Tamping coke oven coal cake collapse detection device and method based on image fusion

Abstract

The invention discloses a tamping coke oven coal cake collapse detection device and method based on image fusion, and belongs to the technical field of coking coal production.The tamping coke oven coal cake collapse detection device comprises a binocular camera, an imaging module, an edge detection module, a collapse detection module, an image splicing module and a decision support module. Clear and reliable monitoring videos can be obtained under any working condition, so that a reliable data source is provided for subsequent analysis work, misjudgment collapse in the subsequent analysis process is reduced, misjudgment conditions are effectively eliminated by analyzing images of the top and the bottom of a coal cake respectively and calculating two collapse rates for mutual verification, and the accuracy of analysis is improved. By means of the method, the finally obtained actual collapse rate result is more scientific and reliable, decision support information is provided after all the coal cakes are transported, workers can visually and conveniently obtain the collapse conditions of the coal cakes, therefore, decisions can be made in time, and the decision making efficiency of the workers is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of coke production, and particularly relates to a tamping coke oven coal cake collapse detection device and method based on image fusion. BACKGROUND

[0002] Coal cake collapse detection is the core of automation technology implementation in the coking industry. Real-time detection of coal cake collapse can ensure production efficiency and safety. Coal is tamped into coal cakes in the tamping bin. During the process of transporting the coal cakes to the carbonization furnace, real-time detection of whether the coal cakes have collapsed can enable workers to quickly take necessary measures such as cutting and cleaning, thereby improving production efficiency. In addition, accurate estimation of the degree of coal cake collapse can help reduce the difficulty of furnace temperature regulation and control and reduce the risk of equipment damage. The current coal cake collapse monitoring has the following problems:

[0003] 1. Disconnection between coal cake reinforcement and detection: Most existing technologies focus on reinforcing coal cakes through various technologies to reduce the rate of cake collapse. However, merely reinforcing coal cakes without real-time detection of coal cake collapse during the cake loading process cannot provide support for the automation of the coking industry.

[0004] 2. Limitations of detection methods: The current detection methods based on electromagnetic wave radar ranging have certain technical limitations. These methods can usually only detect the collapse of the top of the coal cake and cannot detect the collapse of the two sides of the coal cake, thus cannot accurately estimate the scale and impact of the collapse, thereby limiting the comprehensive evaluation and timely response to the coal cake collapse situation. SUMMARY

[0005] To solve some or all of the technical problems existing in the prior art, the present application provides a tamping coke oven coal cake collapse detection device based on image fusion, comprising:

[0006] A binocular camera, the binocular camera is provided with two groups, two groups of binocular cameras are respectively arranged above the coal cake and below the right side of the coal cake, and the binocular camera is composed of an infrared lens and a visible light lens;

[0007] An imaging module, configured to obtain a set of analysis images based on the binocular camera every interval, and a set of analysis images includes an analysis image of the bottom of the coal cake and an analysis image of the top of the coal cake;

[0008] An edge detection module, configured to determine the boundary of the coal cake based on the analysis image of the top of the coal cake, and determine whether the boundary of the coal cake is within a normal range;

[0009] A collapse detection module, configured to determine the regional collapse rate of the coal cake and the overall collapse rate of the coal cake based on the analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake;

[0010] The image stitching module stitches the analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake based on feature points in the analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake, and obtains a full-size spliced image of the coal cake.

[0011] The decision support module outputs decision support information when the coal cake is transported, and the decision support information includes the overall collapse rate of the coal cake and the full-size spliced image of the coal cake.

[0012] Further, the imaging module comprises:

[0013] The video acquisition unit acquires infrared lens videos and visible light lens videos of the bottom and the top of the coal cake based on the binocular camera.

[0014] The video fusion unit is configured to fuse the infrared lens videos and the visible light lens videos of the bottom and the top of the coal cake respectively, and obtain a set of monitoring videos, which includes a monitoring video of the bottom of the coal cake and a monitoring video of the top of the coal cake.

