the messy ropes with the distance from the boundary frame of the roller edge not within the preset range;
and the alarm module is used for giving an alarm if the number of the messy ropes counted by the number counting module exceeds a set number.
Further, the state determination module is specifically configured to:
and judging whether the roller is in a rotating state or not according to a comparison result of a difference value between two frames of images separated by a preset time length and a preset threshold value.
Further, the image recognition model adopts a target detection algorithm or an image segmentation algorithm.
Further, the apparatus further comprises:
the timing module is used for calculating the duration time of the first rope disorder when the distance between the first rope disorder and the boundary frame of the roller side is not within the preset range;
the alarm module is further used for giving an alarm if the duration time of the messy ropes calculated by the timing module exceeds the set time and the roller is in a stop state.
According to a third aspect of the embodiments of the present disclosure, there is provided a terminal device, including:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method as described above.
According to a fourth aspect of embodiments of the present disclosure, there is provided a non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method as described above.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
through the real-time intelligent analysis to the regional image of cylinder, can realize the intelligent perception of the indiscriminate rope abnormal phenomena of cylinder to send the warning in real time, so that in time carry out the shutdown processing, improved the reliability of equipment operation greatly.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in greater detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts throughout.
FIG. 1 is a schematic flow diagram illustrating a machine vision based method of drum roping detection according to an exemplary embodiment of the present disclosure;
FIG. 2 is a process flow diagram of drum roping detection provided by the present disclosure;
FIG. 3 is a flowchart of the processing procedure of the AI business model for the identification result of the rope disorder;
FIG. 4 is a diagram of the effect of the yolo algorithm on the identification of a misrope target;
FIG. 5 is a diagram of the effect of yolact algorithm on the identification of a rope-disorder target;
FIG. 6 is a schematic view of a garniture at a roller highwall;
FIG. 7 is a block diagram illustrating a machine vision based drum roping detection apparatus according to an exemplary embodiment of the present disclosure;
FIG. 8 is a schematic diagram illustrating a computing device, according to an example embodiment of the present disclosure.
Detailed Description
Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used in this disclosure to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present disclosure, "a plurality" means two or more unless specifically limited otherwise.
The applicant finds that at the beginning of rope disorder, signs such as rope overlapping twisting, loosening and the like exist, and by identifying the signs, the winding problem of the steel wire rope can be approached in time before the machine stops due to the rope disorder.
Based on the consideration, the drum messy rope detection method based on the machine vision is provided, an AI video recognition model is established and trained in a pertinence mode, the rotation condition of the drum is monitored based on a camera, the image of the messy rope is directly obtained, the winding condition of a steel wire rope on the drum is discriminated in real time, and when the messy rope, the loosening and other conditions occur, the obtained image is compared with the image in the existing database, and alarm information is output.
Fig. 2 is a process flow diagram of drum roping detection provided by the present disclosure.
As shown in fig. 2, a high-speed camera can be used to collect video data of the drum area, and a depth camera can be used if necessary, so that when the wire rope on the drum is twisted, the depth distance can be shot to perform depth positioning, and the wire rope can be known to be twisted, thereby reducing misjudgment based on a plane figure. And because the judgment of the image may adopt an example segmentation method more, the depth camera is more convenient to perform example segmentation by a depth-of-field judgment method.
The AI video identification model is used for identifying the rope disorder degree of the steel wire rope on the roller. The video intelligent analysis function is mainly completed in the AI video identification, and the video intelligent analysis function is used for monitoring pictures according to real-time videos of the camera and AI analysis result information. When the steel wire rope roller does not rotate, the disorder judgment of the steel wire rope is not carried out, whether the steel wire rope rotates or not is judged only according to the pictures before and after the frame, and after the judgment is carried out, the disorder analysis is carried out, so that the identification efficiency can be improved, and the occupation of cloud and edge resources is reduced.
The recognition result of the AI video recognition model is output to the AI service model, and the AI service model can adopt an integrated service system. The system provides a unified login interface. The method comprises the functions of a main interface graph, a real-time data statistical curve graph, statistical analysis and the like. Because the management system of the vertical shaft elevator can have different monitoring and control positions according to the action of each specific part, the main interface diagram can have the functions of loading, counting and the like of the lifting objects of the main elevator besides the steel wire rope roller module related in the scheme.
Therefore, the 3D image of the whole main elevator can be reflected in the main interface graph, the operation condition and the alarm condition of each part can be displayed in the main interface, when an alarm (such as a yellow alarm) appears in a certain place, the alarm can be continuously flickered in the area, and therefore information such as the position, the degree and the like of the fault can be determined at the first time.
In the real-time data statistics, the real-time rope disorder state can be displayed according to a certain time period like the time similar to stock, for example, the current hour is taken as the period, the number of the rope disorder appearing at each time point can be displayed on a current chart in a curve (broken line) form, and the current 12 hours, the current day, the current week and the like can be displayed.
Because the steel wire rope needs to be checked and replaced at regular time, other equipment such as a roller and the like also needs regular check and maintenance, the management of current staff can be realized in the model, if the current staff needs to check the steel wire rope at regular time according to the requirement, and the like, and the staff can deal with the problems timely according to the requirement after the alarm of the steel wire rope occurs.
Video viewing and playback functions are also supported in the AI service model. And displaying monitoring video pictures of different positions of the vertical shaft lifting system in real time in a video list mode. Monitoring point equipment information, real-time alarm information and treatment state checking are supported; and a manual auxiliary labeling function is provided, and manual inspection of the video with machine error identification or missing identification is realized. The system also has the functions of checking historical alarm details, replaying historical videos, treating alarm information, issuing, filling and the like. When the steel wire rope is in an abnormal working state, abnormal video storage is realized for abnormal working conditions of rope biting and rope disorder, and historical alarm video playback in about 3 months is supported.
Specifically, fig. 3 is a flowchart of a processing procedure of the AI service model for the rope tangling recognition result. As shown in fig. 3, the recognition result is stored in the system, an alarm is sent out by comparison and issued to a terminal of a maintenance worker, if the recognition accords with the disorder definition, the worker maintains the steel wire rope, otherwise, the wrong alarm processing flow is entered, the worker modifies the picture recognition result, the worker submits the maintenance result through the terminal when maintaining the steel wire rope, in addition, when the worker finds that the disorder condition without alarm leakage occurs during maintenance, the missed alarm picture position information is obtained and submitted, and the missed alarm picture position information is uploaded to the terminal through the missed alarm processing flow, so that the reason of missed alarm is further analyzed.
Technical solutions of embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flow chart diagram illustrating a machine vision-based drum roping detection method according to an exemplary embodiment of the present disclosure.
With reference to figure 1 of the drawings,
the method comprises the following steps:
110. acquiring an image of a roller area;
specifically, the image of the drum area is a video frame taken from the video of the camera.
120. Judging whether the roller is in a rotating state according to the image;
specifically, in order to judge whether the roller rotates, 3 seconds of video can be prestored and placed in a cache space, the 3 seconds of video has the following purposes of identifying whether the roller rotates, and if the roller rotates, the 3 seconds of video serves as the video basis for judging whether the rope is disordered or not; if not, releasing the buffer and not judging. Then the 3 second video is stored continuously.
The specific process of identifying whether the roller moves is as follows:
firstly, a certain area range on a cylinder body of a roller is defined (a coordinate range needs to be manually adjusted according to the position of the roller on an image), after the area is preprocessed in the modes of image sharpening, noise point balancing and the like, the front and the back of a video are compared at an interval of 3 seconds, a gray level histogram of the image before and after 3 seconds is obtained, when a large difference exists between the image after 3 seconds and the image before 3 seconds (a threshold value is usually set, and the value needs to be comprehensively determined according to the environment and a test result), namely, the image in the area range is changed, namely: the drum is rotated.
