A coal overflow identification system based on marker edge detection for a coal conveying system

Abstract

The application discloses a coal overflow identification system of a coal conveying system based on marker edge detection, which comprises a PLC module, a computing server module, a video monitoring module, a belt module, a display interface module and an emergency rescue module, wherein the six modules are sequentially connected, the PLC module controls the belt operation, the video monitoring module transmits monitoring to the server module, when the server detects that the blockage occurs, the display interface module displays the alarm level, and the emergency rescue module is informed to perform corresponding rescue treatment. The application can process more than 10 camera images by adding only one computer, has low cost and good effect, can realize early warning in a place with clear camera and suitable environment, and can realize synchronous alarm even in a harsh environment due to the use of a certain value of the threshold. The operation personnel can reduce the time and energy spent on monitoring, thereby greatly saving the labor cost of the enterprise.

Description

Technical Field

[0001] This invention relates to the field of video safety recognition technology for coal conveyor belt transportation, and in particular to a coal spillage recognition system for coal conveying systems based on marker edge detection. Background Technology

[0002] The coal conveyor belt systems in thermal power plants are long, and operators typically work from the control room, with no on-site staff. They assess the conveyor's condition based on camera feeds. During production, wet or sticky coal often accumulates on the walls of the feed inlet, clogging it completely. The belt continues to run, eventually causing a large amount of coal to overflow. Although each conveyor belt has a coal blockage switch at its head, the varying types of coal mean that particularly wet coal can directly clog the switch. Overflowing coal requires manual cleaning, significantly increasing the workload for operators. To prevent overflow, operators must constantly monitor the head of each conveyor belt. Even so, the time from the onset of overflow to actual spillage is only a few seconds, and every minute delayed stopping the belt results in an additional ten tons of coal spilling. This is especially problematic during night shifts, when the environment is dark and operators are fatigued, increasing the risk of overflows.

[0003] Relying on manual identification of coal spills, even the most diligent operators are bound to make oversights. Furthermore, existing alarm devices cannot accurately detect coal blockages, causing operators to spend a lot of time on this simple task. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the problems existing in the above and / or existing coal spill identification systems based on marker edge detection in coal conveying systems, this invention is proposed.

[0006] Therefore, the problem this invention aims to solve is how to provide a method that uses a camera positioned above the conveyor belt to intelligently determine whether the material inlet is blocked, replacing manual intervention with image recognition. This addresses the low accuracy of current blockage alarms on coal conveyor belts in thermal power plants, reducing coal spillage and lowering the workload of on-duty operators.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a coal spillage identification system for a coal conveying system based on marker edge detection, comprising a PLC module, a computing server module, a video monitoring module, a belt conveyor module, a display interface module, and an emergency rescue module;

[0008] The PLC module is the system's control module, used for adjusting the system's belt speed.

[0009] The computing server module is the system's computing module, used for saving monitoring videos and recording the PLC's operating status.

[0010] The video monitoring module is a video recording module for the belt, used to update the real-time status of the belt and store the previous monitoring videos of the belt in the computing server module.

[0011] The belt conveyor module is a belt operation module used for coal transportation, and a two-level alarm mechanism is set on the belt.

[0012] The display interface module transmits a corresponding signal to the belt conveyor module when an alarm problem occurs, so that the personnel on duty of the emergency rescue module can quickly understand the belt fault area and the current video monitoring status of the belt fault area.

[0013] As a preferred embodiment of the coal spill identification system for a coal conveying system based on marker edge detection described in this invention, the system operation flow is as follows:

[0014] The belt is started via the PLC module, and the PLC module transmits the operating status to the computer service module.

[0015] After the computer service module reads the belt start / stop signal change from the PLC module, it sends the power-on signal to the video monitoring module. After the computer service module reads the signal, it models the video for the first ten seconds of the video. Each alarm position gets an initial state. During real-time operation, the real-time value is compared with the initial value. If it exceeds the set allowable value range, it is considered that the alarm level has been triggered.

[0016] When the alarm state is triggered for 3 or more consecutive frames, the corresponding alarm level will be triggered.

[0017] When a Level 1 alarm is triggered, a warning message will appear on the display interface module. When a Level 2 alarm is triggered, the interlocking PLC system will stop the conveyor belt.

[0018] As a preferred embodiment of the coal spillage identification system for a coal conveying system based on marker edge detection described in this invention, the belt module is configured with a two-level alarm mechanism, wherein the first-level alarm is set inside the material drop head cover and the second-level alarm is set outside the belt head cover. The first level represents a warning of an abnormal state, and the second level represents that coal has spilled.

[0019] As a preferred embodiment of the coal overflow identification system for a coal conveying system based on marker edge detection described in this invention, the method for determining the occurrence of a fault in the coal overflow identification system is to compare the overlap rate between the real-time processing matrix and the model matrix. When this overlap rate is less than 71%, it is considered that coal blockage has occurred, and an alarm is triggered.

[0020] The model matrix is ​​the belt recognition matrix under normal conditions;

[0021] The processing matrix is ​​a processed real-time monitoring video matrix, and its processing method is as follows:

[0022] After acquiring the camera image, the first step is to convert the image to grayscale, transforming the three-channel image into a single-channel image.

[0023] Vertical edges are detected by using a defined convolution kernel, and a convolution operation is performed on the image matrix.

[0024] The processed matrix after convolution is then subjected to binarization filtering to filter out areas with blurred edges and extract areas with clear boundaries. Binarization filtering involves assigning a value of 0 to pixels with grayscale values ​​below a threshold and assigning a value of 1 to pixels with grayscale values ​​above the threshold.

[0025] The processing matrices from the past 10 seconds are superimposed, and a probability distribution filter is applied to each point in the matrix. Points that appear less than 80% of the time within 100 frames are deleted, while points that appear more than 80% of the time are retained, thus generating a final processing matrix.

[0026] As a preferred embodiment of the coal spillage identification system for a coal conveying system based on marker edge detection described in this invention, the belt conveyor module is considered to be operating normally when the overlap rate between the processing matrix and the model matrix is ​​higher than 71%.

[0027] When the overlap rate between the processing matrix of the primary marker area and the model matrix is ​​less than 71%, it is considered that the belt module is blocked in coal, triggering the primary alarm state.

[0028] When the Level 1 alarm state is triggered for 3 consecutive seconds, the Level 1 alarm will be triggered, and a warning prompt will appear on the display interface module. The duty personnel of the emergency rescue module can observe the area of ​​the Level 1 alarm in the belt module and monitor it in real time through the display interface module.

[0029] When the overlap rate between the secondary marker area processing matrix and the model matrix is ​​less than 71%, it is considered that the belt module is experiencing coal blockage, triggering a secondary alarm state.

[0030] When the level 2 alarm state is triggered for 3 consecutive seconds, the level 2 alarm is triggered, and the display interface module sends a stop belt operation signal to the PLC module, and the PLC module stops the belt operation.

[0031] As a preferred embodiment of the coal spillage identification system for a coal conveying system based on marker edge detection described in this invention, the binarization filtering process is performed by Gaussian filtering for noise reduction.

[0032] As a preferred embodiment of the coal spillage identification system for a coal conveying system based on marker edge detection described in this invention, wherein: a primary alarm marker and a secondary alarm marker are set in the belt conveyor module;

[0033] The method for placing alarm markers involves using the PLC's belt start / stop recordings to locate coal blockage recordings in the video recorder. Multi-level markers are then deployed in areas with a history of frequent coal blockages. Since belt operation safety is of paramount importance, a two-level alarm mechanism is implemented.

[0034] As a preferred embodiment of the coal spillage identification system for a coal conveying system based on marker edge detection described in this invention, the video monitoring module consists of cameras with storage capacity that capture real-time images of multiple areas of the conveyor belt module.

[0035] A computer device includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of the system described above.

[0036] A computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the system described above.

[0037] The beneficial effects of this invention are that it solves the long-standing problem of coal blockage in coal conveying systems, transforming post-incident cleanup into proactive alarms. Most industrial systems have monitoring cameras installed at the head of the conveyor belts. This invention can process images from more than 10 cameras with just one additional computer, achieving good results at a lower cost. Proactive alarms can be triggered in areas with clear camera feeds and suitable environmental conditions. Because the threshold values ​​are fixed, synchronous alarms can be triggered even in harsh environments. This reduces the time and effort required for operators to monitor the system, significantly saving on labor costs for enterprises. Attached Figure Description

[0038] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0039] Figure 1 This is a structural diagram of a coal spillage identification system for a coal conveying system based on marker edge detection, as shown in Example 1.

[0040] Figure 2 This is a screenshot of a coal spill identification system for a coal conveying system based on marker edge detection, as shown in Example 1.

[0041] Figure 3 This is a belt conveyor early warning diagram for a coal spill identification system based on marker edge detection in Example 2.

[0042] Figure 4 This is a belt blockage diagram of a coal spillage identification system based on marker edge detection in Example 2.

[0043] Figure 5 The left side shows a preset matrix diagram of a coal spillage identification system for a coal conveying system based on marker edge detection in Example 2. Figure 5 The right side shows a real-time matrix diagram of a coal spillage identification system based on marker edge detection in a coal conveying system, as described in Example 2.

[0044] Figure 6 This is a threshold setting diagram for a coal spillage identification system based on marker edge detection in a coal conveying system, as shown in Example 2. Detailed Implementation

[0045] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0046] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0048] Example 1

[0049] Reference Figure 1 This is the first embodiment of the present invention, which provides a coal spill identification system for a coal conveying system based on marker edge detection. The coal spill identification system for a coal conveying system based on marker edge detection includes...

[0050] As shown Figure 1100 PLC modules, 200 computing server modules, 300 video monitoring modules, 400 belt conveyor modules, 500 display interface modules, and 600 emergency rescue modules;

[0051] PLC module 100 is the system's control module, used for adjusting the system's belt speed.

[0052] The computing server module 200 is the system's computing module, used for saving monitoring videos and recording the PLC's operating status.

[0053] The video monitoring module 300 is a video recording module for the belt, used to update the real-time status of the belt and store the previous monitoring videos of the belt in the computing server module 200.

[0054] The belt conveyor module 400 is a belt conveyor operating module used for coal transportation, and it is equipped with a two-level alarm mechanism on the belt.

[0055] When the belt conveyor module 400 experiences an alarm, the display interface module 500 transmits a corresponding signal to the display interface module 500, allowing the on-duty personnel of the emergency rescue module 600 to quickly understand the belt fault area and the current video monitoring status of the belt fault area.

[0056] The system operation process is as follows:

[0057] The belt is started by the PLC module 100, and the PLC module 100 transmits the operating status to the computer service module 200.

[0058] After the computer service module 200 reads the belt start / stop signal change from the PLC module 100, it sends the power-on signal to the video monitoring module 300. After reading the signal, the computer service module 200 models the video for the first ten seconds of the video. Each alarm position gets an initial state. During real-time operation, the real-time value is compared with the initial value. If it exceeds the set allowable value range, it is considered that the alarm level has been triggered.

[0059] When the alarm state is triggered for 3 or more consecutive frames, the corresponding alarm level will be triggered.

[0060] When a Level 1 alarm is triggered, the display module 500 will show a warning message. When a Level 2 alarm is triggered, the interlocking PLC system will stop the conveyor belt.

[0061] The belt conveyor module 400 is equipped with a two-level alarm mechanism. The first-level alarm is set inside the feed head cover, and the second-level alarm is set outside the belt head cover. The first level indicates an abnormal state, and the second level indicates that coal has overflowed.

[0062] In the coal spill detection of the coal conveying system, the method for determining the occurrence of faults is to compare the overlap rate between the real-time processing matrix and the model matrix. When this overlap rate is less than 71%, it is considered that there is a coal blockage and an alarm is triggered.

[0063] The model matrix is ​​the belt recognition matrix under normal conditions;

[0064] The processing matrix is ​​a processed real-time monitoring video matrix; its processing method is...

[0065] After acquiring the camera image, the first step is to convert the image to grayscale, transforming the three-channel image into a single-channel image.

[0066] Vertical edges are detected by using a defined convolution kernel, and a convolution operation is performed on the image matrix.

[0067] The processed matrix after convolution is then subjected to binarization filtering to filter out areas with blurred edges and extract areas with clear boundaries. Binarization filtering involves assigning a value of 0 to pixels with grayscale values ​​below a threshold and assigning a value of 1 to pixels with grayscale values ​​above the threshold.

[0068] The processing matrices from the past 10 seconds are superimposed, and a probability distribution filter is applied to each point in the matrix. Points that appear less than 80% of the time within 100 frames are deleted, while points that appear more than 80% of the time are retained, thus generating a final processing matrix.

[0069] When the overlap rate between the processing matrix and the model matrix is ​​higher than 71%, the belt module 400 is considered to be operating normally.

[0070] When the overlap rate between the processing matrix of the primary marker area and the model matrix is ​​less than 71%, it is considered that the belt module 400 is experiencing coal blockage, triggering a primary alarm state.

[0071] When the Level 1 alarm state is triggered for 3 consecutive seconds, the Level 1 alarm is triggered, the display interface module 500 displays a warning prompt, and the duty personnel of the emergency rescue module 600 can observe the area of ​​the Level 1 alarm in the belt module 400 and real-time monitoring through the display interface module 500.

[0072] When the overlap rate between the secondary marker area processing matrix and the model matrix is ​​less than 71%, it is considered that the belt module 400 has experienced coal blockage, triggering a secondary alarm state.

[0073] When the level 2 alarm state is triggered for 3 consecutive seconds, the level 2 alarm is triggered, and the display interface module 500 sends a stop belt operation signal to the PLC module 100, and the PLC module 100 stops the belt operation.

[0074] Example 2

[0075] The second embodiment of the present invention differs from the first embodiment in that it further includes:

[0076] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0077] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0078] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0079] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0080] Example 3

[0081] Reference Figures 2 to 4 This is the third embodiment of the present invention, which differs from the previous two embodiments in that: this embodiment is a factory case based on the coal spillage identification system of the coal conveying system based on marker edge detection.

[0082] At 05:36:31 on August 9, 2022, a coal blockage occurred on the 3C conveyor belt. Figures 2 to 4 The process is explained.

[0083] Calibration process:

[0084] 1. The primary alarm setting for this belt is a white paint mark inside the hood, and the secondary alarm setting is the hood frame. Its structure is as follows: Figure 2 As shown in the center.

[0085] Usage process:

[0086] 1. After the operator starts the 3C conveyor belt on the operating interface, the PLC sends a signal to the coal plow and the SIS system.

[0087] 2. The identification server reads that the 3C belt has started, determines that the 3C belt has started running, and then connects to the camera of the video surveillance system.

[0088] 3. During the first ten seconds of belt conveyor operation, there will be no coal at the feed inlet, indicating an unloaded state. In this unloaded state, an image processing algorithm is used to derive an initial value, such as... Figure 3 As shown.

[0089] 4. The image is then processed in real time to obtain a real-time reference value. When the real-time reference value differs too much from the initial value, a level one alarm is triggered first.

[0090] 5. After a Level 1 alarm is triggered, the alarm and screenshot records are sent to the front-end interface for display, such as... Figure 4 As shown.

[0091] 6. When the level 2 alarm is triggered, a signal is sent to the PLC to forcibly stop the belt operation.

[0092] Example 4

[0093] Reference Figure 5 This is the fourth embodiment of the present invention, which differs from the previous three embodiments in that it provides a description of the algorithm.

[0094] Since images are stored in a matrix format in a computer, they are referred to as image matrices during processing, and the result after processing is called a processing matrix.

[0095] After acquiring the camera image, the image is first converted to grayscale, transforming the three-channel image into a single-channel image.

[0096] Vertical edges are detected by using a predefined convolution kernel, such as fil = [[1, 0, -1], [1, 0, -1], [1, 0, -1]]. The image matrix is ​​then convolved with this kernel.

[0097] Convolution: Project the center position of the convolution kernel onto each pixel of the image matrix. For example, if a 3x3 convolution kernel is projected onto the original image, there will be 9 overlapping numbers. Multiply the value of the original image matrix at the corresponding position by the value of the convolution kernel, and then add the nine values ​​to get the processed value of that pixel position in the original image.

[0098] The processed matrix after convolution is then subjected to binarization filtering to filter out areas with blurred edges and extract areas with clear boundaries. Binarization filtering assigns a value of 0 to pixels with grayscale values ​​below a threshold and a value of 1 to pixels with grayscale values ​​above the threshold. Convolution is performed at position 186 in the original image: 156*1 + 254*1 + 25*1 + 200*0 + 186*0 + 10*0 - 162*1 - 110*1 - 58*1 = 105

[0099] The processing matrices from the past 10 seconds are superimposed, and a probability distribution filter is applied to each point in the matrix. For example, points that appear less than 80% of the time within 100 frames are deleted, while points that appear more than 80% of the time are retained. This generates a final processing matrix. Figure 5 As shown on the left.

[0100] 1. The model matrix is ​​now complete. The same processing is then applied to each frame of the real-time image to obtain the real-time processing matrix, as shown below. Figure 5 As shown on the right.

[0101] 2. Compare the overlap rate between the real-time processing matrix and the model matrix. When the overlap rate is lower than a threshold, it is considered that coal blockage has occurred, and an alarm is triggered.

[0102] Example 5

[0103] Reference Figure 6The fifth embodiment of the present invention differs from the previous four embodiments in that it provides an explanation of the calculation of the threshold.

[0104] This invention sets five values: the alarm state must last for 3 seconds, the matrix processing must be superimposed within 10 seconds, the matrix frame count must be 100 frames, and the overlap rate between the processing matrix and the model matrix is ​​less than 71%, with less than 80% of the points and secondary markers removed.

[0105] Of these five numerical settings, alarm status and matrix processing are common knowledge and have not been innovatively designed.

[0106] The requirement of 100 frames for the matrix frame count is determined by the marker area processing of this invention. In the original state, 25 matrix frames are required for judgment. However, since this invention is a secondary marker area processing matrix, the number of matrix frames for judgment needs to be increased fourfold to achieve two alarm judgments.

[0107] The reason why less than 80% of the points in the image need to be deleted is due to the judgment of the PLC system and the nature of the belt. For blockage, a blockage area exceeding 70% of the original passage area is generally considered to be a blockage. However, since the PLC system needs a certain amount of time to make a judgment and feedback, and the belt has a certain amount of friction for transporting coal, it is necessary to delete less than 80% of the points to form the final matrix. Only in this way can the fault tolerance and accuracy of the standard matrix be proven. Otherwise, it is easy to ignore non-blockage situations caused by friction and certify blockages, or blockages may not be judged in time, resulting in unnecessary losses.

[0108] Finally, regarding the threshold design, this invention implemented multiple threshold settings, including 50% to 80%. When the overlap rate is below 50%, there is no blockage and no judgment is needed. When the overlap rate exceeds 80%, blockage has already occurred, and judgment has no practical effect. Therefore, fault accuracy is determined based on these values. After data evaluation, the highest accuracy, reaching 100%, was achieved when the threshold was set to 71%.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A coal overflow identification system based on marker edge detection for a coal conveying system, characterized in that: Includes a PLC module (100), a computing server module (200), a video monitoring module (300), a belt conveyor module (400), a display interface module (500), and an emergency rescue module (600). The PLC module (100) is the system's control module, used for adjusting the belt speed of the system; The computing server module (200) is the system's computing module, used for saving monitoring videos and recording the PLC's operating status; The video monitoring module (300) is a video recording module for the belt, used to update the real-time status of the belt and store the previous monitoring videos of the belt in the computing server module (200). The belt module (400) is a belt operation module used for coal transportation, and a two-level alarm mechanism is set on the belt. The display interface module (500) transmits a corresponding signal to the display interface module (500) when the belt module (400) has an alarm problem, so that the duty personnel of the emergency rescue module (600) can quickly understand the belt fault area and the current video monitoring status of the belt fault area; Among them, the method for determining the occurrence of faults in the coal overflow identification of the coal conveying system is to compare the overlap rate between the real-time processing matrix and the model matrix. When the overlap rate is less than 71%, it is considered that coal blockage has occurred, and an alarm is triggered. The model matrix is ​​the belt recognition matrix under normal conditions; The processing matrix is ​​a processed real-time monitoring video matrix. The processing method is as follows: after acquiring the camera image, the image is first converted to grayscale, converting the three-channel image into a single-channel image. Vertical edges are detected by using a set convolution kernel. A convolution operation is performed on the image matrix. The processed matrix after the convolution operation is then binarized and filtered to filter out areas with blurred edge boundaries and extract areas with clear boundaries. Binarization filtering assigns a value of 0 to pixels with grayscale values ​​below a threshold and a value of 1 to pixels with grayscale values ​​above the threshold. The processing matrices from the past 10 seconds are superimposed, and a probability distribution filter is applied to each point in the matrix. Points that appear less than 80% of the time in 100 frames are deleted, while points that appear more than 80% of the time are retained, thus generating a final processing matrix.

2. The coal overflow identification system based on marker edge detection of the coal conveying system according to claim 1, characterized in that: The system operation process is as follows: The belt is started by the PLC module (100), and the PLC module (100) transmits the running status to the computer service module (200). After the computer service module (200) reads the belt start / stop signal change from the PLC module (100), it sends the power-on signal to the video monitoring module (300). After the computer service module (200) reads the signal, it models the video in the first ten seconds of the video. Each alarm position gets an initial state. During real-time operation, the real-time value is compared with the initial value. If it exceeds the set allowable value range, it is considered that the alarm level is triggered. When the alarm state is triggered for 3 or more consecutive frames, the corresponding alarm level will be triggered. When a Level 1 alarm is triggered, the display interface module (500) will display a warning message. When a Level 2 alarm is triggered, the interlocking PLC system will stop the belt conveyor.

3. A coal spill identification system for a coal conveying system based on marker edge detection as described in claim 1 or 2, characterized in that: The belt conveyor module (400) is equipped with a two-level alarm mechanism. The first-level alarm is set inside the feed head cover, and the second-level alarm is set outside the belt head cover. The first level indicates an abnormal state warning, and the second level indicates that coal has overflowed.

4. A coal spill identification system for a coal conveying system based on marker edge detection as described in any one of claims 3, characterized in that: When the overlap rate between the processing matrix and the model matrix is ​​higher than 71%, the belt module (400) is considered to be operating normally; When the overlap rate between the processing matrix of the primary marker area and the model matrix is ​​less than 71%, it is considered that the belt module (400) is experiencing coal blockage, triggering a primary alarm state. When the Level 1 alarm state is triggered for 3 consecutive seconds, the Level 1 alarm is triggered, the display interface module (500) displays a warning prompt, and the duty personnel of the emergency rescue module (600) can observe the area of ​​the Level 1 alarm in the belt module (400) and real-time monitoring through the display interface module (500); When the overlap rate between the secondary marker area processing matrix and the model matrix is ​​less than 71%, it is considered that the belt module (400) is experiencing coal blockage, triggering a secondary alarm state. When the level 2 alarm state is triggered for 3 consecutive seconds, the level 2 alarm is triggered, and the display interface module (500) sends a stop belt operation signal to the PLC module (100), and the PLC module (100) stops the belt operation.

5. The coal spill identification system for a coal conveying system based on marker edge detection as described in claim 4, characterized in that: The binarization filtering process is a noise reduction process performed using Gaussian filtering.

6. The coal spillage identification system for a coal conveying system based on marker edge detection as described in claim 5, characterized in that: In the belt module (400), the first-level alarm markers and the second-level alarm markers are set; The method for placing alarm markers involves using the PLC's belt start / stop recordings to locate coal blockage recordings in the video recorder. Multi-level markers are then deployed in areas with a history of frequent coal blockages. Since belt operation safety is of paramount importance, a two-level alarm mechanism is implemented.

7. A coal spill identification system for a coal conveying system based on marker edge detection as described in claim 5 or 6, characterized in that: The video monitoring module (300) consists of cameras with storage capacity that capture real-time images from multiple areas of the belt module (400).

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the system according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the system according to any one of claims 1 to 7.

Images