Coal conveyor belt fault identification method, device and storage medium

Abstract

The invention relates to a method, device and storage medium for identifying faults of a coal conveyor belt, belonging to the field of image recognition technology, and solves the problem that a single monitoring component in the prior art is prone to misjudgment of faults, thereby reducing the accuracy of identifying faults. The device comprises a video terminal above the coal conveyor belt, a video terminal below the coal conveyor belt, a frame, a coal conveyor belt and a video analysis and recognition host; the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt are respectively located above and below the frame and the coal conveyor belt, and the video terminal above the coal conveyor belt is connected to the video terminal below the coal conveyor belt; the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt are both connected to the video analysis and recognition host.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a method, a device and a storage medium for identifying a coal conveyor belt fault. Background Art

[0002] As my country's industrialization process continues to deepen, the demand for energy in the production process continues to increase. As the largest energy resource in my country, coal resources are increasingly being produced. As the most important fuel resource in my country's thermal power generation industry, with the improvement of mechanization level, coal conveyor belts are widely used in ore mining, transportation and processing. However, due to the increase in transportation capacity requirements and the improvement of scientific and technological levels, the load per unit time, the complexity of the environment and the total transportation length requirements of coal conveyor belts are gradually increasing.

[0003] As the core component of the coal conveying system, the coal conveyor belt has the largest contact area with the coal ore. Due to its material and working environment, it is also the most easily damaged component. During the transportation process, coal ore often contains some sharp foreign objects, such as gangue, iron wire and large steel plates. When falling into the belt and during transportation, it will cause destructive physical damage to the belt, such as scratches, failures and deviations. At the same time, due to the harsh operating environment, chemical damage problems such as belt aging and corrosion will also occur. These damage processes will have serious consequences for the coal conveyor belt, threatening the safe and stable operation of the power plant and causing huge economic losses.

[0004] In the prior art, Chinese patent CN116513758A discloses "an intelligent coal conveying monitoring system". Through the installation of components, ash removal components and monitoring components, the system can not only monitor the coal conveyor belt in real time, but also timely and effectively remove dust on the surface of the camera. However, the system mainly uses a single monitoring component to monitor the coal conveyor belt in real time. The monitoring of a single monitoring component is prone to misjudgment of faults, which greatly reduces the accuracy of fault identification and affects the work efficiency of the coal conveyor and the staff.

[0005] In summary, since the prior art mostly uses a single monitoring component to monitor the coal conveyor belt in real time, the single monitoring component is prone to misjudgment of faults, thereby reducing the accuracy of fault identification. Summary of the invention

[0006] The present invention solves the problem that a single monitoring component in the prior art is prone to misjudgment of faults, thereby reducing the accuracy of fault identification.

[0007] The method for identifying a coal conveyor belt fault of the present invention is implemented based on a coal conveyor belt fault identification device and comprises the following steps:

[0008] Step S1, recording the time it takes for the frame and the coal conveyor belt to run one circle;

[0009] Step S2, the video terminal above the coal conveyor belt sends the location information of the suspected fault to the video terminal below the coal conveyor belt, and the video terminal below the coal conveyor belt amplifies the suspected fault identified by the video terminal above the coal conveyor belt and sends it to the video analysis and recognition host for suspected fault determination processing;

[0010] Step S3, if the video analysis and recognition host determines that the suspected fault identified by the video terminal above the coal conveyor belt is a real fault, the operation of step S4 is executed; otherwise, the operation of step S7 is executed;

[0011] Step S4, taking the difference between the time when the video terminal above the coal conveyor belt recognizes the real fault and the time when the video terminal below the coal conveyor belt recognizes the real fault;

[0012] Step S5, calculating the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt that recognize the real fault;

[0013] Step S6, the video analysis and recognition host determines and recognizes the type of the real fault based on the time for the frame and the coal conveyor belt to run one circle, the difference between the time when the video terminal above the coal conveyor belt recognizes the real fault and the time when the video terminal below the coal conveyor belt recognizes the real fault, and the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt to recognize the real fault;

[0014] Step S7, end the operation.

[0015] Further, in one embodiment of the present invention, in step S2, the video analysis and recognition host performs the process of suspected fault determination, specifically:

[0016] The video analysis and recognition host normalizes the height of the minimum rectangle of the suspected fault identified by the video terminal above the coal conveyor belt, and makes a suspected fault judgment based on the normalization result.

[0017] Furthermore, in one embodiment of the present invention, the video analysis and recognition host performs normalization processing on the height of the smallest rectangle of the suspected fault identified by the video terminal above the coal conveyor belt, specifically:

[0018] ;

[0019] in, For the video stream The normalized height value of the frame, is the frame value, For the The height of the frame, is the current frame number calculated, For the i The height of the frame. is the total number of calculation frames;

[0020] The suspected fault determination based on the normalized result is specifically as follows:

[0021] when When the value is >3, the video terminal above the coal conveyor belt identifies the suspected fault as a non-fault;

[0022] when When ≤3, the video terminal above the coal conveyor belt identifies the suspected fault as a real fault.

[0023] Furthermore, in one embodiment of the present invention, the type of the real fault is:

[0024] When 1.2≤ When ≤3, the real fault type is longitudinal tearing;

[0025] When 0.6< When <1.2, the real fault type is uniform crack;

[0026] When 0≤ When ≤0.6, the real fault type is transverse tearing.

[0027] Further, in one embodiment of the present invention, in the step S5, the ratio of the width to height ratio of the minimum rectangle of the real fault identified by the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt is calculated, specifically:

[0028] The height and width of the minimum external rectangle of the real fault recognized by the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt are calculated respectively, and the height and width of the minimum external rectangle of the real fault recognized by the video terminal above the coal conveyor belt and the height and width of the minimum external rectangle of the real fault recognized by the video terminal below the coal conveyor belt are compared to obtain the ratio of the aspect ratios of the minimum external rectangle of the real fault recognized by the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt.

[0029] Further, in one embodiment of the present invention, in the step S6, the video analysis and recognition host determines the type of the real fault based on the time for the frame and the coal conveyor belt to run one circle, the difference between the time when the video terminal above the coal conveyor belt recognizes the real fault and the time when the video terminal below the coal conveyor belt recognizes the real fault, and the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt to recognize the real fault, specifically:

[0030] When the difference between the time when the video terminal above the coal conveyor belt recognizes the real fault and the time when the video terminal below the coal conveyor belt recognizes the real fault is less than 0.5 seconds, the type of the real fault is a through-type fault;

[0031] When the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt identify that the ratio of the width to height of the minimum rectangle circumscribing the real fault is ≥1.1, the type of the real fault is a longitudinal tear crack in a stable walking state;

[0032] When 0.5<the ratio of the width-to-height ratio of the minimum rectangle circumscribed by the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt is<1.2, the type of the real fault is a uniform crack in the stable running state of the belt;

[0033] When the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt identify that the ratio of the width to height of the minimum rectangle circumscribing the real fault is ≤0.5, the type of the real fault is transverse tearing under stable belt movement;

[0034] If there is no time for the video terminal above the coal conveyor belt to identify the real fault, and the time interval between the video terminal below the coal conveyor belt identifying the real fault twice is the time it takes for the rack and the coal conveyor belt to run one circle, then the type of the real fault is a through-type fault;

[0035] If there is no time for the video terminal below the coal conveyor belt to identify the real fault, and the time interval between the video terminal above the coal conveyor belt identifying the real fault twice is the time it takes for the rack and the coal conveyor belt to run one circle, then the type of the real fault is a non-penetration fault;

[0036] If the time interval between the video terminal above the coal conveyor belt identifying the real fault twice, or the time interval between the video terminal below the coal conveyor belt identifying the real fault is less than the time it takes for the frame and the coal conveyor belt to run one circle, then the type of the real fault is a multiple fault.

[0037] Further, in one embodiment of the present invention, the coal conveyor belt fault identification device comprises a video terminal above the coal conveyor belt, a video terminal below the coal conveyor belt, a frame and a coal conveyor belt and a video analysis and identification host;

[0038] The video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt are respectively located above and below the frame and the coal conveyor belt, and the video terminal above the coal conveyor belt is connected to the video terminal below the coal conveyor belt;

[0039] The video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt are both connected to the video analysis and recognition host.

[0040] An electronic device described in the present invention comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0041] Memory, used to store computer programs;

[0042] The processor is used to implement the steps of the coal conveyor belt fault identification method described in any of the above methods when executing the program stored in the memory.

[0043] The present invention provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the coal conveyor belt fault identification method described in any one of the above methods are implemented.

