Rough running detection method, device, system and equipment and storage medium
The semantic segmentation model detects the coal particle area of the ore slurry screen plate structure and calculates the proportion of coal volume, which solves the problems of low precision and low degree of automation in the existing technology, and realizes high-precision and high-automation rough detection, ensuring the normal operation of the flotation machine.
Patent Information
- Application Number
- CN202411709674.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-27
- Publication Date
- 2025-02-28
AI Technical Summary
The existing rough-running detection methods have low accuracy and low automation. It is impossible to effectively determine whether the structure of the ore slurry screen plate is thicker, resulting in the normal operation of the flotation machine being affected.
By obtaining the image of the ore slurry screen plate structure, coal particles are detected based on the semantic segmentation model, the proportion of coal volume in the total area of the coal block area is calculated, and compared with the preset threshold. If the threshold is exceeded, it is judged to be thick and an alarm is pushed.
It improves the accuracy and automation of rough detection, and can accurately determine whether the ore slurry screen plate structure is thick, ensures the normal operation of the flotation machine, and avoids metal loss and increase production costs.
Smart Images
Figure CN119540212A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of slurry coarseness detection, and in particular to a method, device, system, equipment and storage medium for coarseness detection. Background Art
[0002] Slurry coarsening refers to the phenomenon that the unqualified coarse particles in the graded products exceed the specified range, resulting in an abnormal increase in the coarse particle content in the slurry. During the operation of the classifier or flotation machine, if the overflow concentration increases, the particle size becomes coarser, and the return material volume gradually increases, this is usually a manifestation of slurry coarsening. In addition, it may also be accompanied by changes in flotation foam and disharmony in the flotation agent. Excessive coarse particle content will affect the normal operation of the flotation machine, causing flotation to not bubble and reduce flotation efficiency. The accumulation of coarse sand around the flotation tank will increase the difficulty of stirring the flotation machine and increase the load on the motor. In severe cases, it may cause the motor temperature to rise, smoke or even burn. When the coarseness phenomenon is serious, it may force the entire flotation system to stop processing coarse sand, resulting in metal loss and increased production costs. However, the existing coarseness detection methods have low accuracy and low automation. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a method, device, system, equipment and storage medium for coarse run detection, so as to solve the problems of low accuracy and low degree of automation of existing coarse run detection methods.
[0004] In a first aspect, an embodiment of the present application provides a method for detecting a runaway error, including:
[0005] Acquire images of the pulp screen structure;
[0006] Based on the semantic segmentation model, the preprocessed image is subjected to coal particle detection to obtain multiple coal particle regions;
[0007] When coal particle areas are detected, the water spray device is controlled to start;
[0008] Based on the coal particle area, calculate the total area of the coal block area;
[0009] Compare the proportion of coal volume in the total area of the coal block region with a preset threshold;
[0010] If the proportion of coal volume is greater than the preset threshold, the slurry screen plate structure is judged to be coarse and an alarm is pushed.
[0011] In the above implementation process, the embodiment of the present application obtains an image of the slurry screen plate structure; performs coal particle detection on the preprocessed image based on the semantic segmentation model to obtain multiple coal particle areas; when the coal particle area is detected, the water spray device is controlled to start; based on the coal particle area, the total area of the coal block area is calculated; the proportion of coal in the total area of the coal block area is compared with a preset threshold; if the proportion of coal is greater than the preset threshold, the slurry screen plate structure is judged to be coarse, and an alarm is pushed; the detection accuracy is high, and the coal particle area is automatically processed. At the same time, when the proportion of coal in the total area of the coal block area is too high, an alarm is pushed to ensure the safety of the slurry screening device.
[0012] Furthermore, the total area of the coal block region is calculated based on the coal particle region, including:
[0013] Setting a number of coal particle regions as coordinates representing a number of points in the coal block region;
[0014] The contour area calculation function of the computer vision library is used to calculate the contour area of each coal particle region. The contour area calculation function is based on Green's formula:
[0015]
[0016] The contour areas of each coal particle region are added together to obtain the total area of the coal block region.
[0017] In the above implementation process, the total area of the coal block region is calculated in order to obtain the proportion of the coal quantity.
