Coal leakage detection method, device and equipment for coal-fired units

Abstract

The present invention provides a method, device and equipment for detecting coal leakage in a coal-fired unit, which collect image information of a target area in the coal-fired unit; analyze pixel values ​​in the image information, and determine black areas in the image information based on the pixel values; extract the black areas in the image information to obtain an image to be detected; input the image to be detected into a coal leakage classification network, and output texture features of the image to be detected, wherein the coal leakage classification network is pre-trained based on texture feature samples and image samples to be detected; if the texture feature is determined to be coal, a coal leakage prompt message is issued, and the accuracy of coal leakage detection can be guaranteed by implementing image collection of the target area and then undergoing double-layer recognition through image analysis and coal leakage classification network, thereby better ensuring the operating safety of the coal-fired unit.

Description

Technical Field

[0001] The present invention relates to the field of coal combustion safety technology, and in particular to a method, device and equipment for detecting coal leakage in a coal-fired unit. Background Art

[0002] The burner is a core device in a thermal power plant. It generates steam by burning coal, drives the turbine generator to rotate, and thus generates electricity. The quality of the burner directly affects the power supply capacity and efficiency of the thermal power plant, so it plays a very important role. However, during the combustion process, coal powder easily accumulates in places such as the flue and ash platform, causing many problems, such as increasing resistance, causing wear on the compressor inlet and blades, and increasing the exhaust temperature. What is more serious is that the accumulated coal may cause it to ignite and cause a fire, aggravating the safety hazards of the thermal power plant.

[0003] Therefore, how to accurately determine whether coal leakage has occurred has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0004] The present invention provides a method, device and equipment for detecting coal leakage of a coal-fired unit, which are used to solve the defect that the prior art cannot accurately detect coal leakage of a coal-fired unit.

[0005] The present invention provides a method for detecting coal leakage in a coal-fired unit, comprising: collecting image information of a target area in the coal-fired unit;

[0006] Analyzing pixel values ​​in the image information, and determining black areas in the image information based on the pixel values;

[0007] Extracting the black area in the image information to obtain the image to be detected;

[0008] Input the image to be detected into a leakage coal classification network, and output the texture features of the image to be detected, wherein the leakage coal classification network is pre-trained based on texture feature samples and image samples to be detected;

[0009] If it is determined that the texture feature is burning coal, a coal leakage prompt message is issued.

[0010] According to the coal-fired unit coal leakage detection method provided by the present invention, before issuing the coal leakage prompt information if the texture feature is determined to be coal-fired, the method further comprises:

[0011] Determine the position coordinates of the black area;

[0012] Based on the position coordinates, the coal leakage position of the coal-fired unit is located.

[0013] According to the method for detecting coal leakage in a coal-fired unit provided by the present invention, after locating the coal leakage position of the coal-fired unit, the method further comprises:

[0014] Determining the area of ​​the black region;

[0015] Based on the correlation between the area and the coal quantity, the coal leakage quantity of the coal-fired unit corresponding to the area is determined.

[0016] According to the coal leakage detection method for a coal-fired unit provided by the present invention, the step of issuing coal leakage prompt information comprises:

[0017] Determine a coal leakage amount threshold curve corresponding to the coal leakage position;

[0018] Based on the coal leakage threshold curve, determine the danger level of the coal leakage position under the coal leakage state;

[0019] A coal leakage warning is issued based on the degree of danger.

[0020] According to the coal leakage detection method for a coal-fired unit provided by the present invention, the issuing of a coal leakage prompt based on the danger level includes:

[0021] When the danger level is level one, an audible and light alarm will be issued;

[0022] When the danger level is level 2, a prompt is issued to stop the operation of the relevant coal mill for maintenance;

[0023] When the danger level is level three, the relevant coal mills are controlled to shut down urgently.

[0024] The method for detecting coal leakage in a coal-fired unit according to the present invention further comprises:

[0025] determining a coal consumption rate of the coal-fired unit;

[0026] Determining a collection time interval based on the coal consumption rate;

[0027] Image information of the target area in the coal-fired unit is collected according to the collection time interval.

[0028] The method for detecting coal leakage in a coal-fired unit according to the present invention further comprises:

[0029] Determine the size change of the black area in the image information collected twice adjacently;

[0030] Based on the size change, a coal leakage rate of the coal-fired unit is determined.

[0031] According to the coal leakage detection method for coal-fired units provided by the present invention, extracting the black area in the image information to obtain the image to be detected includes:

[0032] Determine a boundary contour of the black area, and extract the black area based on the boundary contour;

[0033] Determine the center point of the black area, and intercept a black image of a preset size in all directions based on the center point;

[0034] The brightness, saturation and hue of the black image are adjusted to target values ​​respectively to obtain an image to be detected.

[0035] The present invention also provides a coal leakage detection device for a coal-fired unit, comprising:

[0036] An acquisition module, used to acquire image information of a target area in a coal-fired unit;

[0037] A determination module, configured to analyze pixel values ​​in the image information and determine a black area in the image information based on the pixel values;

[0038] A cutout module is used to cut out the black area in the image information to obtain an image to be detected;

[0039] A detection module, used for inputting the image to be detected into a leakage coal classification network, and outputting texture features of the image to be detected, wherein the leakage coal classification network is pre-trained based on texture feature samples and samples of the image to be detected;

[0040] The prompt module is used to issue a coal leakage prompt message if it is determined that the texture feature is coal burning.

[0041] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for detecting coal leakage in a coal-fired unit as described above is implemented.

[0042] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting coal leakage in a coal-fired unit as described in any one of the above is implemented.

[0043] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for detecting coal leakage in a coal-fired unit.

[0044] The present invention provides a method, device and equipment for detecting coal leakage in a coal-fired unit, which collect image information of a target area in the coal-fired unit; analyze pixel values ​​in the image information, and determine black areas in the image information based on the pixel values; extract the black areas in the image information to obtain an image to be detected; input the image to be detected into a coal leakage classification network, and output texture features of the image to be detected, wherein the coal leakage classification network is pre-trained based on texture feature samples and image samples to be detected; if the texture feature is determined to be coal, a coal leakage prompt message is issued, and the accuracy of coal leakage detection can be guaranteed by implementing image collection of the target area and then undergoing double-layer recognition through image analysis and coal leakage classification network, thereby better ensuring the operating safety of the coal-fired unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a schematic flow chart of a method for detecting coal leakage in a coal-fired unit provided by an embodiment of the present invention;

[0047] Figure 2 It is a structural schematic diagram of a coal leakage detection device for a coal-fired unit provided by an embodiment of the present invention;

[0048] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Combine the following Figure 1-Figure 3 The invention describes a method, device and equipment for detecting coal leakage in a coal-fired unit.

[0051] Figure 1 It is a flow chart of a method for detecting coal leakage in a coal-fired unit provided in an embodiment of the present invention.

[0052] like Figure 1 As shown, a method for detecting coal leakage in a coal-fired unit provided by an embodiment of the present invention mainly comprises the following steps:

[0053] 101. Collect image information of the target area in the coal-fired unit.

[0054] In a specific implementation process, the camera can be used to collect image information of the target area in the coal-fired unit, where the target area refers to the area where there is a risk of coal leakage. The area is set for the user, and the camera is installed at the corresponding position to ensure that the camera can accurately collect image information of the target area.

[0055] Alternatively, multiple image acquisition devices may be installed to collect image information at multiple locations to ensure that the final coal leakage detection result is more accurate and reliable.

[0056] 102. Analyze pixel values ​​in the image information, and determine black areas in the image information based on the pixel values.

[0057] The image information is analyzed and processed to identify the pixel values ​​in the image, and then the black area in the image information is determined by determining the pixel values. The pixel values ​​corresponding to different colors are different, so the black area can be captured quickly by determining the pixel values.

[0058] For example, the pixel values ​​at different positions in the image information may be determined, and the area with pixel values ​​between a first preset threshold and a second preset threshold is regarded as a black area, wherein the first preset threshold and the second preset threshold are determined by the user according to the pixel value distribution diagram.

[0059] You can also convert the image from the RGB color gamut to the HSV color gamut, which can greatly reduce the impact of light on color recognition. Then, by identifying black through the HSV color gamut, you can complete the recognition more quickly and ensure the accuracy of the recognition.

[0060] In the image information, the black area of ​​the target area usually only indicates the leaked coal. Therefore, by identifying the black area, it can reflect to a certain extent whether the coal leakage has occurred. If the black area is identified, it means that there is a coal leakage. If the black area is not identified, it means that the current coal-fired unit is operating normally.

[0061] 103. Extract the black area in the image information to obtain the image to be detected.

[0062] After the black area in the image information is identified, in order to ensure the accuracy of the final coal leakage detection, the black area is selected to be identified and determined separately. Therefore, it is necessary to extract the black area in the image information and use the black area as the image to be detected.

[0063] Specifically, it can be to determine the boundary contour of the black area, extract the black area based on the boundary contour, and the black area is the black part of the image information. Then, the center point of the black area is determined, and a black image of a preset size is intercepted around the center point, so as to achieve the expansion and contraction of the size of the black area to meet the image recognition requirements, and then adjust the brightness, saturation and hue of the black image to the target value to obtain the image to be detected. By adjusting the size of the black area, the brightness, saturation and hue, it is ensured that the image to be detected meets the detection requirements, and the recognition failure due to attribute problems is avoided calmly, which better guarantees the accuracy of the final coal leakage detection.

[0064] 104. Input the image to be detected into the leaky coal classification network, and output the texture feature of the image to be detected, wherein the leaky coal classification network is pre-trained based on the texture feature samples and the image samples to be detected.

[0065] The image to be detected is input into the leaky coal classification network, which recognizes the information of the image to be detected, and outputs the texture features of the current image to be detected after internal convolution operation processing. The leaky coal classification network is pre-trained based on texture feature samples and image samples to be detected. Through the analysis and recognition of the neural network model, the texture features of the image to be detected can be accurately identified.

[0066] 105. If the texture feature is determined to be burning coal, a coal leakage warning message will be issued.

[0067] The texture features are compared. When the texture features match the texture features of coal, it is determined that the current coal-fired unit has coal leakage. At this time, a coal leakage prompt message is issued to remind relevant personnel to perform safety maintenance in time, etc. If the texture of the current image to be detected is not a coal texture after texture comparison, it indicates that the current coal-fired unit has no coal leakage.

[0068] By performing preliminary identification on the black area and then finely identifying the black area, the accuracy of the final coal leakage detection result is ensured, avoiding the impact on the working efficiency of the coal-fired unit due to erroneous detection results.

[0069] A method for detecting coal leakage in a coal-fired unit provided in the present embodiment comprises collecting image information of a target area in the coal-fired unit; analyzing pixel values ​​in the image information, and determining black areas in the image information based on the pixel values; extracting black areas in the image information to obtain an image to be detected; inputting the image to be detected into a coal leakage classification network, and outputting texture features of the image to be detected, wherein the coal leakage classification network is pre-trained based on texture feature samples and image samples to be detected; if the texture feature is determined to be coal, a coal leakage prompt message is issued, and by collecting images of the target area and then performing double-layer recognition through image analysis and coal leakage classification network, the accuracy of coal leakage detection can be ensured, thereby better ensuring the operating safety of the coal-fired unit.

[0070] Furthermore, based on the above-mentioned embodiment, if the texture feature is determined to be coal burning, before issuing a coal leakage prompt message in this embodiment, it also includes: determining the position coordinates of the black area; based on the position coordinates, locating the coal leakage position of the coal-fired unit, and determining the area of ​​the black area; based on the correlation between the area and the coal quantity, determining the coal leakage amount of the coal-fired unit corresponding to the area.

[0071] Specifically, after determining that there is coal leakage in the coal-fired unit, the specific coal leakage position can be located by determining the position coordinates, and the area of ​​the black area can be determined at the same time. The larger the coal leakage, the larger the area of ​​the black area. Therefore, by determining the area, the amount of coal leakage can be better reflected. Among them, the amount of coal leakage can be volume or mass. Taking volume as an example, through the pre-constructed relationship between area and coal amount (volume), the current amount of coal leakage of the coal-fired unit can be quickly calculated from the current area. By determining the amount of coal leakage, the degree of coal leakage can also be understood, and the maintenance work of the coal-fired unit can be completed quickly.

[0072] Further, based on the above embodiment, the issuing of coal leakage prompt information in this embodiment includes: determining the coal leakage threshold curve corresponding to the coal leakage position; determining the danger level of the coal leakage position under the coal leakage state based on the coal leakage threshold curve; issuing a coal leakage prompt based on the danger level. Issuing a coal leakage prompt based on the danger level includes: issuing a sound and light alarm prompt when the danger level is level one; issuing a shutdown and maintenance prompt when the danger level is level two; and controlling the coal-fired unit to stop operating when the danger level is level three.

[0073] Specifically, different coal leakage locations have corresponding coal leakage thresholds that are different. If the same coal leakage amount is present at different coal leakage locations, the degree of danger will also be different. Therefore, it is necessary to first determine the coal leakage threshold curve of the current coal leakage location and the degree of danger of the current coal leakage location under different coal leakage amounts.

[0074] Different types of alarm prompts are provided for different degrees of danger. According to the relationship between the amount of coal leakage from small to large, the degree of danger is divided into the first, second and third levels. At the same time, different prompts are provided for different degrees of danger, which can ensure the safety of work while ensuring the working efficiency of the coal-fired unit. When the amount of coal leakage is at the first level, the degree of danger is determined to be the first level. At this time, an alarm prompt of sound and light can be issued to remind relevant personnel that coal leakage has occurred. When the amount of coal leakage reaches the second level, it is the second level of danger, indicating that the amount of coal leakage at this time is already large and there are major safety hazards. It is necessary to issue a prompt to stop the operation of the relevant coal mill for maintenance to remind the user of the current degree of danger. When the amount of coal leakage reaches the third level, the current degree of danger is determined to be the third level, indicating that a serious coal leakage accident has occurred, and it is necessary to directly control the emergency shutdown of the relevant coal mill to ensure absolute operating safety and avoid safety accidents caused by coal leakage.

[0075] Furthermore, based on the above embodiment, the present embodiment also includes: determining the coal consumption rate of the coal-fired unit; determining the collection time interval based on the coal consumption rate; collecting image information of the target area in the coal-fired unit according to the collection time interval; determining the size change of the black area in the image information collected twice adjacently; and determining the coal leakage rate of the coal-fired unit based on the size change.

[0076] Specifically, first determine the coal consumption rate when the coal-fired unit is working normally. Different coal consumption rates will also have different degrees of danger for coal leakage. Therefore, according to the coal consumption rate, determine the collection time interval to ensure that no serious coal leakage problems occur during the image information collection interval, and ensure that the coal leakage amount during the collection time interval is within a controllable range.

[0077] Then the size change of the black area between two adjacent times can be determined, and the amount of coal leakage increased within the collection time interval can be determined. Then, according to the amount of coal leakage and the collection time interval, the coal leakage speed can be calculated. Therefore, an alarm can be issued in time according to the coal leakage speed, and the coal leakage speed can be displayed through the human-computer interaction interface, so that relevant personnel can accurately grasp the current coal leakage situation, carry out maintenance in time, and ensure the safe operation of the coal-fired unit.

[0078] Based on the same general inventive concept, the present invention also protects a coal leakage detection device for a coal-fired unit. The coal leakage detection device for a coal-fired unit provided by the present invention is described below. The coal leakage detection device for a coal-fired unit described below and the coal leakage detection method for a coal-fired unit described above can be referenced to each other.

[0079] Figure 2 It is a structural schematic diagram of a coal leakage detection device for a coal-fired unit provided in an embodiment of the present invention.

[0080] like Figure 2 As shown, this embodiment provides a coal leakage detection device for a coal-fired unit, comprising:

[0081] The acquisition module 201 is used to acquire image information of a target area in a coal-fired unit;

[0082] A determination module 202, configured to analyze pixel values ​​in the image information and determine a black area in the image information based on the pixel values;

[0083] The image cutting module 203 is used to cut out the black area in the image information to obtain the image to be detected;

[0084] The detection module 204 is used to input the image to be detected into the leakage coal classification network and output the texture features of the image to be detected, wherein the leakage coal classification network is pre-trained based on the texture feature samples and the image samples to be detected;

[0085] The prompt module 205 is used to issue a coal leakage prompt message if the texture feature is determined to be coal burning.

[0086] The present embodiment provides a coal leakage detection device for a coal-fired unit, comprising the steps of collecting image information of a target area in the coal-fired unit; analyzing pixel values ​​in the image information, and determining black areas in the image information based on the pixel values; extracting black areas in the image information to obtain an image to be detected; inputting the image to be detected into a coal leakage classification network, and outputting texture features of the image to be detected, wherein the coal leakage classification network is pre-trained based on texture feature samples and image samples to be detected; if the texture feature is determined to be coal, a coal leakage prompt message is issued, and by collecting images of the target area and then performing double-layer recognition through image analysis and coal leakage classification network, the accuracy of coal leakage detection can be ensured, thereby better ensuring the operating safety of the coal-fired unit.

[0087] Furthermore, this embodiment also includes a positioning module, which is used to:

[0088] Determine the position coordinates of the black area;

[0089] Based on the position coordinates, locating the coal leakage position of the coal-fired unit;

[0090] Determining the area of ​​the black region;

[0091] Based on the correlation between the area and the coal quantity, the coal leakage quantity of the coal-fired unit corresponding to the area is determined.

[0092] Furthermore, the prompt module 205 in this embodiment is specifically used for:

[0093] Determine a coal leakage amount threshold curve corresponding to the coal leakage position;

[0094] Based on the coal leakage threshold curve, determine the danger level of the coal leakage position under the coal leakage state;

[0095] A coal leakage warning is issued based on the degree of danger.

[0096] Furthermore, the prompt module 205 in this embodiment is also specifically used for:

[0097] When the danger level is level one, an audible and light alarm will be issued;

[0098] When the danger level is level 2, a prompt is issued to stop the operation of the relevant coal mill for maintenance;

[0099] When the danger level is level three, the relevant coal mills are controlled to shut down urgently.

[0100] Furthermore, the acquisition module 201 in this embodiment is specifically used for:

[0101] determining a coal consumption rate of the coal-fired unit;

[0102] Determining a collection time interval based on the coal consumption rate;

[0103] Image information of the target area in the coal-fired unit is collected according to the collection time interval.

[0104] Furthermore, the acquisition module 201 in this embodiment is also specifically used for:

[0105] Determine the size change of the black area in the image information collected twice adjacently;

[0106] Based on the size change, a coal leakage rate of the coal-fired unit is determined.

[0107] Furthermore, the cutout module 203 in this embodiment is specifically used for:

[0108] Determine a boundary contour of the black area, and extract the black area based on the boundary contour;

[0109] Determine the center point of the black area, and intercept a black image of a preset size in all directions based on the center point;

[0110] The brightness, saturation and hue of the black image are adjusted to target values ​​respectively to obtain an image to be detected.

[0111] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0112] like Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 620 and the memory 630 complete mutual communication through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the coal leakage detection method of the coal-fired unit, the method comprising: collecting image information of the target area in the coal-fired unit; analyzing the pixel values ​​in the image information, and determining the black area in the image information based on the pixel values; extracting the black area in the image information to obtain the image to be detected; inputting the image to be detected into the coal leakage classification network, and outputting the texture feature of the image to be detected, wherein the coal leakage classification network is pre-trained based on the texture feature samples and the image samples to be detected; if it is determined that the texture feature is coal burning, a coal leakage prompt message is issued.

[0113] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0114] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the coal leakage detection method for a coal-fired unit provided by the above-mentioned methods, and the method includes: collecting image information of a target area in a coal-fired unit; analyzing pixel values ​​in the image information, and determining a black area in the image information based on the pixel values; extracting the black area in the image information to obtain an image to be detected; inputting the image to be detected into a coal leakage classification network, and outputting texture features of the image to be detected, wherein the coal leakage classification network is pre-trained based on texture feature samples and image samples to be detected; if the texture feature is determined to be coal burning, a coal leakage prompt message is issued.

[0115] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the coal leakage detection method for a coal-fired unit provided by the above-mentioned methods, the method comprising: collecting image information of a target area in a coal-fired unit; analyzing pixel values ​​in the image information, and determining a black area in the image information based on the pixel values; extracting the black area in the image information to obtain an image to be detected; inputting the image to be detected into a coal leakage classification network, and outputting texture features of the image to be detected, wherein the coal leakage classification network is pre-trained based on texture feature samples and image samples to be detected; if it is determined that the texture feature is coal burning, a coal leakage prompt message is issued.

[0116] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0117] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting coal leakage in a coal-fired unit, characterized in that: include: Collect image information of target areas in coal-fired units; Analyzing pixel values ​​in the image information, and determining black areas in the image information based on the pixel values; Extracting the black area in the image information to obtain the image to be detected; Input the image to be detected into a leakage coal classification network, and output the texture features of the image to be detected, wherein the leakage coal classification network is pre-trained based on texture feature samples and image samples to be detected; Determine the position coordinates of the black area; and locate the coal leakage position of the coal-fired unit based on the position coordinates; Determine the area of ​​the black area; and determine the coal leakage amount of the coal-fired unit corresponding to the area based on the correlation between the area and the coal amount; If it is determined that the texture feature is coal burning, a coal leakage prompt message is issued, including: determining a coal leakage threshold curve corresponding to the coal leakage position; determining the danger level of the coal leakage position under the coal leakage level based on the coal leakage threshold curve; issuing a coal leakage prompt based on the danger level; issuing a coal leakage prompt based on the danger level includes: issuing a sound and light alarm prompt when the danger level is level one; issuing a prompt to stop the operation of the relevant coal mill for maintenance when the danger level is level two; and controlling the relevant coal mill to stop operating urgently when the danger level is level three; Determine the coal consumption rate of the coal-fired unit; determine a collection time interval based on the coal consumption rate; collect image information of a target area in the coal-fired unit according to the collection time interval; determine the size change of black areas in the image information collected between two adjacent times; determine the coal leakage rate of the coal-fired unit based on the size change.

2. The method for detecting coal leakage in a coal-fired unit according to claim 1, characterized in that: Extracting the black area in the image information to obtain the image to be detected includes: Determine a boundary contour of the black area, and extract the black area based on the boundary contour; Determine the center point of the black area, and intercept a black image of a preset size in all directions based on the center point; The brightness, saturation and hue of the black image are adjusted to target values ​​respectively to obtain an image to be detected.

3. A coal leakage detection device for a coal-fired unit, characterized in that: include: An acquisition module, used to acquire image information of a target area in a coal-fired unit; A determination module, configured to analyze pixel values ​​in the image information and determine a black area in the image information based on the pixel values; A cutout module is used to cut out the black area in the image information to obtain an image to be detected; A detection module, used for inputting the image to be detected into a leakage coal classification network, and outputting texture features of the image to be detected, wherein the leakage coal classification network is pre-trained based on texture feature samples and samples of the image to be detected; A positioning module is used to determine the position coordinates of the black area; locate the coal leakage position of the coal-fired unit based on the position coordinates; determine the area of ​​the black area; and determine the coal leakage amount of the coal-fired unit corresponding to the area based on the correlation between the area and the coal amount; A prompt module is used to issue a coal leakage prompt message if it is determined that the texture feature is coal burning, and is specifically used to: determine a coal leakage threshold curve corresponding to the coal leakage position; determine the danger level of the coal leakage position under the state of the coal leakage amount based on the coal leakage threshold curve; issue a coal leakage prompt based on the danger level; the issuance of a coal leakage prompt based on the danger level includes: when the danger level is level one, issuing a sound and light alarm prompt; when the danger level is level two, issuing a prompt to stop the operation of the relevant coal mill for maintenance; when the danger level is level three, controlling the relevant coal mill to stop operating urgently; A speed module is used to determine the coal consumption speed of the coal-fired unit; determine a collection time interval based on the coal consumption speed; collect image information of a target area in the coal-fired unit according to the collection time interval; determine the size change of a black area in the image information collected between two adjacent times; and determine the coal leakage speed of the coal-fired unit based on the size change.

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for detecting coal leakage in a coal-fired unit as described in any one of claims 1 to 2 is implemented.

Images