[0044] The present invention solves the problem that a single monitoring component in the prior art is prone to misjudgment of faults, which reduces the accuracy of fault identification. Specific beneficial effects include:

[0045] 1. The coal conveyor belt fault identification method described in the present invention, in the prior art, mostly adopts a single monitoring component to monitor the coal conveyor belt in real time, which makes the single monitoring component prone to misjudgment of faults, thereby reducing the accuracy of fault identification. In order to solve the above technical problems, the present invention coordinates the video terminal above the coal conveyor belt with the video terminal below the coal conveyor belt, and uses the video analysis and identification host to detect coal conveyor belt faults. The technical means overcome the problems of single monitoring angle, lack of detailed analysis and low fault rate in the process of coal conveyor belt fault monitoring, that is, the precise coordination of the video terminal above the coal conveyor belt and the video terminal below the coal conveyor belt is achieved, thereby improving the accuracy of fault identification;

[0046] 2. The coal conveyor belt fault identification method of the present invention uses a video analysis and identification host to make an initial judgment on the suspected fault identified by the video terminal above the coal conveyor belt, and selects the program to be executed according to the judgment result, which can reduce resource utilization;

[0047] 3. The method for identifying the running state of the coal conveyor belt of the present invention calculates the speed and acceleration of the centroid of the calibration points on the frame and the coal conveyor belt, and identifies the running state of the frame and the coal conveyor belt based on the calculation result of the acceleration. This process is easy to operate and easier to implement.

[0048] The coal conveyor belt fault identification method described in the present invention can accurately identify scratches and hidden faults of the frame and the coal conveyor belt, improve and enhance the existing fault identification method, and improve the detection accuracy and speed of the existing fault identification method. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0050] Figure 1 1 is a diagram of a coal conveyor belt fault identification device according to Embodiment 2;

[0051] Among them, 401 is a hopper, 402 is a video terminal above the coal conveyor belt, 403 is a video terminal below the coal conveyor belt, 404 is a frame and a coal conveyor belt, 405 is a video analysis and recognition host, 406 is a display terminal, 407 is an audible and visual alarm system, and 408 is an external control interface. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe various embodiments of the present invention in conjunction with the accompanying drawings. The embodiments described with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be understood as limiting the present invention.

[0053] Embodiment 1: The method for identifying a coal conveyor belt fault described in this embodiment is implemented based on a coal conveyor belt fault identification device, and includes the following steps:

[0054] Step S1, recording the time it takes for the frame and the coal conveyor belt 404 to run one circle;

[0055] Step S2, the video terminal 402 above the coal conveyor belt sends the location information of the suspected fault to the video terminal 403 below the coal conveyor belt, and the video terminal 403 below the coal conveyor belt amplifies the suspected fault identified by the video terminal 402 above the coal conveyor belt and sends it to the video analysis and recognition host 405 for suspected fault determination processing;

[0056] Step S3, if the video analysis and recognition host 405 determines that the suspected fault identified by the video terminal 402 above the coal conveyor belt is a real fault, the operation of step S4 is executed; otherwise, the operation of step S7 is executed;

[0057] Step S4, taking the difference between the time when the video terminal 402 above the coal conveyor belt recognizes the real fault and the time when the video terminal 403 below the coal conveyor belt recognizes the real fault;

[0058] Step S5, calculating the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt that recognize the real fault;

[0059] Step S6, the video analysis and recognition host 405 determines and recognizes the type of the real fault based on the time for the frame and the coal conveyor belt 404 to run one circle, the difference between the time when the video terminal 402 above the coal conveyor belt recognizes the real fault and the time when the video terminal 403 below the coal conveyor belt recognizes the real fault, and the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt to recognize the real fault;

[0060] Step S7, end the operation.

[0061] In this implementation, in step S2, the video analysis and recognition host 405 performs the process of suspected fault determination, specifically:

[0062] The video analysis and recognition host 405 normalizes the height of the smallest circumscribed rectangle of the suspected fault identified by the video terminal 402 above the coal conveyor belt, and makes a suspected fault determination based on the normalization result.

[0063] In this embodiment, the video analysis and recognition host 405 performs normalization processing on the height of the smallest rectangle of the suspected fault identified by the video terminal 402 above the coal conveyor belt, specifically:

[0064] ;

[0065] in, For the video stream The normalized height value of the frame, is the frame value, For the The height of the frame, is the current frame number calculated, For the i The height of the frame. N is the total number of calculation frames;

[0066] The suspected fault determination based on the normalized result is specifically as follows:

[0067] when >3, the video terminal 402 above the coal conveyor belt identifies the suspected fault as a non-fault;

[0068] when When ≤3, the video terminal 402 above the coal conveyor belt recognizes that the suspected fault is a real fault.