[0018] Furthermore, before comparing the coal volume ratio of the total area of the coal block region with the preset threshold, the method further includes:
[0019] Obtain the area of the slurry screen plate structure to obtain the area of the detection area;
[0020] Calculate the proportion of coal:
[0021]
[0022] Among them, S1 represents the total area of the coal block region, and S2 represents the area of the detection area.
[0023] In the above implementation process, the coal ratio is calculated, so that when the coal ratio is too high, an image is obtained to analyze the cause of the roughness.
[0024] Furthermore, it also includes:
[0025] If the coal volume ratio is less than the preset threshold, the image is transmitted to the streaming process and live streaming is performed using tools;
[0026] The images of the area where no coal particles are detected are transmitted to the live streaming process for display.
[0027] In the above implementation process, images are streamed so that staff can view the inspection video at any time to control the progress.
[0028] Furthermore, the coal particle detection is performed on the preprocessed image based on the semantic segmentation model, including:
[0029] Coal particles are detected in the preprocessed images based on the semantic segmentation model, where the model is set to include a spatial attention structure and multiple bottleneck layers.
[0030] In the above implementation process, multiple bottleneck layers are used to reduce the dimension of the feature map, thereby reducing the amount of calculation; by introducing the spatial attention mechanism, these important spatial features can be retained and emphasized in the process of dimensionality reduction and dimensionality increase, so that the network can better capture key information. At the same time, the spatial attention mechanism can help the network focus on more important areas in the image, ignore the background and other irrelevant features, and play a positive role in completing the segmentation task.
[0031] Furthermore, after obtaining the image of the pulp screen plate structure, the method further includes:
[0032] Perform mask processing on the original image to obtain a mask image;
[0033] Dehaze the mask image.
[0034] In the above implementation process, the image is preprocessed to improve the clarity of the image and enhance the edges and details, so that the detection device can more accurately identify and analyze the target object.
[0035] In a second aspect, an embodiment of the present application provides a roughness detection device, including:
[0036] An image acquisition module, used to acquire an image of the slurry screen plate structure;
[0037] An image detection module is used to detect coal particles in the preprocessed image based on a semantic segmentation model to obtain a number of coal particle regions;
[0038] A water spray control module is used to detect the coal particle area, control the start of the water spray device, and set the water spray duration;
[0039] An area calculation module is used to calculate the total area of the coal block area based on the coal particle area;
[0040] A coal quantity comparison module is used to compare the coal quantity ratio of the total area of the coal block area with a preset threshold;
[0041] The push alarm module is used to judge that the slurry screen plate structure is coarse and push the alarm if the coal volume ratio is greater than the preset threshold.
[0042] In the third aspect, an embodiment of the present application provides a roughness detection system, comprising: a roughness detection device and a slurry slag removal structure as described above, wherein the roughness detection device is connected to the slurry slag removal structure; the slurry slag removal structure comprises a slurry slag removal frame, in which a slurry screen plate structure, a conveying pipeline structure arranged at the bottom of the slurry screen plate structure, a sampling pipeline structure arranged above the slurry screen plate structure, a camera structure arranged above the slurry screen plate structure, a water spray device structure arranged above the slurry screen plate structure, and a fill light are arranged.
[0043] In a fourth aspect, an embodiment of the present application provides an electronic device, including:
[0044] A processor, a memory and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the above-mentioned roughness detection method.
[0045] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a server, the above-mentioned roughness detection method is implemented. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0047] Figure 1 A schematic diagram of a flow chart of a rough detection method provided in an embodiment of the present application;
[0048] Figure 2 It is a structural schematic diagram of a roughness detection device provided in an embodiment of the present application;
[0049] Figure 3 It is a structural diagram of a rough detection system provided in an embodiment of the present application;
[0050] Figure 4 A schematic diagram of image preprocessing of a rough detection method provided in an embodiment of the present application;
[0051] Figure 5 A schematic diagram of a C2f structure of a rough detection method provided in an embodiment of the present application;
[0052] Figure 6A schematic diagram of an improved bottleneck layer structure of a rough detection method provided in an embodiment of the present application;
[0053] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0054] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0055] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0056] YOLOv8 (You Only Look Once version 8) is the latest version of the YOLO target detection and image segmentation model developed by Ultralytics. It inherits the advantages of the YOLO series of models and makes a number of improvements on this basis, becoming one of the most advanced target detection models currently.