[0015] The sampling unit is configured to determine whether the coal cake exists in the monitoring video, take the time when the coal cake appears in the monitoring video as a sampling start time, take the time when the coal cake disappears from the monitoring video as a sampling end time, and extract a frame of image as an analysis image of the bottom of the coal cake and an analysis image of the top of the coal cake from the monitoring video of the bottom of the coal cake and the monitoring video of the top of the coal cake respectively every fixed time within the time range from the sampling start time to the sampling end time.

[0016] Further, the analysis image acquisition interval time t of the imaging module satisfies ; wherein m is the distance from the cake outlet of the coal bin to the cake inlet of the carbonization furnace; and v is the coal cake conveying speed.

[0017] Further, the edge detection module comprises:

[0018] The edge recognition unit is configured to recognize the boundary of the coal cake in the analysis image of the top of the coal cake.

[0019] The edge determination unit is configured to determine whether the boundary of the coal cake is within a preset normal range, and if the boundary of the coal cake is not within the preset normal range, an alarm is given.

[0020] Further, the collapse detection module comprises:

[0021] The collapse area determination unit is configured to determine whether there is a collapse area in the analysis image of the top of the coal cake, and if there is a collapse area, the area of the collapse area is obtained.

[0022] The collapse rate calculation unit is configured to calculate the collapse rate of the coal cake based on the analysis image of the top of the coal cake based on the analysis image of the top of the coal cake.

[0023] ; wherein, is the collapse rate of the nth part of the coal cake based on the analysis image of the top of the coal cake; is the collapse area of the nth part of the coal cake; is the overall area of the nth part of the coal cake;

[0024] The pulverized coal accumulation amount detection unit is configured to acquire the pulverized coal accumulation amount in the analysis image of the bottom of the coal cake.

[0025] The collapse rate checking unit is configured to obtain the collapse rate of the coal cake based on the analysis image of the bottom of the coal cake by consulting the pulverized coal accumulation amount-collapse rate mapping table based on the pulverized coal accumulation amount in the analysis image of the bottom of the coal cake, and if the absolute value of the difference between the collapse rate of the coal cake based on the analysis image of the top of the coal cake and the collapse rate of the coal cake based on the analysis image of the bottom of the coal cake is less than a preset error threshold, the collapse rate of the coal cake based on the analysis image of the top of the coal cake is taken as the actual collapse rate of the part of the coal cake, otherwise, an alarm is given.

[0026] The real-time display unit is configured to display the actual collapse rate of each part of the coal cake in the monitoring video.

[0027] The overall collapse calculation unit is configured to calculate the overall collapse rate of the coal cake.

[0028] ; wherein, L is the overall collapse rate of the coal cake; is the actual collapse rate of the nth part of the coal cake; n is the total number of analysis images, ; wherein T is the total transmission time of the coal cake, ; wherein M is the total length of the coal cake; v is the conveying speed of the coal cake; and t is the analysis image acquisition interval time.

[0029] In another aspect of the present application, the provided image fusion-based tamping coke cake collapse detection method comprises the following steps:

[0030] Step S1: based on the image acquisition of the binocular camera, the infrared lens video and the visible light lens video of the binocular camera are fused to obtain a monitoring video;

[0031] Step S2: judging whether the coal cake appears in the monitoring video, if the coal cake does not appear, waiting for the coal cake to appear, if the coal cake appears, acquiring a group of analysis images every interval time;

[0032] Step S3: based on the analysis of the analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake, the collapse rate of the coal cake based on the analysis image of the top of the coal cake and the collapse rate of the coal cake based on the analysis image of the bottom of the coal cake are obtained, and after checking, the actual collapse rate of the coal cake is obtained;

[0033] Step S4: when a piece of coal cake transportation is completed, decision support information is made and output, the decision support information including: the overall collapse rate of the coal cake and the full-size splicing image of the coal cake.

[0034] The image fusion-based tamping coke cake collapse detection device and method has the following advantages and beneficial effects:

[0035] The application adopts binocular cameras for image acquisition, ensures that clear and reliable monitoring videos can be obtained under any working conditions, thereby providing reliable data sources for subsequent analysis work, reducing the misjudgment rate of the subsequent analysis process, effectively eliminating the occurrence of misjudgment by analyzing the images of the top and bottom of the coal cake respectively and calculating two collapse rates for mutual checking, making the final actual collapse rate result more scientific and reliable, and providing decision support information after the transportation of a piece of coal cake is completed, facilitating the intuitive and convenient acquisition of the collapse condition of the coal cake by the staff, thereby enabling timely decision making and improving the decision making efficiency of the staff. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only used to further understand the embodiments of the application and form a part of the application. For those skilled in the art, other drawings can also be obtained without creative labor based on these drawings. In the drawings:

[0037] Figure 1 is a schematic diagram of the installation position of the binocular camera in the image fusion-based tamping coke cake collapse detection device of the application;

[0038] Figure 2 is a schematic diagram of the parameter definition of the image fusion-based tamping coke cake collapse detection device of the application;

[0039] Figure 3 is a schematic diagram of the real-time collapse detection effect of the image fusion-based tamping coke cake collapse detection device of the application;

[0040] Figure 4 is a schematic diagram of the collapse rate effect of each part of the coal cake in the image fusion-based tamping coke cake collapse detection device of the application;

[0041] Figure 5 is a schematic diagram of the decision support information output effect of the image fusion-based tamping coke cake collapse detection device of the application;

[0042] Figure 6is a flow chart of the image fusion-based tamping coke oven coal cake collapse detection method of the present application. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below in combination with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0044] As shown in Figures 1-5 The image fusion-based tamping coke oven coal cake collapse detection device provided by the present application comprises:

[0045] The binocular camera is provided with two groups, and the two groups of binocular cameras are arranged above the coal cake and below the right side of the coal cake, respectively.

[0046] The imaging module is used to acquire a group of analysis images based on the binocular camera every interval of time, and one group of analysis images comprises an analysis image of the bottom of the coal cake and an analysis image of the top of the coal cake.

[0047] The edge detection module is used to determine the boundary of the coal cake based on the analysis image of the top of the coal cake, and determine whether the boundary of the coal cake is in a normal range.

[0048] The collapse detection module is used to determine the regional collapse rate of the coal cake and the overall collapse rate of the coal cake for the analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake.

[0049] The image stitching module stitches the analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake based on the feature points in each analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake, and obtains a full-size stitched image of the coal cake.

[0050] The decision support module outputs decision support information after the transportation of one coal cake is completed, and the decision support information comprises the overall collapse rate of the coal cake and the full-size stitched image of the coal cake.

[0051] In the embodiments of the present application, the feature points in the analysis image refer to significant points with uniqueness, repeatability and distinguishability. For example, the "corner", "edge" and "rich-textured area" in the image.

[0052] The image fusion-based tamping coke oven coal cake collapse detection device of the present application is arranged beside the transportation device (such as a conveyor belt) for transporting the coal cake from the coal tamping bin to the carbonization furnace.

[0053] The binocular camera consists of an infrared lens and a visible light lens. The infrared lens ensures normal operation in high-heat, dusty, and low-light environments, and can operate continuously even under extreme high-temperature conditions at the coal cake inlet of the carbonization furnace, ensuring clear identification of the coal cake's position and shape. The visible light lens provides rich texture information. By fusing the images captured by the infrared and visible light lenses, the accuracy of assessing the degree of coal cake collapse is improved, and the observation difficulty for operators is reduced, providing clearer and more detailed visual information.

[0054] By placing binocular cameras above and below the right side of the coal cake, the binocular camera above the coal cake can accurately detect the collapse of the coal cake, while the binocular camera below the right side of the coal cake can observe the collapse and compression at the bottom of the coal cake, thus achieving comprehensive detection of the coal cake collapse. By placing the binocular cameras below the right side of the coal cake, it is ensured that the coal cake image will not be obstructed when the carbonization furnace door is opened.

[0055] By providing decision support information after all coal cakes have been transported, staff can intuitively and conveniently obtain information about the collapse of the coal cakes, enabling them to make timely decisions and improving their decision-making efficiency.

[0056] Furthermore, the imaging module includes:

[0057] The video acquisition unit acquires infrared lens video and visible light lens video of the bottom and top of the coal cake respectively based on the binocular camera;

[0058] The image fusion unit is used to fuse the infrared lens video and the visible light lens video of the bottom and top of the coal cake respectively to obtain a set of monitoring videos. The set of monitoring videos includes a monitoring video of the bottom of the coal cake and a monitoring video of the top of the coal cake.

[0059] The sampling unit is used to determine whether there is a coal cake in the monitoring video. The sampling start time is the moment when the coal cake appears in the monitoring video, and the sampling end time is the moment when the coal cake disappears from the monitoring video. Within the time range from the sampling start time to the sampling end time, a frame image is extracted from the monitoring video of the bottom of the coal cake and the monitoring video of the top of the coal cake at fixed time intervals, respectively, as the analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake.

[0060] Furthermore, the image acquisition interval t of the imaging module satisfies Where m is the distance from the outlet of the coal briquette bin to the inlet of the carbonization furnace; v is the coal briquette conveying speed.

[0061] By limiting the time interval for acquiring the analysis images, it is ensured that every part of the coal cake can be captured, thereby enabling a detailed analysis of the entire coal cake's collapse state and guaranteeing the accuracy of the collapse state analysis.

[0062] Furthermore, the edge detection module includes:

[0063] An edge recognition unit is used to identify the boundaries of the coal cake in an analyzed image of the top of the coal cake;

[0064] The edge detection unit is used to determine whether the boundary of the coal cake is within the preset normal range. If the boundary of the coal cake is not within the preset normal range, an alarm will be triggered.

[0065] Furthermore, the collapse detection module includes:

[0066] The collapse area judgment unit is used to determine whether there is a collapse area in the analysis image of the top of the coal cake. If there is a collapse area, the area of ​​the collapse area is obtained.

[0067] The collapse rate calculation unit calculates the collapse rate of the coal cake based on the analysis image of the top of the coal cake;

[0068] ;in, Let n be the collapse rate of the nth part of the coal cake based on the analysis image of the top of the coal cake; Let n be the collapse area of ​​the nth part of the coal cake; Let n be the total area of ​​the nth part of the coal cake;

[0069] The coal powder accumulation detection unit is used to obtain the amount of coal powder accumulation in the analysis image at the bottom of the coal cake;

[0070] The collapse rate verification unit consults the coal powder accumulation-collapse rate mapping table based on the coal powder accumulation in the analysis image at the bottom of the coal cake to obtain the collapse rate of the coal cake based on the analysis image at the bottom of the coal cake. If the absolute value of the difference between the collapse rate of the coal cake based on the analysis image at the top of the coal cake and the collapse rate of the coal cake based on the analysis image at the bottom of the coal cake is less than a preset error threshold, then the collapse rate of the coal cake based on the analysis image at the top of the coal cake is taken as the actual collapse rate of that part of the coal cake; otherwise, an alarm is triggered.

[0071] The real-time display unit is used to display the actual collapse rate of each coal cake in the monitoring video;

[0072] The overall collapse calculation unit is used to calculate the overall collapse rate of the coal cake;

[0073] Where L is the overall collapse rate of the coal cake; Let be the actual collapse rate of the nth part of the coal cake; n is the total number of analyzed images. Where T is the total time for coal cake transport. Where M is the total length of the coal cake; v is the coal cake conveying speed; and t is the interval for acquiring the analysis image.

[0074] In this embodiment of the invention, the coal powder accumulation amount-collapse rate mapping table is a lookup table that reflects the quantitative correspondence between "coal powder accumulation amount" and "coal cake collapse rate", which is obtained after sorting and analyzing experimental data.

[0075] By calculating the collapse rate based on the collapse area of ​​the analysis image at the top of the coal cake and the coal powder accumulation amount of the analysis image at the bottom of the coal cake, the accuracy of the collapse rate was verified and calibrated, thereby effectively improving the accuracy of the collapse rate calculation results.

[0076] like Figure 6 As shown, the image fusion-based method for detecting the collapse of tamped coke oven briquettes provided by this invention includes the following steps:

[0077] Step S1: Based on the images acquired by the binocular camera, fuse the infrared lens video and the visible light lens video of the binocular camera to obtain the monitoring video;

[0078] Step S2: Determine whether a coal cake appears in the monitoring video. If no coal cake appears, wait for it to appear. If a coal cake appears, acquire a set of analysis images at regular intervals.

[0079] Step S3: Analyze the analysis images of the bottom and top of the coal cake to obtain the collapse rate of the coal cake based on the analysis image of the top of the coal cake and the collapse rate of the coal cake based on the analysis image of the bottom of the coal cake. After verification, obtain the actual collapse rate of the coal cake.

[0080] Step S4: After a coal cake is transported, generate and output decision support information, which includes the overall collapse rate of the coal cake and a full-size mosaic image of the coal cake.

[0081] By using binocular cameras for image acquisition, clear and reliable monitoring video can be obtained under any working conditions, thus providing a reliable data source for subsequent analysis and reducing the misjudgment rate in the subsequent analysis process.

[0082] Instead of relying on a single perspective, this method analyzes images of the top and bottom of the coal cake separately and calculates two collapse rates for verification. This cross-validation effectively eliminates misjudgments, making the final actual collapse rate result more scientific and reliable.

[0083] The decision support information output after the coal cake transportation is completed provides producers with an intuitive global view, enabling them to make decisions quickly based on the decision support information, thus improving the efficiency of decision output. Furthermore, the decision support information can be used to analyze the specific location and pattern of the collapse, thereby tracing and optimizing the tamping process and equipment parameters, and realizing closed-loop quality control from "detection" to "improvement".

[0084] It should be noted that, unless otherwise expressly specified and limited, the term "connection" or its synonyms should be interpreted broadly. For example, "connection" can be a fixed connection or a detachable connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal communication of two elements or the interaction between two elements. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances. Furthermore, expressions such as "first" and "second" are merely used to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Meanwhile, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. In addition, "front," "rear," "left," "right," "upper," and "lower" in this document refer to the placement states shown in the accompanying drawings.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A device for detecting the collapse of tamped coke oven coal cake based on image fusion, characterized in that, include: The binocular camera is provided in two sets, with the two sets of binocular cameras respectively positioned above the coal cake and below the right side of the coal cake. The binocular camera consists of an infrared lens and a visible light lens. The imaging module is used to acquire a set of analysis images based on the binocular camera at regular intervals. The set of analysis images includes an analysis image of the bottom of the coal cake and an analysis image of the top of the coal cake. The edge detection module is used to determine the boundary of the coal cake based on the analysis image of the top of the coal cake, and to determine whether the boundary of the coal cake is within the normal range. The collapse detection module is used to determine the regional collapse rate and the overall collapse rate of the coal cake based on the analysis images of the bottom and top of the coal cake. The image stitching module stitches the analysis images of the bottom and top of each coal cake based on feature points in the analysis images of the bottom and top of each coal cake to obtain a full-size stitched image of the coal cake. The decision support module outputs decision support information after a coal cake is transported, including the overall collapse rate of the coal cake and a full-size mosaic image of the coal cake.

2. The image fusion-based coke oven briquette collapse detection device according to claim 1, characterized in that, The imaging module includes: The video acquisition unit acquires infrared lens video and visible light lens video of the bottom and top of the coal cake respectively based on the binocular camera; The image fusion unit is used to fuse the infrared lens video and the visible light lens video of the bottom and top of the coal cake respectively to obtain a set of monitoring videos. The set of monitoring videos includes a monitoring video of the bottom of the coal cake and a monitoring video of the top of the coal cake. The sampling unit is used to determine whether there is a coal cake in the monitoring video. The sampling start time is the moment when the coal cake appears in the monitoring video, and the sampling end time is the moment when the coal cake disappears from the monitoring video. Within the time range from the sampling start time to the sampling end time, a frame image is extracted from the monitoring video of the bottom of the coal cake and the monitoring video of the top of the coal cake at fixed time intervals, respectively, as the analysis image of the bottom of the coal cake and the analysis image of the top of the coal cake.

3. The image fusion-based coke oven briquette collapse detection device according to claim 1, characterized in that, The image acquisition interval t of the imaging module satisfies Where m is the distance from the outlet of the coal briquette bin to the inlet of the carbonization furnace; v is the coal briquette conveying speed.

4. The image fusion-based coke oven briquette collapse detection device according to claim 1, characterized in that, The edge detection module includes: An edge recognition unit is used to identify the boundaries of the coal cake in an analyzed image of the top of the coal cake; The edge detection unit is used to determine whether the boundary of the coal cake is within the preset normal range. If the boundary of the coal cake is not within the preset normal range, an alarm will be triggered.

5. The image fusion-based coke oven briquette collapse detection device according to claim 1, characterized in that, The collapse detection module includes: The collapse area judgment unit is used to determine whether there is a collapse area in the analysis image of the top of the coal cake. If there is a collapse area, the area of ​​the collapse area is obtained. The collapse rate calculation unit calculates the collapse rate of the coal cake based on the analysis image of the top of the coal cake; ;in, Let n be the collapse rate of the nth part of the coal cake based on the analysis image of the top of the coal cake; Let n be the collapse area of ​​the nth part of the coal cake; Let n be the total area of ​​the nth part of the coal cake; The coal powder accumulation detection unit is used to obtain the amount of coal powder accumulation in the analysis image at the bottom of the coal cake; The collapse rate verification unit consults the coal powder accumulation-collapse rate mapping table based on the coal powder accumulation in the analysis image at the bottom of the coal cake to obtain the collapse rate of the coal cake based on the analysis image at the bottom of the coal cake. If the absolute value of the difference between the collapse rate of the coal cake based on the analysis image at the top of the coal cake and the collapse rate of the coal cake based on the analysis image at the bottom of the coal cake is less than a preset error threshold, then the collapse rate of the coal cake based on the analysis image at the top of the coal cake is taken as the actual collapse rate of that part of the coal cake; otherwise, an alarm is triggered. The real-time display unit is used to display the actual collapse rate of each coal cake in the monitoring video; The overall collapse calculation unit is used to calculate the overall collapse rate of the coal cake; Where L is the overall collapse rate of the coal cake; Let be the actual collapse rate of the nth part of the coal cake; n is the total number of analyzed images. Where T is the total time for coal cake transport. Where M is the total length of the coal cake; v is the coal cake conveying speed; and t is the interval for acquiring the analysis image.

6. A method for detecting the collapse of tamped coke oven briquettes based on image fusion, implemented using the image fusion-based coke oven briquettes collapse detection device as described in any one of claims 1-5, characterized in that, Includes the following steps: Step S1: Based on the images acquired by the binocular camera, fuse the infrared lens video and the visible light lens video of the binocular camera to obtain the monitoring video; Step S2: Determine whether a coal cake appears in the monitoring video. If no coal cake appears, wait for it to appear. If a coal cake appears, acquire a set of analysis images at regular intervals. Step S3: Analyze the analysis images of the bottom and top of the coal cake to obtain the collapse rate of the coal cake based on the analysis image of the top of the coal cake and the collapse rate of the coal cake based on the analysis image of the bottom of the coal cake. After verification, obtain the actual collapse rate of the coal cake. Step S4: After a coal cake is transported, generate and output decision support information, which includes the overall collapse rate of the coal cake and a full-size mosaic image of the coal cake.

Images