[0069] In this implementation manner, the categories of the real faults are:

[0070] When 1.2≤ When ≤3, the real fault type is longitudinal tearing;

[0071] When 0.6< When <1.2, the real fault type is uniform crack;

[0072] When 0≤ When ≤0.6, the real fault type is transverse tearing.

[0073] In this embodiment, in step S5, the ratio of the width to height ratio of the minimum rectangle of the real fault circumscribed by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt is calculated, specifically:

[0074] The height and width of the minimum external rectangle of the real fault recognized by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt are calculated respectively, and the height and width of the minimum external rectangle of the real fault recognized by the video terminal 402 above the coal conveyor belt and the height and width of the minimum external rectangle of the real fault recognized by the video terminal 403 below the coal conveyor belt are compared to obtain the ratio of the aspect ratios of the minimum external rectangle of the real fault recognized by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt.

[0075] In this embodiment, in step S6, the video analysis and identification host 405 determines the type of real fault based on the time for the frame and the coal conveyor belt 404 to run one circle, the difference between the time when the video terminal 402 above the coal conveyor belt identifies the real fault and the time when the video terminal 403 below the coal conveyor belt identifies the real fault, and the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt to identify the real fault, specifically:

[0076] When the difference between the time when the video terminal 402 above the coal conveyor belt recognizes the real fault and the time when the video terminal 403 below the coal conveyor belt recognizes the real fault is less than 0.5 seconds, the type of the real fault is a through-type fault;

[0077] When the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt identify that the ratio of the width to height ratio of the minimum rectangle circumscribing the real fault is ≥1.1, the type of the real fault is a longitudinal tear crack in a stable walking state;

[0078] When 0.5 < the ratio of the width-to-height ratio of the minimum rectangle circumscribed by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt < 1.2, the type of the real fault is a uniform crack in the stable running state of the belt;

[0079] When the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt identify that the ratio of the width to height ratio of the minimum rectangle circumscribing the real fault is ≤0.5, the type of the real fault is the transverse tearing of the belt under stable running;

[0080] If there is no time for the video terminal 402 above the coal conveyor belt to identify the real fault, and the time interval between the video terminal 403 below the coal conveyor belt identifying the real fault twice is the time for the rack and the coal conveyor belt 404 to run one circle, then the type of the real fault is a through-type fault;

[0081] If there is no time for the video terminal 403 below the coal conveyor belt to identify the real fault, and the time interval between the video terminal 402 above the coal conveyor belt identifying the real fault twice is the time for the rack and the coal conveyor belt 404 to run one circle, then the type of the real fault is a non-penetrating fault;

[0082] If the time interval between the video terminal 402 above the coal conveyor belt identifying the real fault twice, or the time interval between the video terminal 403 below the coal conveyor belt identifying the real fault is less than the time it takes for the frame and the coal conveyor belt 404 to run one circle, then the type of the real fault is a multiple fault.

[0083] In the prior art, a single monitoring component is mainly used to monitor the coal conveyor belt in real time. The monitoring of a single monitoring component is prone to misjudgment of faults, which greatly reduces the accuracy of fault identification.

[0084] In order to solve the above technical problems, this embodiment designs a coal conveyor belt fault identification method, which includes the following steps:

[0085] Step S1, obtaining the rotational angular velocity values ​​of the frame and the coal conveyor belt 404, and obtaining the running speed of the frame and the coal conveyor belt 404 and the time T0 for one circle of movement through the driving roller diameter and the rotational angular velocity value;

[0086] Step S2, when the video terminal 402 above the coal conveyor belt identifies a suspected fault, it will send the location information to the video terminal 403 below the coal conveyor belt, and establish a connection relationship between the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt. Finally, the video terminal 403 below the coal conveyor belt needs to amplify the suspected fault and send it to the video analysis and recognition host 405 for suspected fault determination processing, so as to accurately obtain relevant information such as the suspected fault location and direction;

[0087] Step S3, before the video analysis and recognition host 405 determines the video frame, no matter what type of suspected fault the frame and coal conveyor belt 404 is, the suspected fault in the video frame must move quickly in a very short time. For the transverse tear, longitudinal tear and uniform crack of the frame and coal conveyor belt 404, the height change value is the largest. The height of the suspected fault phenomenon is expressed by the height value of the circumscribed minimum rectangle. In order to avoid the height difference generated during the movement of the suspected fault phenomenon, the height is used as the main analysis value for normalization, and the normalization is expressed according to the following calculation method:

[0088] ;

[0089] in, For the video stream The normalized height value of the frame, is the frame value, For the The height of the frame, is the current frame number calculated, For the i The height of the frame. N is the total number of calculation frames;

[0090] according to Value, can be used to determine whether the suspected fault is a real fault:

[0091] when >3, the video terminal 402 above the coal conveyor belt identifies the suspected fault as a non-fault;

[0092] when When ≤3, the video terminal 402 above the coal conveyor belt identifies the suspected fault as a real fault;

[0093] When the video terminal 402 above the coal conveyor belt identifies that the suspected fault is a real fault, the type of the real fault can be further determined, specifically:

[0094] When 1.2≤ When ≤3, the real fault type is longitudinal tearing;

[0095] When 0.6< When <1.2, the real fault type is uniform crack;

[0096] When 0≤ When ≤0.6, the real fault type is transverse tearing;

[0097] According to this determination method, it is possible to preliminarily determine the type of real fault identified by the video terminal 402 above the coal conveyor belt;

[0098] If the video analysis and recognition host 405 determines that the suspected fault identified by the video terminal 402 above the coal conveyor belt is a real fault, in order to further determine the type of the real fault identified by the video terminal 402 above the coal conveyor belt, the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt start to cooperate with each other, and then the operation of step S4 is executed, otherwise, the operation of step S7 is executed;

[0099] Step S4, obtaining the time when the video terminal 402 above the coal conveyor belt identifies the real fault as T1, and the time when the video terminal 403 below the coal conveyor belt identifies the real fault as T2, and calculating the time difference ∆T=T1-T2 when the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt identify the real fault;

[0100] Step S5: To determine the type of the real fault of the frame and the coal conveyor belt 404, the aspect ratio is also needed. The four vertices of the smallest rectangle of the real fault identified by the video terminal 402 above the coal conveyor belt are defined as follows: , , and , then the height of the minimum rectangle surrounding the real fault identified by the video terminal 402 above the coal conveyor belt is and width , can be calculated by the following formula:

[0101] ;

[0102] ;

[0103] Similarly, the four vertices of the minimum rectangle of the real fault circumscribed by the video terminal 403 below the coal conveyor belt are defined as , , and , then the video terminal 403 below the coal conveyor belt recognizes the height of the minimum rectangle surrounding the real fault and width , can be calculated by the following formula:

[0104] ;

[0105] ;

[0106] The video streams of the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt are The width and height ratio of the minimum rectangle enclosing the frame is expressed using the following formula:

[0107] ;

[0108] ;

[0109] in, The video stream of the video terminal 402 above the coal conveyor belt is The ratio of the width and height of the minimum rectangle enclosing the frame, The video stream of the video terminal 403 below the coal conveyor belt is The ratio of the width and height of the smallest rectangle enclosing the frame;

[0110] The ratio of the width to height ratio of the minimum rectangle of the real fault identified by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt is established as follows:

[0111] ;

[0112] in, The ratio of the width to height ratio of the minimum rectangle enclosed by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt to identify the real fault;

[0113] Step S6, the video analysis and recognition host 405 determines and recognizes the type of the real fault based on the time for the frame and the coal conveyor belt 404 to run one circle, the difference between the time when the video terminal 402 above the coal conveyor belt recognizes the real fault and the time when the video terminal 403 below the coal conveyor belt recognizes the real fault, and the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt to recognize the real fault;

[0114] Specifically:

[0115] When the difference ∆T between the time when the video terminal 402 above the coal conveyor belt recognizes the real fault and the time when the video terminal 403 below the coal conveyor belt recognizes the real fault is less than 0.5 seconds, it can be determined that the type of the real fault is a through-type fault;

[0116] When the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt recognize the ratio of the width to height of the minimum rectangle surrounding the real fault When ≥1.1, it can be determined that the type of real fault is a longitudinal tear crack under stable walking state;

[0117] When 0.5 < the ratio of the width to height of the minimum rectangle of the real fault identified by the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt When the value is less than 1.2, it can be determined that the real fault type is a uniform crack in the belt under stable running state;

[0118] When the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt recognize the ratio of the width to height of the minimum rectangle surrounding the real fault When ≤0.5, it can be determined that the real fault type is transverse tearing under stable belt running;

[0119] If the time T1 when the video terminal 402 above the coal conveyor belt recognizes the real fault does not occur, and the interval between the time T2 when the video terminal 403 below the coal conveyor belt recognizes the real fault is the time T0 when the rack and the coal conveyor belt 404 run one circle, there is coal seam obstruction, and it can be determined that the type of the real fault is a through-type fault;

[0120] If the time T2 when the video terminal 403 below the coal conveyor belt recognizes the real fault does not occur, and the interval between the time T1 when the video terminal 402 above the coal conveyor belt recognizes the real fault twice is the time T0 when the rack and the coal conveyor belt 404 run one circle, then it can be determined that the type of the real fault is a non-penetrating fault, or further manual identification is required;

[0121] If the interval between the time T1 when the video terminal 402 above the coal conveyor belt recognizes the real fault twice, or the time T2 when the video terminal 403 below the coal conveyor belt recognizes the real fault is less than the time T0 when the rack and the coal conveyor belt 404 run one circle, then it can be determined that the type of the real fault is a multiple fault;

[0122] Step S7, end the operation;

[0123] Based on the data results of the video analysis recognition host 405, the data are output through the display terminal 406 and the sound and light alarm system 407 respectively, and the corresponding general control signal is output at the external control interface 408 to perform corresponding operations on the controlled end equipment. For example, in the event of a fault, the belt motor is connected to perform a shutdown operation to avoid damage to the equipment caused by continued operation.

[0124] Therefore, this embodiment uses the video terminal 402 above the coal conveyor belt to make a preliminary judgment on the suspected fault. If the suspected fault is determined to be a real fault, the cooperation between the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt will be started. This process improves work efficiency. In the process of coordinated work between the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt, it is necessary to consider that the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt have different positions and different installation heights and angles, and their judgment values ​​for the same fault are different. In order to avoid the problem of different judgment values ​​for the same fault, this embodiment uses the video analysis and recognition host 405 to determine the suspected fault identified by the video terminal 402 above the coal conveyor belt, and the cooperation between the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt to determine the real fault. Two judgment methods are adopted to achieve the purpose of more efficient and accurate judgment of suspected faults, thereby solving the problem that a single monitoring component in the prior art is prone to misjudgment of faults, thereby reducing the accuracy of fault identification.

[0125] Embodiment 2: This embodiment further limits the method for identifying a fault of a coal conveyor belt described in Embodiment 1. The coal conveyor belt fault identification device includes a video terminal 402 above the coal conveyor belt, a video terminal 403 below the coal conveyor belt, a frame and a coal conveyor belt 404, and a video analysis and identification host 405.

[0126] The video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt are respectively located above and below the frame and the coal conveyor belt 404, and the video terminal 402 above the coal conveyor belt is connected to the video terminal 403 below the coal conveyor belt;

[0127] The video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt are both connected to the video analysis and recognition host 405.

[0128] In the prior art, a single monitoring component is often used to monitor the coal conveyor belt in real time. The single monitoring component is prone to misjudgment of fault identification, thereby reducing the accuracy of fault identification.

[0129] Based on the above technical issues, such as Figure 1 As shown, this embodiment designs a coal conveyor belt fault identification device, which includes a hopper 401, a video terminal 402 above the coal conveyor belt, a video terminal 403 below the coal conveyor belt, a frame and a coal conveyor belt 404, a video analysis and identification host 405, a display terminal 406, an audible and visual alarm system 407 and an external control interface 408;

[0130] The hopper 401 is located above the frame and the coal conveyor belt 404. In the movement direction of the coal conveyor belt of the frame and the coal conveyor belt 404, a video terminal 402 above the coal conveyor belt and a video terminal 403 below the coal conveyor belt are respectively arranged above and below the frame and the coal conveyor belt 404, and the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt are symmetrically arranged. The video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt are connected by a network cable. The video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt are both batch-input into the video analysis and recognition host 405 through the switch. The video analysis and recognition host 405 analyzes and processes the input video information stream, and the analysis results are input into the display terminal 406. At the same time, the sound and light alarm system 407 is used to give sound and light prompts to some of the information on the identified faults. For the information results on the identified faults that require equipment control, the corresponding control signals are output at the external control interface 408.

[0131] The device overcomes the problems of single monitoring angle, lack of detailed analysis and low fault rate in fault determination during coal conveyor belt fault monitoring by utilizing the mutual cooperation between the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt, and by using the video analysis and identification host 405 to detect coal conveyor belt faults. The device achieves the purpose of mutual cooperation between the video terminal 402 above the coal conveyor belt and the video terminal 403 below the coal conveyor belt, thereby realizing accurate judgment of identified faults, improving the accuracy of fault identification and reducing the error rate.

[0132] Embodiment 3: The method for identifying the running state of a coal conveyor belt described in this embodiment is implemented by using the coal conveyor belt fault identification device described in embodiment 2, and includes the following steps:

[0133] Step S10, setting calibration points on the frame and the coal conveyor belt 404, the video terminal 403 below the coal conveyor belt observes the calibration points, and records the centroids of the calibration points of two adjacent frames in adjacent video streams;

[0134] Step S20, the video analysis and recognition host 405 calculates the velocity and acceleration in the x-axis and y-axis directions based on the centroid of the calibration point;

[0135] In step S30, the video analysis recognition host 405 recognizes the transport status of the frame and the coal conveyor belt 404 based on the calculated acceleration of the centroid of the calibration point.

[0136] In this embodiment, the coal conveyor belt fault identification device described in the second embodiment can also be applied to the coal conveyor belt operation status identification method, including the following steps:

[0137] Step S10, for the abnormal state of the unstable walking state, the transport speed of the frame and the coal conveyor belt 404 is uneven, that is, there is acceleration. The center of mass is the center of the non-cavity object. When the frame and the coal conveyor belt 404 move, their center of mass will also be displaced accordingly. For the eccentric motion and belt slipping motion process, the center of mass changes in the x-axis and y-axis directions;

[0138] Set the video terminal 403 below the coal conveyor belt to observe the calibration points on the rack and the coal conveyor belt 404, and define the centroid of the calibration points of two adjacent frames in adjacent video streams as and , define the velocities of the center of mass of the calibration point in the x-axis and y-axis directions respectively:

[0139] ;

[0140] ;

[0141] in, is the velocity of the center of mass of the calibration point in the x-axis direction, is the velocity of the center of mass of the calibration point in the y-axis direction, is the time between the centroids of the calibration points of two adjacent frames;

[0142] Step S20, you can establish the first The acceleration values ​​of the center of mass of the frame calibration point on the x-axis and y-axis:

[0143] ;

[0144] ;

[0145] in, For the The acceleration value of the center of mass of the frame calibration point on the x-axis, For the The acceleration value of the center of mass of the frame calibration point on the y-axis;

[0146] Step S30, by obtaining the acceleration values ​​of the centroid of the calibration point on the x-axis and the y-axis, it is possible to effectively distinguish whether the running state of the frame and the coal conveyor belt 404 is longitudinal jamming, slipping or belt deviation;

[0147] when ≥0.1, and =0, the running state of the frame and the coal conveying belt 404 can be determined as stuck and slipping;

[0148] when = 0, and When ≥0.1, the running state of the frame and the coal conveyor belt 404 can be determined as lateral deviation;

[0149] when ≥0.1, and When ≥0.1, the running state of the frame and the coal conveyor belt 404 can be determined as stuck and deviated;

[0150] Based on the data results of the video analysis recognition host 405, the data are output through the display terminal 406 and the sound and light alarm system 407 respectively, and the corresponding general control signal is output at the external control interface 408 to perform corresponding operations on the controlled end equipment. For example, in the event of a fault, the belt motor is connected to perform a shutdown operation to avoid damage to the equipment caused by continued operation.

[0151] Embodiment 4: An electronic device described in this embodiment includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus;

[0152] Memory, used to store computer programs;

[0153] The processor is used to implement the steps of the coal conveyor belt fault identification method described in Implementation Mode 1 when executing the program stored in the memory.

[0154] Implementation method five: A computer-readable storage medium described in this implementation method stores a computer program, and when the computer program is executed by a processor, the steps of the coal conveyor belt fault identification method described in implementation method one are implemented.

[0155] The above is a detailed introduction to the coal conveyor belt fault identification method, equipment and storage medium proposed in the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for identifying a coal conveyor belt fault, the method being implemented based on a coal conveyor belt fault identification device, and characterized in that: The following steps are involved: Step S1, recording the time it takes for the frame and the coal conveyor belt (404) to run one circle; Step S2, the video terminal (402) above the coal conveyor belt sends the location information of the suspected fault to the video terminal (403) below the coal conveyor belt, and the video terminal (403) below the coal conveyor belt amplifies the suspected fault identified by the video terminal (402) above the coal conveyor belt, and sends it to the video analysis and recognition host (405) for suspected fault determination processing; Step S3, if the video analysis and recognition host (405) determines that the suspected fault identified by the video terminal (402) above the coal conveyor belt is a real fault, the operation of step S4 is executed; otherwise, the operation of step S7 is executed; Step S4, taking the difference between the time when the video terminal (402) above the coal conveyor belt recognizes the real fault and the time when the video terminal (403) below the coal conveyor belt recognizes the real fault; Step S5, calculating the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal (402) above the coal conveyor belt and the video terminal (403) below the coal conveyor belt to identify the real fault; Step S6, the video analysis and recognition host (405) determines and recognizes the type of the real fault based on the time taken for the frame and the coal conveyor belt (404) to run one circle, the difference between the time when the video terminal (402) above the coal conveyor belt recognizes the real fault and the time when the video terminal (403) below the coal conveyor belt recognizes the real fault, and the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal (402) above the coal conveyor belt and the video terminal (403) below the coal conveyor belt to recognize the real fault; Step S7, end the operation; In the step S2, the video analysis and recognition host (405) performs a process of determining a suspected fault, specifically: The video analysis and recognition host (405) normalizes the height of the smallest rectangle surrounding the suspected fault identified by the video terminal (402) above the coal conveyor belt, and determines the suspected fault based on the normalization result; The video analysis and recognition host (405) performs normalization processing on the height of the smallest rectangle of the suspected fault identified by the video terminal (402) above the coal conveyor belt, specifically: Among them, R k is the normalized height value of the kth frame in the video stream, k is the frame value, h k is the height of the kth frame, i is the current frame number calculated, and h i is the height value of the i-th frame, and N is the total number of calculated frames; The suspected fault determination based on the normalized result is specifically as follows: When R k >3, the video terminal (402) above the coal conveyor belt identifies the suspected fault as a non-fault; When R k When ≤3, the video terminal (402) above the coal conveyor belt recognizes that the suspected fault is a real fault.

2. The method for identifying coal conveyor belt faults according to claim 1, characterized in that: The types of real faults described are: When 1.2≤R k When ≤3, the real fault type is longitudinal tearing; When 0.6<R k When <1.2, the real fault type is uniform crack; When 0≤R k When ≤0.6, the real fault type is transverse tearing.

3. The method for identifying coal conveyor belt faults according to claim 1, characterized in that: In the step S5, the ratio of the width to height ratio of the minimum rectangle circumscribed by the video terminal (402) above the coal conveyor belt and the video terminal (403) below the coal conveyor belt that recognizes the real fault is calculated, specifically: The height and width of the minimum external rectangle of the real fault identified by the video terminal (402) above the coal conveyor belt and the video terminal (403) below the coal conveyor belt are calculated respectively, and the height and width of the minimum external rectangle of the real fault identified by the video terminal (402) above the coal conveyor belt are compared with the height and width of the minimum external rectangle of the real fault identified by the video terminal (403) below the coal conveyor belt to obtain the ratio of the aspect ratios of the minimum external rectangle of the real fault identified by the video terminal (402) above the coal conveyor belt and the video terminal (403) below the coal conveyor belt.

4. The method for identifying coal conveyor belt faults according to claim 1, characterized in that: The coal conveyor belt fault identification device comprises a video terminal (402) above the coal conveyor belt, a video terminal (403) below the coal conveyor belt, a frame and a coal conveyor belt (404) and a video analysis and identification host (405); The video terminal (402) above the coal conveyor belt and the video terminal (403) below the coal conveyor belt are respectively located above and below the frame and the coal conveyor belt (404), and the video terminal (402) above the coal conveyor belt is connected to the video terminal (403) below the coal conveyor belt; The video terminal (402) above the coal conveyor belt and the video terminal (403) below the coal conveyor belt are both connected to the video analysis and recognition host (405).

5. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the coal conveyor belt fault identification method described in any one of claims 1-4 when executing the program stored in the memory.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for identifying a coal conveyor belt fault according to any one of claims 1 to 4 are implemented.

Images