[0057] The C2f module, full name CSP Bottleneck with 2Convolutions, is an important module for feature extraction and enhancement in YOLOv8. It is based on the CSP (Cross Stage Partial) network structure and effectively integrates feature information at different levels through cross-stage partial aggregation.
[0058] Bottleneck layer is a structure in deep neural network.
[0059] Please see Figure 1 , Figure 1 A schematic diagram of a flow chart of a rough run detection method provided in an embodiment of the present application. The rough run detection method includes:
[0060] 100. Obtain an image of the pulp screen plate structure.
[0061] Optionally, the image of the pulp screen plate structure can be captured by a camera and sent to an industrial computer, which performs pre-processing and detection analysis on the image.
[0062] On the basis of the above embodiment, the roughness detection method of the embodiment of the present application can also be embodied as follows: after acquiring the image of the pulp screen plate structure, it also includes:
[0063] Perform mask processing on the original image to obtain a mask image; perform defogging on the mask image. For the processing process, please refer to Figure 4 .
[0064] Among them, the image is preprocessed to improve the clarity of the image and enhance the edges and details, so that the detection device can more accurately identify and analyze specific areas in the image.
[0065] 200. Based on the semantic segmentation model, coal particles are detected in the preprocessed image to obtain multiple coal particle areas.
[0066] Specifically, coal particles are detected on the preprocessed image based on a semantic segmentation model, wherein the model is set to include a spatial attention structure and multiple bottleneck layers.
[0067] Optionally, the semantic segmentation model uses an improved YOLOv8 model, and adds a spatial attention structure to the C2f structure in the YOLOv8 model. The C2f structure diagram is as follows: Figure 5 As shown in the figure, the C2f structure contains n bottleneck layers (BottleNeck) structure, which is often used to reduce the dimension of feature maps, thereby reducing the amount of calculation. However, in the process of reducing and increasing the dimension, some important spatial information may be lost. By introducing the spatial attention mechanism, these important spatial features can be retained and emphasized in the process of dimensionality reduction and dimensionality increase, so that the network can better capture key information; at the same time, the spatial attention mechanism can help the network focus on more important areas in the image, ignore the background and other irrelevant features, and play a positive role in completing the segmentation task. The improved bottleneck layer (BottleNeck) is shown in the figure. Figure 6 shown.
[0068] For example, please refer to Figure 5 , where c_in is the number of feature channels of the input network, c_out is the number of feature channels of the output, and 0.5c_in is 0.5 times c_in. The input image is extracted through convolution Conv, and the output feature map is c_out. The channel is then split through split, where the split 0.5c_out is retained, and the remaining 0.5c_out is calculated by n BottleNeck operators. Because the BottleNeck operator does not change the number of channels, the number of output channels is still 0.5c_out. The output is fused with the separated feature map calculated by Conv, split, and n BottleNeck in the channel dimension to obtain the layer feature map, and finally a convolution operation is performed to output the final feature map.
[0069] For example, please refer to Figure 6, BottleNeck (bottleneck) structure, first passes through a 1x1 convolution layer to reduce the number of feature channels and improve the reasoning speed, and then extracts features through 3x3 convolution. Since the number of channels has been reduced in the previous step, it then goes through 1x1 convolution to increase the dimension and restore the original dimension. The improved structure reduces the 256-layer feature map to 64 layers through 1x1 convolution, and then divides it into two channels for processing.
[0070] Channel 1 extracts image features through two conventional Conv convolution operators. The obtained feature map is passed through the coordinate mapping structure Grid generator to generate sampling points for affine transformation. This step is Grid-parameterized grid sampling. Each time, pixels are collected from different coordinates of the image to the target image. The formula is:
[0071]
[0072] in, is the coordinate of the original image, is the coordinate of the output target image, A θ represents an affine relationship, and θ is the affine transformation matrix.
[0073] Channel 2 maintains the original BottleNeck structure, and then performs bilinear interpolation sampling on the output and the affine transformation matrix to supplement the pixel values of the vacant positions, thereby adding a spatial attention mechanism to the channel and increasing the amount of spatial feature information. Finally, it is upgraded to 1x1 to restore the original feature channel.
[0074] Exemplarily, the preprocessed image is passed into the pre-trained YOLOv8 semantic segmentation model to perform coal particle detection, and multiple coal particle regions contour1, contour2, contour3, ..., contourn are obtained.
[0075] 300. When a coal particle area is detected, the water spray device is controlled to start.
[0076] Optionally, when coal particles are detected for the first time, a signal is sent to the control unit, which controls the start of a water spray device and controls the water spray device to set the water spray time; it is used to remove accumulated coal slurry, eliminate misidentification caused by coal slurry accumulation, and increase detection accuracy.
[0077] Among them, the setting time of water spraying can be set according to specific needs. For example, the setting time of the embodiment of the present application is 10 seconds.
[0078] 400. Based on the coal particle area, calculate the total area of the coal block area.
[0079] Specifically, several coal particle regions are set as coordinates representing several points of the coal block region; the contour area calculation function contourarea of the computer vision library opencv is used to calculate the contour area of each coal particle region, and the contour area calculation function is based on Green's formula:
[0080]
[0081] Add up the contour areas of each coal particle region to obtain the total area of the coal block region: rea1, area2, area3, ...arean.
[0082] Thus, the total area of the coal block region is calculated to obtain the proportion of coal quantity.
[0083] 500. Compare the proportion of coal volume in the total area of the coal block region with a preset threshold.
[0084] Optionally, before comparing the coal volume ratio of the total area of the coal block region with a preset threshold, the method further includes:
[0085] Obtain the area of the slurry screen plate structure and obtain the area of the detection area; calculate the proportion of coal volume:
[0086]
[0087] Among them, S1 represents the total area of the coal block region, and S2 represents the area of the detection area.
[0088] Thus, the coal ratio is calculated, and when the coal ratio is too high, an image is acquired to analyze the cause of the roughening.
[0089] 600. If the proportion of coal volume is greater than the preset threshold, the slurry screen plate structure is judged to be coarse and an alarm is pushed.
[0090] On the basis of the above embodiment, the rough running detection method of the embodiment of the present application can also be embodied as follows:
[0091] If the proportion of coal is less than the preset threshold, the image will be transmitted to the streaming process and live streaming will be carried out using tools; the image of the area where no coal particles are detected will be transmitted to the streaming live streaming process for display.
[0092] Exemplarily, the obtained coal quantity ratio Ratio is compared with the preset threshold Threshold. If the coal quantity ratio Ratio is greater than the threshold, it is judged as a rough detection, and the picture is uploaded to the server as an alarm snapshot picture for on-site personnel to review. If the coal quantity ratio Ratio is less than the threshold, the picture is transmitted to the streaming process, and the ffmpeg tool is used for live streaming, so that the staff can view the detection video at any time. At the same time, the image without detected coal particles is also transmitted to the live streaming process for display.
[0093] As described above, the embodiment of the present application obtains an image of a slurry screen plate structure; performs coal particle detection on the preprocessed image based on a semantic segmentation model to obtain multiple coal particle areas; when the coal particle area is detected, a water spray device is controlled to start; based on the coal particle area, the total area of the coal block area is calculated; the proportion of coal in the total area of the coal block area is compared with a preset threshold; if the proportion of coal is greater than the preset threshold, the slurry screen plate structure is judged to be coarse, and an alarm is pushed; the detection accuracy is high, and the coal particle area is automatically processed. At the same time, when the proportion of coal in the total area of the coal block area is too high, an alarm is pushed to ensure the safety of the slurry screening device.
[0094] The above steps are not to be performed in a strict order as described in the numbers, but should be understood as an overall solution.
[0095] In the second aspect, based on the above embodiments, Figure 2 This is a schematic diagram of the structure of a roughness detection device provided in an embodiment of the present application. Figure 2 The device for detecting rough coal running provided in this embodiment specifically includes: an image acquisition module 201, an image detection module 202, a water spray control module 203, an area calculation module 204, a coal quantity comparison module 205 and a push alarm module 206.
[0096] Among them, the image acquisition module 201 is used to acquire the image of the slurry screen plate structure; the image detection module 202 is used to perform coal particle detection on the preprocessed image based on the semantic segmentation model to obtain a number of coal particle areas; the water spray control module 203 is used to detect the coal particle area, control the start of the water spray device, and set the water spray time; the area calculation module 204 is used to calculate the total area of the coal block area according to the coal particle area; the coal quantity comparison module 205 is used to compare the coal quantity ratio of the total area of the coal block area with a preset threshold; the push alarm module 206 is used to judge that the slurry screen plate structure is coarse if the coal quantity ratio is greater than the preset threshold, and push the alarm.
[0097] As described above, the embodiment of the present application obtains an image of a slurry screen plate structure; performs coal particle detection on the preprocessed image based on a semantic segmentation model to obtain multiple coal particle areas; when the coal particle area is detected, a water spray device is controlled to start; based on the coal particle area, the total area of the coal block area is calculated; the proportion of coal in the total area of the coal block area is compared with a preset threshold; if the proportion of coal is greater than the preset threshold, the slurry screen plate structure is judged to be coarse, and an alarm is pushed; the detection accuracy is high, and the coal particle area is automatically processed. At the same time, when the proportion of coal in the total area of the coal block area is too high, an alarm is pushed to ensure the safety of the slurry screening device.
[0098] The rough run detection device provided in the embodiment of the present application can be used to execute the rough run detection method provided in the above embodiment, and has corresponding functions and beneficial effects.
[0099] Third, please refer to Figure 3 The embodiment of the present application provides a rough run detection system, including: a rough run detection device and a slurry slag removal structure as described above, wherein the rough run detection device is connected to the slurry slag removal structure; the slurry slag removal structure includes a slurry slag removal frame, in which a slurry screen plate structure 20, a conveying pipeline structure 60 arranged at the bottom of the slurry screen plate structure, a sampling pipeline structure 10 arranged above the slurry screen plate structure, a camera structure 30 arranged above the slurry screen plate structure, a water spray device structure 40 arranged above the slurry screen plate structure, and a fill light 50 are arranged.
[0100] Exemplarily, the ore pulp is guided to the ore pulp slag removal structure through the sampling pipe structure 10; the ore pulp is slag-removed through the ore pulp screen plate structure 20, and the slag-removed ore pulp enters the mineral processing process through the conveying pipe structure 60; the mineral processing process is started by controlling the fill light 50 to be turned on through the industrial computer, and the image acquisition function of the camera structure 30 is turned on at the same time, and the camera structure 30 transmits the acquired video stream to the industrial computer; the industrial computer starts the built-in image recognition function, and performs image preprocessing, particle detection, live streaming, and alarm sending processes on each frame of the image; the industrial computer controls the water spray device structure 40 at the same time, and when coarse particles are detected on the screen plate, the water spray device structure 40 is started for flushing; the industrial computer transmits the final detection results and alarm pictures to the management and control platform to notify the staff; after the operator receives the alarm signal, he confirms it through video monitoring, determines the cause of the coarse particles, and checks the vibrating screen plate and other related links.
[0101] In a fourth aspect, an embodiment of the present application further provides an electronic device, which can integrate the roughness detection device provided in an embodiment of the present application. Figure 7 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 7 The electronic device includes: an input device 73, an output device 74, a memory 72 and one or more processors 71; the memory 72 is used to store one or more programs; when the one or more programs are executed by the one or more processors 71, the one or more processors 71 implement the roughness detection method provided in the above embodiment. The input device 73, the output device 74, the memory 72 and the processor 71 can be connected by a bus or other means. Figure 7 The example of connecting through bus is taken in the following.
[0102] The processor 71 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 72, that is, implements the above-mentioned roughness detection method.
[0103] The electronic device provided above can be used to execute the roughness detection method provided in the above embodiment, and has corresponding functions and beneficial effects.
[0104] In the fifth aspect, an embodiment of the present application also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the rough detection method as described above, and can achieve the same beneficial effects.
[0105] Of course, the storage medium containing computer executable instructions provided in the embodiment of the present application is not limited to the coarse running detection method described above, and the computer executable instructions can also execute the related operations in the coarse running detection method provided in any embodiment of the present application.
[0106] In a sixth aspect, the embodiments of the present application also provide a computer program product, and the methods described in the various embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the various embodiments of the present application is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM (Open Application Model) or other programmable device.
[0107] The computer program or instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it may also be an optical medium, such as a digital video disk; it may also be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.
[0108] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0109] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0110] If the functions are implemented in the form of software function modules 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 application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0111] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0112] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0113] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A rough detection method, characterized in that: include: Acquire images of the pulp screen structure; Based on the semantic segmentation model, the preprocessed image is subjected to coal particle detection to obtain several coal particle regions; When the coal particle area is detected, the water spraying device is controlled to start and the water spraying duration is set; Based on the coal particle area, calculate the total area of the coal block area; Compare the proportion of coal volume in the total area of the coal block region with a preset threshold; If the proportion of coal volume is greater than the preset threshold, the slurry screen plate structure is judged to be coarse and an alarm is pushed.
2. The method for detecting roughness according to claim 1, characterized in that: The total area of the coal block region is calculated based on the coal particle region, including: Setting a number of coal particle regions as coordinates representing a number of points in the coal block region; The contour area calculation function of the computer vision library is used to calculate the contour area of each coal particle region. The contour area calculation function is based on Green's formula: The contour areas of each coal particle region are added together to obtain the total area of the coal block region.
3. The method for detecting roughness according to claim 1, characterized in that: Before comparing the coal volume ratio of the total area of the coal block region with the preset threshold, the method further includes: Obtain the area of the slurry screen plate structure to obtain the area of the detection area; Calculate the proportion of coal: Among them, S1 represents the total area of the coal block region, and S2 represents the area of the detection area.
4. The method for detecting roughness according to claim 1, characterized in that: Also includes: If the coal volume ratio is less than the preset threshold, the image is transmitted to the streaming process and live streaming is performed using tools; The images of the area where no coal particles are detected are transmitted to the live streaming process for display.
5. The method for detecting roughness according to claim 1, characterized in that: The method of performing coal particle detection on the preprocessed image based on the semantic segmentation model includes: Coal particles are detected in the preprocessed images based on the semantic segmentation model, where the model is set to include a spatial attention structure and multiple bottleneck layers.
6. The method for detecting roughness according to claim 1, characterized in that: After obtaining the image of the pulp screen plate structure, the method further includes: Perform mask processing on the original image to obtain a mask image; Dehaze the mask image.
7. A rough detection device, characterized in that: include: An image acquisition module, used to acquire an image of the slurry screen plate structure; An image detection module is used to detect coal particles in the preprocessed image based on a semantic segmentation model to obtain a number of coal particle regions; A water spray control module is used to detect the coal particle area, control the start of the water spray device, and set the water spray duration; An area calculation module is used to calculate the total area of the coal block area based on the coal particle area; A coal quantity comparison module is used to compare the coal quantity ratio of the total area of the coal block area with a preset threshold; The push alarm module is used to judge that the slurry screen plate structure is coarse and push the alarm if the coal volume ratio is greater than the preset threshold.
8. A rough detection system, characterized in that: include: The roughness detection device and slurry slag removal structure as described in claim 7, the roughness detection device is connected to the slurry slag removal structure; the slurry slag removal structure includes a slurry slag removal frame, and the slurry slag removal frame is provided with a slurry screen plate structure, a conveying pipeline structure arranged at the bottom of the slurry screen plate structure, a sampling pipeline structure arranged above the slurry screen plate structure, a camera structure arranged above the slurry screen plate structure, a water spray device structure arranged above the slurry screen plate structure, and a fill light.
9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the roughness detection method according to any one of claims 1 to 6.
10. 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 the server, the method for detecting roughness as described in any one of claims 1 to 6 is implemented.