130. If the roller is in a rotating state, identifying the roller side and a bouncer boundary frame in the image by using a pre-trained image identification model;
optionally, before performing the image recognition in step 130, the detected image may be preprocessed by noise reduction, sharpening, linear transformation, etc., so that the image features are more obvious and easy to extract.
After the preprocessing is finished, learning and identification can be carried out according to the marked rope disorder database, and the specific process is as follows:
learning according to the type of the rope disorder database required by different algorithms, and correspondingly learning and identifying according to the corresponding algorithms. In the embodiment, the yolo algorithm and the yolact algorithm are used as two methods for image recognition, and corresponding labeling recognition is carried out. The yolo algorithm represents a target detection algorithm, and is characterized by high learning speed, high recognition speed and low requirement on hardware, and has the defects that background patterns are easy to interfere and the number of pictures to be marked is large. yolact represents an image segmentation algorithm and has the characteristics of less learning data volume, accurate labeling, less background interference and higher requirement on hardware and slightly lower speed.
The method can select corresponding improvement for the requirements, if the characteristics are obvious, the yolo algorithm can be selected to improve the speed, and if the expenditure is sufficient and the hardware can keep up, the image segmentation algorithm can be selected to be more accurate. Fig. 4 and 5 are diagrams illustrating the effect of the yolo algorithm and yolact algorithm on the identification of the target with the straying rope.
140. Counting the number of the messy ropes with the distance from the boundary frame of the roller side not within a preset range;
specifically, after the target identification model identifies whether the rope is disordered, the position where the rope is disordered is judged according to the service logic, because the rope is at the roller side as shown in fig. 6, and the situation belongs to a normal phenomenon, therefore, when the situations occur, the position where the rope is disordered needs to be judged whether the rope is at the roller side.
Of course, it is also a suitable method to learn the special position images which are not messy ropes by using a deep learning method, and label the position as a normal label frame.
150. And if the number of the messy ropes exceeds the set number, giving an alarm.
Specifically, after the target recognition model outputs the final recognition result, the recognition result needs to be fed back to the AI service model by the application system interface module according to the rope disorder degree, and an alarm result is output according to a definition rule, such as: if the number of the messy ropes exceeds the set number, an alarm is given out.
The alarm also grades according to the degree of the messy ropes, if the alarm is slightly twisted, only yellow early warning is carried out, the alarm time is short, the alarm of the degree can remind a maintainer that the steel wire ropes are possibly worn and the like, the steel wire ropes are overhauled as soon as possible, if the messy ropes are very obvious, even the ropes are greatly fallen off from the roller, the machine is about to be stopped, red alarm is carried out, long-time alarm is carried out, and the elevator operator is reminded to stop as soon as possible.
Preferably, the garbled state is continuously tracked by continuously judging whether the drum is stopped or not through the video during the period from the time when the garbled state is identified to the time when the alarm is manually turned off by a worker.
Optionally, in this embodiment, the method further includes:
160. calculating the duration of the rope disorder when the distance between the first rope disorder and the boundary frame of the roller side is not within a preset range;
170. and if the duration time of the messy ropes exceeds the set time and the roller is in a stop state, giving an alarm.
Specifically, besides the number of the messy ropes, the duration of the messy ropes is an important index reflecting the messy rope degree, and of course, the normal condition that the distance between the messy ropes and the boundary frame of the roller edge is within the preset range still needs to be eliminated. And (3) giving an alarm according to the comparison result of the duration time of the rope disorder and the set time, wherein the rope disorder lasts for more than 3 seconds, and the drum slowly rotates until the drum is jammed due to the rope disorder, so that the highest-level alarm can be given.
The method solves the problems of rope disorder, rope loosening and the like of the vertical shaft elevator, makes more innovation and improvement in aspects of image detection service logic, alarm detection modes and the like, is designed in an extension mode in the aspect of problem management of the vertical shaft elevator, such as function display of a service platform and the like, and provides corresponding improvement measures for fault and leakage monitoring. The method and the device are helpful for monitoring and overhauling the rope disorder problem of the vertical shaft elevator more quickly and timely, and are a more complete, comprehensive, accurate and timely solution.
Fig. 7 is a block diagram illustrating a structure of a machine vision-based drum tangle detecting apparatus according to an exemplary embodiment of the present disclosure.
With reference to figure 7 of the drawings,
the device includes:
the image acquisition module is used for acquiring an image of the roller area;
the state judgment module is used for judging whether the roller is in a rotating state according to the image;
the image recognition module is used for recognizing the roller side and the disordered rope boundary frame in the image by using a pre-trained image recognition model if the roller is judged to be in a rotating state by the state judgment module;
the quantity counting module is used for counting the quantity of the messy ropes with the distance from the boundary frame of the roller edge not within the preset range;
and the alarm module is used for giving an alarm if the number of the messy ropes counted by the number counting module exceeds a set number.
FIG. 8 is a schematic diagram illustrating a computing device, according to an example embodiment of the present disclosure.
Referring to fig. 8, computing device 800 includes memory 810 and processor 820.
The Processor 820 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 810 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions for the processor 820 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. In addition, the memory 810 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, may also be employed. In some embodiments, memory 810 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 810 has stored thereon executable code that, when processed by the processor 820, may cause the processor 820 to perform some or all of the methods described above.
The aspects of the present disclosure have been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. Those skilled in the art should also appreciate that the acts and modules referred to in the specification are not necessarily required by the invention. In addition, it can be understood that steps in the method of the embodiment of the present disclosure may be sequentially adjusted, combined, and deleted according to actual needs, and modules in the device of the embodiment of the present disclosure may be combined, divided, and deleted according to actual needs.
Furthermore, the method according to the present disclosure may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present disclosure.
Alternatively, the present disclosure may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) that, when executed by a processor of an electronic device (or computing device, server, or the like), causes the processor to perform some or all of the various steps of the above-described method according to the present disclosure.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A roller rope disorder detection method based on machine vision is characterized by comprising the following steps:
acquiring an image of a roller area;
judging whether the roller is in a rotating state according to the image;
if the roller is in a rotating state, identifying the roller side and a bouncer boundary frame in the image by using a pre-trained image identification model;
counting the number of the messy ropes with the distance from the boundary frame of the roller side not within a preset range;
and if the number of the messy ropes exceeds the set number, giving an alarm.
2. The method according to claim 1, wherein the determining whether the drum is in a rotating state according to the image comprises:
and judging whether the roller is in a rotating state or not according to a comparison result of a difference value between two frames of images separated by a preset time length and a preset threshold value.
3. The method of claim 1, wherein the image recognition model employs an object detection algorithm or an image segmentation algorithm.
4. The method according to any one of claims 1-3, further comprising:
calculating the duration of the rope disorder when the distance between the first rope disorder and the boundary frame of the roller side is not within a preset range;
and if the duration time of the messy ropes exceeds the set time and the roller is in a stop state, giving an alarm.
5. A device for detecting the disorder of ropes of a roller based on machine vision is characterized by comprising:
the image acquisition module is used for acquiring an image of the roller area;
the state judgment module is used for judging whether the roller is in a rotating state according to the image;
the image recognition module is used for recognizing the roller side and the disordered rope boundary frame in the image by using a pre-trained image recognition model if the roller is judged to be in a rotating state by the state judgment module;
the quantity counting module is used for counting the quantity of the messy ropes with the distance from the boundary frame of the roller edge not within the preset range;
and the alarm module is used for giving an alarm if the number of the messy ropes counted by the number counting module exceeds a set number.
6. The apparatus of claim 5, wherein the state determination module is specifically configured to:
and judging whether the roller is in a rotating state or not according to a comparison result of a difference value between two frames of images separated by a preset time length and a preset threshold value.
7. The apparatus of claim 5, wherein the image recognition model employs an object detection algorithm or an image segmentation algorithm.
8. The apparatus of any one of claims 5-7, further comprising:
the timing module is used for calculating the duration time of the first rope disorder when the distance between the first rope disorder and the boundary frame of the roller side is not within the preset range;
the alarm module is further used for giving an alarm if the duration time of the messy ropes calculated by the timing module exceeds the set time and the roller is in a stop state.
9. A terminal device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any one of claims 1-4.
10. A non-transitory machine-readable storage medium having executable code stored thereon, wherein the executable code, when executed by a processor of an electronic device, causes the processor to perform the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110282982.8A CN112862817A (en) | 2021-03-16 | 2021-03-16 | Roller rope disorder detection method and device based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110282982.8A CN112862817A (en) | 2021-03-16 | 2021-03-16 | Roller rope disorder detection method and device based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112862817A true CN112862817A (en) | 2021-05-28 |
Family
ID=75994886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110282982.8A Pending CN112862817A (en) | 2021-03-16 | 2021-03-16 | Roller rope disorder detection method and device based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862817A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101264851A (en) * | 2008-05-12 | 2008-09-17 | 湖南三一起重机械有限公司 | Crane disorderly rope alarm method and device, and crane using the same device |
| US20090147280A1 (en) * | 2007-11-15 | 2009-06-11 | Konica Minolta Business Technologies, Inc. | Image forming method and image forming apparatus |
| CN103466490A (en) * | 2012-09-27 | 2013-12-25 | 中联重科股份有限公司 | Crane control method and system based on image processing and crane |
| CN104477723A (en) * | 2014-12-25 | 2015-04-01 | 中国矿业大学 | Disorder rope monitoring system for winding reel of mine hoist and disorder rope judging method |
| CN107403443A (en) * | 2017-07-28 | 2017-11-28 | 中南大学 | A kind of more rope multi-lay windings row's rope form state online test method and device based on machine vision |
| CN109635823A (en) * | 2018-12-07 | 2019-04-16 | 湖南中联重科智能技术有限公司 | The method and apparatus and engineering machinery of elevator disorder cable for identification |
| CN110458090A (en) * | 2019-08-08 | 2019-11-15 | 成都睿云物联科技有限公司 | Working state of excavator detection method, device, equipment and storage medium |
| CN110490995A (en) * | 2019-08-26 | 2019-11-22 | 精英数智科技股份有限公司 | A kind of belt operating status method for monitoring abnormality, system, equipment and storage medium |
| CN110929591A (en) * | 2019-11-04 | 2020-03-27 | 广州供电局有限公司 | Transformer substation monitoring method and device, computer equipment and storage medium |
| CN111401421A (en) * | 2020-03-06 | 2020-07-10 | 上海眼控科技股份有限公司 | Image category determination method based on deep learning, electronic device, and medium |
| CN111523472A (en) * | 2020-04-23 | 2020-08-11 | 杭州海康威视系统技术有限公司 | Active target counting method and device based on machine vision |
| CN111784681A (en) * | 2020-07-08 | 2020-10-16 | 长沙克莱自动化设备有限公司 | Steel wire rope disorder detection method and device, computer equipment and storage medium |
-
2021
- 2021-03-16 CN CN202110282982.8A patent/CN112862817A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090147280A1 (en) * | 2007-11-15 | 2009-06-11 | Konica Minolta Business Technologies, Inc. | Image forming method and image forming apparatus |
| CN101264851A (en) * | 2008-05-12 | 2008-09-17 | 湖南三一起重机械有限公司 | Crane disorderly rope alarm method and device, and crane using the same device |
| CN103466490A (en) * | 2012-09-27 | 2013-12-25 | 中联重科股份有限公司 | Crane control method and system based on image processing and crane |
| CN104477723A (en) * | 2014-12-25 | 2015-04-01 | 中国矿业大学 | Disorder rope monitoring system for winding reel of mine hoist and disorder rope judging method |
| CN107403443A (en) * | 2017-07-28 | 2017-11-28 | 中南大学 | A kind of more rope multi-lay windings row's rope form state online test method and device based on machine vision |
| CN109635823A (en) * | 2018-12-07 | 2019-04-16 | 湖南中联重科智能技术有限公司 | The method and apparatus and engineering machinery of elevator disorder cable for identification |
| CN110458090A (en) * | 2019-08-08 | 2019-11-15 | 成都睿云物联科技有限公司 | Working state of excavator detection method, device, equipment and storage medium |
| CN110490995A (en) * | 2019-08-26 | 2019-11-22 | 精英数智科技股份有限公司 | A kind of belt operating status method for monitoring abnormality, system, equipment and storage medium |
| CN110929591A (en) * | 2019-11-04 | 2020-03-27 | 广州供电局有限公司 | Transformer substation monitoring method and device, computer equipment and storage medium |
| CN111401421A (en) * | 2020-03-06 | 2020-07-10 | 上海眼控科技股份有限公司 | Image category determination method based on deep learning, electronic device, and medium |
| CN111523472A (en) * | 2020-04-23 | 2020-08-11 | 杭州海康威视系统技术有限公司 | Active target counting method and device based on machine vision |
| CN111784681A (en) * | 2020-07-08 | 2020-10-16 | 长沙克莱自动化设备有限公司 | Steel wire rope disorder detection method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| YI-LE YANG等: "A Method of Pedestrians Counting Based on Deep Learning", 《2019 3RD INTERNATIONAL CONFERENCE ON ELECTRONIC INFORMATION TECHNOLOGY AND COMPUTER ENGINEERING (EITCE)》, pages 2010 - 2013 * |
| 高加索 等: "绞车滚筒乱绳原因分析及解决方法", 《石油矿场机械》, pages 82 - 86 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3130555B1 (en) | Rope and rope groove monitoring | |
| CN104773626B (en) | A kind of building hoist standard knot bolt safe condition detection means | |
| CN109635823B (en) | Method and device for identifying winding disorder rope and engineering machinery | |
| CN109919066B (en) | Method and device for detecting density abnormality of passengers in rail transit carriage | |
| CN104182338A (en) | Fatigue driving early warning product detection accuracy test method | |
| CN111767902A (en) | Method, device and equipment for identifying dangerous goods of security check machine and storage medium | |
| CN105809219B (en) | A kind of the prefabricated pipe section quality testing statistical system and method for tunnel prefabricated pipe section production line | |
| CN111080668A (en) | Brake pad wear fault detection method and system | |
| CN111524136A (en) | Boxing abnormality detection system and method | |
| CN110738630A (en) | Training method and detection system of recursive deep learning system | |
| CN112862817A (en) | Roller rope disorder detection method and device based on machine vision | |
| CN115456963A (en) | Stock yard belt deviation detection method and system based on visual identification | |
| CN110264470B (en) | Freight train tarpaulin monitoring method, device, terminal and storage medium | |
| CN115144399A (en) | Assembly quality detection method and device based on machine vision | |
| CN212515899U (en) | Boxing abnormality detection system | |
| CN117197090A (en) | Disposable tableware surface defect detection system based on deep learning | |
| CN111717616A (en) | Scraper conveyor inclined chain detection method based on image recognition and control system | |
| CN112801072B (en) | Elevator non-flat-layer door opening fault recognition device and method based on computer vision | |
| CN115953405A (en) | Bridge crack identification method and device for augmented reality equipment | |
| CN115797859A (en) | Crown block hanging iron ladle image identification method and system | |
| CN111127442B (en) | Trolley wheel shaft defect detection method and device | |
| CN114212483A (en) | Scraper conveyor part fault identification method and device based on CV algorithm | |
| CN114596507A (en) | Bridge modeling monitoring method, device, equipment and storage medium | |
| CN109214390B (en) | Fence state detection method and system based on machine vision principle | |
| CN113762783A (en) | Online detection platform for digital industrial products |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |