CN117152675A - Method, device and equipment for detecting ignition of combustor - Google Patents
Method, device and equipment for detecting ignition of combustor Download PDFInfo
- Publication number
- CN117152675A CN117152675A CN202310907335.0A CN202310907335A CN117152675A CN 117152675 A CN117152675 A CN 117152675A CN 202310907335 A CN202310907335 A CN 202310907335A CN 117152675 A CN117152675 A CN 117152675A
- Authority
- CN
- China
- Prior art keywords
- fire
- flame
- point
- ignition
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 78
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 16
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 16
- 238000010304 firing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 8
- 239000003245 coal Substances 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000003905 indoor air pollution Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 7
- 238000010248 power generation Methods 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 208000001408 Carbon monoxide poisoning Diseases 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention provides a method, a device and equipment for detecting the ignition of a burner, wherein the method comprises the steps of collecting a target image of the burner through image collecting equipment; dividing the target image into grids with target quantity based on a preset dividing mode; respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is greater than a flame brightness threshold value; extracting a fire point image based on the outline of the fire point; inputting a fire point image to a fire detection model, and determining whether the fire point is flame, wherein the fire detection model is built in advance based on training of a fire point image sample and a flame sample; if the ignition point is determined to be flame, a fire extinguishing prompt is sent to a user terminal, an alarm is sent, if the ignition point is determined not to be flame, the ignition point is determined to be false alarm, whether the ignition point exists or not is primarily determined through brightness detection, and then flame detection is carried out through a fire detection model, so that the accuracy of final fire detection is ensured, and the power generation safety is effectively ensured.
Description
Technical Field
The invention relates to the technical field of power generation safety, in particular to a method, a device and equipment for detecting ignition of a combustor.
Background
A burner is a core device in a thermal power plant, which generates steam by burning flames to drive a turbine generator to rotate, thereby generating electric power. The quality of the burner directly affects the power supply capacity and efficiency of the thermal power plant, and thus has a very important role. However, during use of the burner, a fire phenomenon may be observed due to damage of the burner. The ignition of the burner means that the burner may have a coal leakage or other faults requiring maintenance, which may affect the safe production of the whole power plant.
Therefore, how to monitor the ignition state of the burner in real time is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The invention provides a method, a device and equipment for detecting the ignition of a combustor, which are used for solving the defect of lower accuracy of the ignition detection of the combustor in the prior art.
The invention provides a method for detecting ignition of a combustor, which comprises the following steps:
collecting a target image of the burner by an image collecting device;
dividing the target image into grids with target quantity based on a preset dividing mode;
respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is larger than a flame brightness threshold value;
extracting a fire point image based on the outline of the fire point;
inputting the ignition point image to an ignition detection model, and determining whether the ignition point is flame, wherein the ignition detection model is built in advance based on the ignition point image sample and the flame sample;
and if the ignition point is determined to be flame, a fire extinguishing prompt is sent to the user terminal, an alarm is sent out, and if the ignition point is determined not to be flame, the ignition point is determined to be false alarm.
According to the method for detecting the ignition of the burner provided by the invention, after the ignition point is determined to be flame, the method further comprises the following steps:
determining the concentration of carbon monoxide produced by the flame;
and if the carbon monoxide concentration is greater than a preset carbon monoxide concentration threshold, sending out an indoor air pollution prompt.
The method for detecting the ignition of the burner provided by the invention further comprises the following steps:
determining a fire point location of the flame;
and starting fire extinguishing equipment to perform positioning fire extinguishing on the ignition point position, and closing the fire coal supply corresponding to the ignition point position.
According to the method for detecting the ignition of the burner provided by the invention, after the brightness of each grid is respectively identified, the method further comprises the following steps:
comparing the brightness differences between the different grids;
and when the brightness difference value is larger than a preset difference value, indicating that a fire point exists in the grid with larger brightness.
According to the method for detecting the ignition of the burner, which is provided by the invention, the ignition point image is extracted based on the outline of the ignition point, and the method comprises the following steps:
determining image brightness values at different positions in the grid corresponding to the ignition points;
determining a contour of the fire point based on the image brightness values at the different locations;
and according to the outline, the ignition point image is scratched.
The method for detecting the ignition of the burner provided by the invention further comprises the following steps:
collecting video images of the ignition point in a target duration;
identifying flame coordinates in the video image, and determining whether dynamic flames exist in the video image according to the flame coordinates;
if the dynamic flame exists, the ignition is determined to happen, otherwise, the false alarm is determined.
According to the method for detecting the ignition of the burner provided by the invention, after the ignition point is determined to be flame, the method further comprises the following steps:
determining the flame size and determining a hazard level based on the flame size;
when the dangerous degree is first-level, sending out sound and lamplight alarm prompt;
when the dangerous degree is the second level, sending a prompt for stopping the burner to work and overhaul;
and when the dangerous degree is three-stage, controlling the burner to stop running.
The method for detecting the ignition of the burner provided by the invention further comprises the following steps:
counting the firing times of different parts of the burner within a preset time period;
and adjusting the monitoring frequency of the different parts based on the firing times, and adjusting the corresponding fire extinguishing modes.
The invention also provides a burner fire detection device, comprising:
the acquisition module is used for acquiring a target image of the burner through the image acquisition equipment;
the segmentation module is used for segmenting the target image into grids with target quantity based on a preset segmentation mode;
the determining module is used for respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is larger than a flame brightness threshold value;
the extraction module is used for extracting a fire point image based on the outline of the fire point;
the detection module is used for inputting the ignition point image into an ignition detection model to determine whether the ignition point is flame, wherein the ignition detection model is built in advance based on the ignition point image sample and the flame sample;
and the prompting module is used for sending a fire extinguishing prompt to the user terminal and giving an alarm if the ignition point is determined to be flame, and determining the ignition point to be false alarm if the ignition point is determined to be not flame.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method for detecting a fire of a burner as described above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of fire detection of a burner as described in any of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements a method of fire detection of a burner as described in any of the above.
The invention provides a method, a device and equipment for detecting the ignition of a combustor, wherein the method comprises the steps of collecting a target image of the combustor through image collecting equipment; dividing the target image into grids with target quantity based on a preset dividing mode; respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is greater than a flame brightness threshold value; extracting a fire point image based on the outline of the fire point; inputting a fire point image to a fire detection model, and determining whether the fire point is flame, wherein the fire detection model is built in advance based on training of a fire point image sample and a flame sample; if the ignition point is determined to be flame, a fire extinguishing prompt is sent to a user terminal, an alarm is sent, if the ignition point is determined not to be flame, the ignition point is determined to be false alarm, whether the ignition point exists or not is primarily determined through brightness detection, and then flame detection is carried out through a fire detection model, so that the accuracy of final fire detection is ensured, and the power generation safety is effectively ensured.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for detecting fire in a burner according to an embodiment of the present invention;
fig. 2 is a schematic structural view of a burner fire detection device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
A method, apparatus and device for detecting a fire of a burner according to the present invention will be described with reference to fig. 1 to 3.
Fig. 1 is a schematic flow chart of a method for detecting fire of a burner according to an embodiment of the present invention.
As shown in fig. 1, the method for detecting the ignition of the burner provided by the embodiment of the invention mainly comprises the following steps:
101. the target image of the burner is acquired by an image acquisition device.
In a specific implementation process, the image acquisition equipment is arranged at a position capable of accurately irradiating the burner, so that the image acquisition equipment such as a camera can timely and accurately acquire the burner, the acquisition process can be real-time, and analysis and judgment are carried out by acquiring a target image of the burner in real time.
The target image acquired by the image acquisition device can be a color image, a black-and-white image, an infrared image and the like.
102. Based on a preset division mode, dividing the target image into grids with target quantity.
After the target image is acquired, in order to more accurately identify the target image, the target image may be selectively segmented, for example, the target image may be equally divided according to an area, and the target image may be segmented into 16 grids with the same size, and each grid is respectively identified, so that accuracy of identification can be ensured.
The position of the easy-to-catch fire point in the target image can be determined, and the target image is divided into grids with target quantity according to the position of the easy-to-catch fire point, wherein the easy-to-catch fire point refers to the point with the largest ignition frequency in the historical time or is the high-risk ignition point identified by related personnel. The grid division is carried out in a manner of easy ignition points, the specific analysis is carried out in specific conditions, the accuracy of image analysis can be ensured, and the image recognition speed is increased.
103. The brightness of each grid is respectively identified, and when the brightness is larger than the flame brightness threshold value, the presence of a fire point in the current grid is determined.
The brightness of the shot target image in the normal working state is basically kept within a certain range, and if fire occurs, the brightness of the ignition point is far greater than the brightness of the non-ignition point, so that whether the current grid has the ignition point can be determined by judging the brightness of the grid. For example, assuming that the flame luminance threshold is a, when the luminance of the grid is less than or equal to a, it indicates that there is no fire point in the grid at this time, and when the luminance of the grid is greater than a, it indicates that there is a fire point in the grid at this time. The brightness of the grid refers to the brightness corresponding to the brightest point in the grid. The brightness difference values of different grids can be compared, and when the brightness difference value is larger than a preset difference value, the fact that the ignition point exists in the grid with larger brightness is indicated.
Through the mode of brightness recognition, whether the ignition point exists can be recognized fast, the principle is simple, the recognition is accurate, and the ignition detection efficiency is improved effectively.
104. Based on the outline of the ignition point, an ignition point image is extracted.
And determining whether a fire point exists in the target image in a brightness judging mode, if the fire point does not exist, not performing other processing, and performing image acquisition according to the image acquisition requirement. If the ignition point is determined to exist, further identification processing is needed to determine whether the ignition point detection is accurate.
At this time, it is necessary to extract the outline of the ignition point, that is, the outline of the ignition point at the boundary where the brightness is greatly changed, may be determined based on the image brightness values at the different positions, that is, the outline of the ignition point, because the brightness at the different positions of the ignition point is different, the outline of the ignition point is extracted according to the outline.
105. And inputting a fire point image into a fire detection model to determine whether the fire point is flame, wherein the fire detection model is built in advance based on training of the fire point image sample and the flame sample.
The ignition point image is input into an ignition detection model, and a detection result is output, wherein the detection result comprises flame and non-flame. The ignition point detection model is obtained by training based on an ignition point image sample and a flame sample, and the accuracy of final flame detection can be ensured through a large number of sample experiments and tests.
The process of the fire detection model can be to identify the texture features of the ignition point image, and the texture features of the flame are different from those of the common photo, so that the detection of whether the flame is the flame can be rapidly and accurately finished through the comparison of the texture features.
106. If the ignition point is determined to be flame, a fire extinguishing prompt is sent to the user terminal, an alarm is sent out, and if the ignition point is determined not to be flame, the ignition point is determined to be false alarm.
If the flame detection module determines that the ignition point image is flame, a fire extinguishing prompt is immediately sent to the user terminal, so that a user can extinguish the fire in time, and an alarm is sent out to ensure the safety of the burner and the safety of personnel. If the ignition point is determined not to be flame, determining that the ignition point is detected as false alarm, and continuing to keep normal ignition monitoring without alarm processing.
The method for detecting the ignition of the burner comprises the steps of collecting a target image of the burner through an image collecting device; dividing the target image into grids with target quantity based on a preset dividing mode; respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is greater than a flame brightness threshold value; extracting a fire point image based on the outline of the fire point; inputting a fire point image to a fire detection model, and determining whether the fire point is flame, wherein the fire detection model is built in advance based on training of a fire point image sample and a flame sample; if the ignition point is determined to be flame, a fire extinguishing prompt is sent to a user terminal, an alarm is sent, if the ignition point is determined not to be flame, the ignition point is determined to be false alarm, whether the ignition point exists or not is primarily determined through brightness detection, and then flame detection is carried out through a fire detection model, so that the accuracy of final fire detection is ensured, and the power generation safety is effectively ensured.
Further, on the basis of the above embodiment, in this embodiment, after determining that the ignition point is a flame, the method further includes: determining the concentration of carbon monoxide produced by the flame; and if the carbon monoxide concentration is greater than the preset carbon monoxide concentration threshold, sending out an indoor air pollution prompt.
Specifically, after the flame is determined again, the flame is usually caused by coal leakage, so that a large amount of carbon monoxide is likely to be generated, the concentration of carbon monoxide needs to be collected in time, when the concentration of carbon monoxide is greater than a preset carbon monoxide concentration threshold value, the risk of carbon monoxide poisoning is indicated, and at the moment, an air pollution prompt needs to be sent out. To ensure the safety of the related personnel.
Further, on the basis of the above embodiment, the present embodiment further includes: determining the ignition point position of the flame; and starting the fire extinguishing equipment to perform positioning fire extinguishing on the ignition point position, and closing the fire coal supply corresponding to the ignition point position.
Specifically, after the fire is determined, the position of the fire point is required to be accurately positioned, then the fire extinguishing equipment positioned at the position is started to extinguish the fire point, fire extinguishing and extinguishing are timely completed, and corresponding fire coal transportation is closed, so that the fire extinguishing efficiency is ensured, and personnel and property losses caused by further expansion of fire are prevented.
Further, on the basis of the above embodiment, the present embodiment further includes: collecting video images of the ignition point in a target duration; identifying flame coordinates in the video image, and determining whether dynamic flames exist in the video image according to the flame coordinates; if the dynamic flame exists, the ignition is determined to happen, otherwise, the false alarm is determined.
Specifically, in order to more accurately determine whether a fire occurs, after determining that a flame exists through the neural network model, the video analysis determination can be performed, and the flame determination can be performed more precisely, so that whether the flame changes in the combustion process or not, namely whether the flame is dynamic or not is detected, and if the flame is dynamic, the accuracy of the fire can be further verified. If the dynamic flame is not found, the false detection is indicated.
Further, on the basis of the foregoing embodiment, after the ignition point is determined to be a flame in this embodiment, the method further includes: determining the flame size and determining the risk degree according to the flame size; when the dangerous degree is first-level, sound and lamplight alarm prompt are sent out; when the dangerous degree is the second level, sending out a prompt for stopping the burner to work and overhaul; and when the hazard level is three-level, controlling the burner to stop running.
Specifically, carry out the warning of different modes according to different dangerous degrees, can guarantee production safety in the time, can also guarantee work efficiency, when dangerous degree is the one-level, send sound and light warning suggestion, remind the staff in time to put out a fire and handle. And when the dangerous degree is the second level, sending out an overhaul prompt to ensure the normal operation of the burner in the subsequent working process. And when the dangerous degree is three-level, the burner is controlled to stop working immediately. Therefore, the method and the device can be used for processing according to specific problems, and meet the requirement of intelligent monitoring.
Further, on the basis of the above embodiment, the present embodiment further includes: counting the firing times of different parts of the burner within a preset time period; and adjusting the monitoring frequency of different components based on the firing times, and adjusting the corresponding fire extinguishing modes.
Specifically, in order to better realize fire prevention, the firing times of different parts of the burner can be counted, the firing probability of the different parts is calculated, and then the monitoring frequency of the different parts is adjusted through the firing probability, for example, the parts with larger firing probability can be subjected to real-time image information acquisition and identification processing, and the parts with smaller firing probability can be subjected to image acquisition every five minutes. Therefore, different acquisition frequency judgment is carried out according to different firing probabilities, and the resource cost can be saved. And according to the number of fires, the corresponding fire extinguishing modes can be adjusted, including different modes of fire hydrant fire extinguishing, fire extinguisher fire extinguishing and the like. Therefore, by adjusting the fire extinguishing mode and the monitoring frequency, the fire detection can be timely realized, the fire can be timely extinguished when the fire occurs, and certain cost can be saved.
Based on the same general inventive concept, the present invention also provides a burner fire detection device, and the burner fire detection device provided by the present invention is described below, and the burner fire detection device described below and the burner fire detection method described above can be referred to correspondingly.
Fig. 2 is a schematic structural view of a burner fire detection device according to an embodiment of the present invention.
As shown in fig. 2, a device for detecting ignition of a burner according to an embodiment of the present invention includes:
an acquisition module 201, configured to acquire a target image of a combustor through an image acquisition device;
a segmentation module 202, configured to segment the target image into a target number of grids based on a preset segmentation manner;
a determining module 203, configured to identify the brightness of each grid, and determine that a fire point exists in the current grid when the brightness is greater than a flame brightness threshold;
an extraction module 204, configured to extract a fire point image based on a contour of the fire point;
the detection module 205 is configured to input a fire point image to a fire detection model, and determine whether the fire point is a flame, where the fire detection model is pre-constructed based on training of a fire point image sample and a flame sample;
and the prompting module 206 is used for sending out a fire extinguishing prompt to the user terminal and giving out an alarm if the ignition point is determined to be flame, and determining the ignition point to be false alarm if the ignition point is determined to be not flame.
The device for detecting the ignition of the burner comprises an image acquisition device, a detection device and a control device, wherein the image acquisition device is used for acquiring a target image of the burner; dividing the target image into grids with target quantity based on a preset dividing mode; respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is greater than a flame brightness threshold value; extracting a fire point image based on the outline of the fire point; inputting a fire point image to a fire detection model, and determining whether the fire point is flame, wherein the fire detection model is built in advance based on training of a fire point image sample and a flame sample; if the ignition point is determined to be flame, a fire extinguishing prompt is sent to a user terminal, an alarm is sent, if the ignition point is determined not to be flame, the ignition point is determined to be false alarm, whether the ignition point exists or not is primarily determined through brightness detection, and then flame detection is carried out through a fire detection model, so that the accuracy of final fire detection is ensured, and the power generation safety is effectively ensured.
Further, the embodiment further includes a security detection module, configured to:
determining the concentration of carbon monoxide produced by the flame;
and if the carbon monoxide concentration is greater than a preset carbon monoxide concentration threshold, sending out an indoor air pollution prompt.
Further, the embodiment further includes a positioning module, configured to:
determining a fire point location of the flame;
and starting fire extinguishing equipment to perform positioning fire extinguishing on the ignition point position, and closing the fire coal supply corresponding to the ignition point position.
Further, the determining module 203 in this embodiment is specifically configured to:
comparing the brightness differences between the different grids;
and when the brightness difference value is larger than a preset difference value, indicating that a fire point exists in the grid with larger brightness.
Further, the extracting module 204 in this embodiment is specifically configured to:
determining image brightness values at different positions in the grid corresponding to the ignition points;
determining a contour of the fire point based on the image brightness values at the different locations;
and according to the outline, the ignition point image is scratched.
Further, the embodiment further includes a verification module, configured to:
collecting video images of the ignition point in a target duration;
identifying flame coordinates in the video image, and determining whether dynamic flames exist in the video image according to the flame coordinates;
if the dynamic flame exists, the ignition is determined to happen, otherwise, the false alarm is determined.
Further, the prompting module 206 in this embodiment is specifically configured to:
determining the flame size and determining a hazard level based on the flame size;
when the dangerous degree is first-level, sending out sound and lamplight alarm prompt;
when the dangerous degree is the second level, sending a prompt for stopping the burner to work and overhaul;
and when the dangerous degree is three-stage, controlling the burner to stop running.
Further, the embodiment further includes a statistics module, configured to:
counting the firing times of different parts of the burner within a preset time period;
and adjusting the monitoring frequency of the different parts based on the firing times, and adjusting the corresponding fire extinguishing modes.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
As shown in fig. 3, the electronic device may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. The processor 310 may invoke logic instructions in the memory 330 to perform a burner fire detection method comprising: collecting a target image of the burner by an image collecting device; dividing the target image into grids with target quantity based on a preset dividing mode; respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is larger than a flame brightness threshold value; extracting a fire point image based on the outline of the fire point; inputting the ignition point image to an ignition detection model, and determining whether the ignition point is flame, wherein the ignition detection model is built in advance based on the ignition point image sample and the flame sample; and if the ignition point is determined to be flame, a fire extinguishing prompt is sent to the user terminal, an alarm is sent out, and if the ignition point is determined not to be flame, the ignition point is determined to be false alarm.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the method of detecting a burner fire provided by the methods described above, the method comprising: collecting a target image of the burner by an image collecting device; dividing the target image into grids with target quantity based on a preset dividing mode; respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is larger than a flame brightness threshold value; extracting a fire point image based on the outline of the fire point; inputting the ignition point image to an ignition detection model, and determining whether the ignition point is flame, wherein the ignition detection model is built in advance based on the ignition point image sample and the flame sample; and if the ignition point is determined to be flame, a fire extinguishing prompt is sent to the user terminal, an alarm is sent out, and if the ignition point is determined not to be flame, the ignition point is determined to be false alarm.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method for detecting a burner fire provided by the above methods, the method comprising: collecting a target image of the burner by an image collecting device; dividing the target image into grids with target quantity based on a preset dividing mode; respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is larger than a flame brightness threshold value; extracting a fire point image based on the outline of the fire point; inputting the ignition point image to an ignition detection model, and determining whether the ignition point is flame, wherein the ignition detection model is built in advance based on the ignition point image sample and the flame sample; and if the ignition point is determined to be flame, a fire extinguishing prompt is sent to the user terminal, an alarm is sent out, and if the ignition point is determined not to be flame, the ignition point is determined to be false alarm.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for detecting a fire in a burner, comprising:
collecting a target image of the burner by an image collecting device;
dividing the target image into grids with target quantity based on a preset dividing mode;
respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is larger than a flame brightness threshold value;
extracting a fire point image based on the outline of the fire point;
inputting the ignition point image to an ignition detection model, and determining whether the ignition point is flame, wherein the ignition detection model is built in advance based on the ignition point image sample and the flame sample;
and if the ignition point is determined to be flame, a fire extinguishing prompt is sent to the user terminal, an alarm is sent out, and if the ignition point is determined not to be flame, the ignition point is determined to be false alarm.
2. The burner fire detection method according to claim 1, further comprising, after the determining that the fire point is a flame:
determining the concentration of carbon monoxide produced by the flame;
and if the carbon monoxide concentration is greater than a preset carbon monoxide concentration threshold, sending out an indoor air pollution prompt.
3. The burner fire detection method according to claim 1, characterized by further comprising:
determining a fire point location of the flame;
and starting fire extinguishing equipment to perform positioning fire extinguishing on the ignition point position, and closing the fire coal supply corresponding to the ignition point position.
4. The burner fire detection method according to claim 1, wherein after the identifying the brightness of each of the grids, respectively, further comprises:
comparing the brightness differences between the different grids;
and when the brightness difference value is larger than a preset difference value, indicating that a fire point exists in the grid with larger brightness.
5. The burner fire detection method according to claim 1, wherein the extracting a fire point image based on the outline of the fire point comprises:
determining image brightness values at different positions in the grid corresponding to the ignition points;
determining a contour of the fire point based on the image brightness values at the different locations;
and according to the outline, the ignition point image is scratched.
6. The burner fire detection method according to claim 1, characterized by further comprising:
collecting video images of the ignition point in a target duration;
identifying flame coordinates in the video image, and determining whether dynamic flames exist in the video image according to the flame coordinates;
if the dynamic flame exists, the ignition is determined to happen, otherwise, the false alarm is determined.
7. The method of detecting a fire in a burner according to claim 1, further comprising, after said determining that said fire point is a flame:
determining the flame size and determining a hazard level based on the flame size;
when the dangerous degree is first-level, sending out sound and lamplight alarm prompt;
when the dangerous degree is the second level, sending a prompt for stopping the burner to work and overhaul;
and when the dangerous degree is three-stage, controlling the burner to stop running.
8. The burner fire detection method according to any one of claims 1 to 7, characterized by further comprising:
counting the firing times of different parts of the burner within a preset time period;
and adjusting the monitoring frequency of the different parts based on the firing times, and adjusting the corresponding fire extinguishing modes.
9. A burner fire detection apparatus, comprising:
the acquisition module is used for acquiring a target image of the burner through the image acquisition equipment;
the segmentation module is used for segmenting the target image into grids with target quantity based on a preset segmentation mode;
the determining module is used for respectively identifying the brightness of each grid, and determining that a fire point exists in the current grid when the brightness is larger than a flame brightness threshold value;
the extraction module is used for extracting a fire point image based on the outline of the fire point;
the detection module is used for inputting the ignition point image into an ignition detection model to determine whether the ignition point is flame, wherein the ignition detection model is built in advance based on the ignition point image sample and the flame sample;
and the prompting module is used for sending a fire extinguishing prompt to the user terminal and giving an alarm if the ignition point is determined to be flame, and determining the ignition point to be false alarm if the ignition point is determined to be not flame.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the burner fire detection method of any one of claims 1 to 8 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310907335.0A CN117152675A (en) | 2023-07-21 | 2023-07-21 | Method, device and equipment for detecting ignition of combustor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310907335.0A CN117152675A (en) | 2023-07-21 | 2023-07-21 | Method, device and equipment for detecting ignition of combustor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117152675A true CN117152675A (en) | 2023-12-01 |
Family
ID=88901521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310907335.0A Pending CN117152675A (en) | 2023-07-21 | 2023-07-21 | Method, device and equipment for detecting ignition of combustor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152675A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109410222A (en) * | 2018-11-01 | 2019-03-01 | 浩云科技股份有限公司 | A kind of flame detecting method and device |
| CN113723300A (en) * | 2021-08-31 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Artificial intelligence-based fire monitoring method and device and storage medium |
| CN115512307A (en) * | 2022-11-23 | 2022-12-23 | 中国民用航空飞行学院 | Wide-area space infrared multi-point real-time fire detection method and system and positioning method |
| CN115526896A (en) * | 2021-07-19 | 2022-12-27 | 中核利华消防工程有限公司 | Fire prevention and control method and device, electronic equipment and readable storage medium |
| CN117367412A (en) * | 2023-12-07 | 2024-01-09 | 南开大学 | Tightly-coupled laser inertial navigation odometer integrating bundle set adjustment and map building method |
-
2023
- 2023-07-21 CN CN202310907335.0A patent/CN117152675A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109410222A (en) * | 2018-11-01 | 2019-03-01 | 浩云科技股份有限公司 | A kind of flame detecting method and device |
| CN115526896A (en) * | 2021-07-19 | 2022-12-27 | 中核利华消防工程有限公司 | Fire prevention and control method and device, electronic equipment and readable storage medium |
| CN113723300A (en) * | 2021-08-31 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Artificial intelligence-based fire monitoring method and device and storage medium |
| CN115512307A (en) * | 2022-11-23 | 2022-12-23 | 中国民用航空飞行学院 | Wide-area space infrared multi-point real-time fire detection method and system and positioning method |
| CN117367412A (en) * | 2023-12-07 | 2024-01-09 | 南开大学 | Tightly-coupled laser inertial navigation odometer integrating bundle set adjustment and map building method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108389359A (en) | A kind of Urban Fires alarm method based on deep learning | |
| US20230383943A1 (en) | Method and Smart System for Fault Detection and Prevention in Industrial Boilers | |
| CN110674790B (en) | Abnormal scene processing method and system in video monitoring | |
| CN101625789A (en) | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire | |
| CN109389185B (en) | Video smoke identification method using three-dimensional convolutional neural network | |
| CN112216055B (en) | Fire early warning detection method and system for gas field station | |
| CN109118081A (en) | A kind of operation safety supervisory systems and method based on image procossing mode | |
| CN112801457A (en) | Fire-fighting linkage method and system based on regional fire risk assessment | |
| CN114566028A (en) | Electric vehicle charging risk monitoring method and device and storage medium | |
| CN110930632B (en) | Early warning system based on artificial intelligence | |
| TW202208746A (en) | Fault diagnosis system and method for wind turbine wherein the hidden faults in the operation process can be found in time through the real-time monitoring and trend prediction of the operating status of wind power generation equipment | |
| CN117152675A (en) | Method, device and equipment for detecting ignition of combustor | |
| CN116721519B (en) | Gas leakage early warning method, system and medium based on intelligent gas Internet of things | |
| CN112070072B (en) | Prefabricated cabin fire control system based on image recognition and control method thereof | |
| CN116667536A (en) | Whole process management method, device and equipment for transformer substation monitoring information and storage medium | |
| CN103446698A (en) | Method for automatically sequencing fire sources | |
| CN207924864U (en) | Coal yard spontaneous combustion monitoring system | |
| CN114870294B (en) | Lithium ion battery fire extinguishing method and system based on image recognition | |
| CN109841140A (en) | Teaching machine and its operating method, computing device and computer-readable medium | |
| CN117152485A (en) | Coal leakage detection method, device and equipment for coal-fired unit | |
| CN114612771A (en) | Fire source monitoring method and system based on neural network | |
| CN117671608B (en) | Method and system for starting fire-fighting operation of battery energy storage system and computing equipment | |
| CN117765705A (en) | Fire control monitoring method, device and equipment for wind power plant and storage medium | |
| CN116153007B (en) | Alarm control system and method based on sensor | |
| KR102654042B1 (en) | Fire determination apparatus and method using thermal imaging and RGB dual camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |