Fire extinguishing method, device, equipment and storage medium for thermal power plant

Abstract

The application belongs to the technical field of fire monitoring, and discloses a thermal power plant fire extinguishing method, device, equipment and storage medium. The method comprises the following steps: collecting infrared thermal imaging of a target area; generating a binary image based on the infrared thermal imaging; performing fire detection based on the binary image; after detecting that a fire has occurred, determining a fire source type and a fire area according to the infrared thermal imaging; and performing an extinguishing operation based on the fire source type and the fire area. In the above manner, after detecting that a fire has occurred, the fire source type and the fire area can be accurately identified, and then the extinguishing operation is performed. The fire can be effectively extinguished based on the identified fire source type and fire area, so that the fire is prevented from rekindling.

Description

Technical Field

[0001] This invention relates to the field of fire monitoring technology, and in particular to a fire extinguishing method, apparatus, equipment and storage medium for thermal power plants. Background Technology

[0002] As a core energy supply facility, thermal power plants typically encompass multiple fire-prone areas, including coal conveyor belts, coal storage areas, transformer rooms, power distribution rooms, and boiler auxiliary equipment areas. The causes and thermal radiation characteristics of fires vary significantly across these areas: in the coal conveyor belt area, friction ignition of pulverized coal is the primary cause, initially manifesting as a slow localized temperature rise but rapid spread; in the electrical equipment area, short circuits or electric arcs are the primary cause, resulting in a sudden localized temperature rise accompanied by strong electromagnetic radiation; and in the coal storage area, smoldering is the primary cause, with a small surface temperature gradient but continuous internal heat accumulation.

[0003] Current fire monitoring technologies primarily rely on fixed temperature threshold alarms or smoke diffusion detection. However, boilers, steam pipelines, and operating electrical equipment in thermal power plants already have high surface temperatures under normal operating conditions, making false alarms highly likely when using a uniform temperature threshold. Furthermore, smoke detection exhibits lag in open coal piles and high-wind-speed coal conveying corridors. In addition, existing technologies can only determine the presence of a fire, failing to differentiate between fire source types (electrical fires / coal fires). This results in a lack of targeted firefighting strategies, often leading to reignition due to inappropriate extinguishing agent selection (e.g., using water to extinguish electrical fires) or insufficient dosage.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a fire extinguishing method, apparatus, equipment, and storage medium for thermal power plants, aiming to solve the technical problems of the inability to identify the type of fire source, the inability to quantify the scale of the fire, and the frequent occurrence of fire reignition due to improper selection or insufficient dosage of extinguishing agent.

[0006] To achieve the above objectives, the present invention provides a fire extinguishing method for thermal power plants, the fire extinguishing method for thermal power plants comprising: Acquire infrared thermal imaging sequences of the target monitoring area of ​​the thermal power plant. The target monitoring area includes the coal conveying area, electrical equipment area and / or coal storage area. The infrared thermal imaging sequences are collected by an infrared thermal imager according to a preset sampling period. The infrared thermal imaging sequence is spatially divided according to a preset grid matrix. The temperature difference between adjacent frames of each grid is calculated. The temperature difference is compared with the temperature anomaly threshold of the corresponding region type. A binarized image is generated based on the comparison result. Morphological opening operations are performed on the binarized image to eliminate isolated noise points. The irregularity index of the connected components after processing is calculated. When the irregularity index is greater than a preset rule threshold, the temperature diffusion area growth rate of the connected components is calculated. Whether a fire has occurred is determined based on whether the temperature diffusion area growth rate is greater than a preset growth rate threshold. After a fire is determined, the temperature anomaly region in the binarized image is mapped to a preset visible light reference image based on the pre-calibrated infrared-visible light coordinate transformation matrix. The fire source type is determined according to the preset scene label corresponding to the mapping position, and the fire area is calculated based on the number of squares occupied by the temperature anomaly region in the grid matrix and the area of ​​a single square. Based on the type of fire source, the fire extinguishing agent type and extinguishing method are determined by querying the preset fire extinguishing strategy knowledge base. The fire level is determined based on the fire area. Based on the fire extinguishing agent type, extinguishing method and fire level, the fire extinguishing strategy knowledge base is queried to determine the fire extinguishing agent spray quantity and spray duration, and the automatic fire extinguishing device in the corresponding area is controlled to perform fire extinguishing operation.

[0007] Furthermore, the infrared thermal imaging sequence is spatially divided according to a preset grid matrix, and the temperature difference between adjacent frames for each grid is calculated, including: Infrared thermal imaging is divided into an M×N grid matrix, and the temperature value of each grid is the average temperature of the pixels in the corresponding area. Based on the temperature value of each square, the difference between two consecutive infrared thermal images is calculated to obtain the temperature change difference characteristics. The difference calculation satisfies the following:

[0008] Where T(x,y,t) is the average temperature value of the grid at coordinate (x,y) at time t. TDI For the temperature increase control threshold corresponding to the region type, I FDI (x,y,t) represents the difference label value; Temperature anomaly regions are identified based on the characteristics of temperature change differences, and the binarized image is generated based on these temperature anomaly regions.

[0009] Furthermore, based on a pre-calibrated infrared-visible coordinate transformation matrix, the temperature anomaly region in the binarized image is mapped to a preset visible light reference image, including: Joint calibration of an infrared thermal imager and a visible light camera under the same field of view is performed to obtain the intrinsic parameter matrix, distortion coefficient, and extrinsic parameter matrix of the relative pose of the infrared thermal imager and the visible light camera. Construct an infrared-visible coordinate transformation matrix based on the intrinsic parameter matrix, distortion coefficients, and extrinsic parameter matrix; Extract the contour coordinate set of the temperature anomaly region in infrared thermal imaging, and use the infrared-visible coordinate transformation matrix to project the contour coordinate set onto a preset visible light reference image to obtain the projection region. The cross-union ratio (CUI) is calculated between the projected area and the pre-marked device area masks in the preset visible light reference image. The device area type corresponding to the maximum CUI is determined as the fire source type.

[0010] Furthermore, the formula for calculating the irregularity index is as follows:

[0011] Among them, I TCe I represents the total number of edge pixels of the connected component. TCt The total number of pixels in the connected component; The formula for calculating the growth rate of the temperature diffusion area is:

[0012] Where A(t) and A(t) Δt) represents time t and t' respectively. The area of ​​temperature diffusion at time Δt.

[0013] Furthermore, the temperature anomaly threshold, rule threshold, and growth rate threshold are set differently according to the regional type of the target monitoring area; among them, the growth rate threshold of the coal conveying area is greater than that of the coal storage area, and the temperature anomaly threshold of the electrical equipment area is less than that of the coal conveying area.

[0014] Furthermore, the fire extinguishing strategy knowledge base is stored in the form of rule tables, which include fields for fire source type, extinguishing agent type, extinguishing method, fire level, extinguishing agent injection quantity, and injection duration. Based on the fire source type, the fire extinguishing agent type and fire extinguishing method are determined by querying the preset fire extinguishing strategy knowledge base. This includes: querying the rule table with the fire source type as the index, and matching the corresponding fire extinguishing agent type and fire extinguishing method.

[0015] Furthermore, the fire severity level is determined based on the fire area, including: If the fire area is less than the first area threshold, it is classified as a Level 1 fire. If the fire area is between the first area threshold and the second area threshold, it is determined to be a level two fire; If the fire area is greater than the second area threshold, it is classified as a level three fire. Among them, the amount of extinguishing agent sprayed is positively correlated with the fire level, and the spraying time is also positively correlated with the fire level.

[0016] On the other hand, the present invention also discloses a fire extinguishing device for thermal power plants, comprising: The acquisition module is used to acquire infrared thermal imaging sequences of the target monitoring area of ​​the thermal power plant, including the coal conveying area, electrical equipment area and / or coal storage area; The binarization processing module is used to spatially divide the infrared thermal imaging sequence according to a preset grid matrix, calculate the temperature difference value between adjacent frames of each grid, compare the temperature difference value with the temperature anomaly threshold of the corresponding region type, and generate a binarized image based on the comparison result. The fire detection module is used to perform morphological opening operations on the binarized image to eliminate isolated noise points, calculate the irregularity index of the connected components after processing, and calculate the temperature diffusion area growth rate of the connected components when the irregularity index is greater than a preset rule threshold. Based on whether the temperature diffusion area growth rate is greater than a preset growth rate threshold, it determines whether a fire has occurred. The fire source identification module is used to map the temperature anomaly area in the binarized image to a preset visible light reference image based on a pre-calibrated infrared-visible light coordinate transformation matrix after a fire is determined. The fire source type is determined according to the preset scene label corresponding to the mapping position, and the fire area is calculated according to the number of squares occupied by the temperature anomaly area in the grid matrix and the area of ​​a single square. The fire extinguishing control module is used to query the preset fire extinguishing strategy knowledge base based on the fire source type to determine the type of extinguishing agent and the fire extinguishing method, determine the fire level based on the fire area, query the fire extinguishing strategy knowledge base based on the extinguishing agent type, fire extinguishing method and fire level to determine the amount of extinguishing agent sprayed and the spraying duration, and control the automatic fire extinguishing devices in the corresponding area to perform fire extinguishing operations.

[0017] Furthermore, to achieve the above objectives, the present invention also proposes a fire extinguishing device for thermal power plants, comprising: a memory, a processor, and a fire extinguishing program for thermal power plants stored in the memory and executable on the processor, wherein the fire extinguishing program for thermal power plants is configured to implement the steps of the fire extinguishing method for thermal power plants as described above.

[0018] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a fire extinguishing program for a thermal power plant, wherein when the fire extinguishing program for a thermal power plant is executed by a processor, the steps of the fire extinguishing method for a thermal power plant as described above are implemented.

[0019] This invention effectively eliminates false triggering by high-temperature interference sources such as boilers and normally operating electrical equipment by setting differentiated temperature anomaly thresholds and growth rate thresholds for different monitoring areas of thermal power plants; through infrared-visible cross-modal registration, it accurately maps temperature anomaly areas to the actual physical scene, realizing automatic identification of fire source types; by constructing a fire extinguishing strategy knowledge base, it automatically matches the type of extinguishing agent, spray volume, and spray duration based on the fire source type and fire level, realizing accurate decision-making on fire extinguishing strategies, thereby preventing fire reignition. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating the first embodiment of the fire extinguishing method for thermal power plants according to the present invention. Figure 2 This is a structural block diagram of the first embodiment of the fire extinguishing device for thermal power plants of the present invention.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0023] This invention provides a fire extinguishing method for thermal power plants, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of a fire extinguishing method for thermal power plants according to the present invention.

[0024] In this embodiment, the fire extinguishing method for thermal power plants includes the following steps: Step S10: Acquire infrared thermal images of the target area.

[0025] In this embodiment, the executing entity is a fire extinguishing device for a thermal power plant. This fire extinguishing device has functions such as data processing, data communication, and program execution. The fire extinguishing device can be a computer terminal device or other network device, or other devices with similar functions. This embodiment does not limit the scope of the application.

[0026] It should be noted that power plants, as core infrastructure of the national energy supply, are directly related to the stability of the power grid and the guarantee of electricity supply for society. Currently, fire detection relies on smoke diffusion or temperature threshold triggering. However, this detection only indicates the presence or absence of a fire; it cannot identify the type of fire source or quantify the scale of the fire. Often, improper selection or insufficient dosage of extinguishing agents leads to reignition.

[0027] To address the aforementioned technical issues, this embodiment acquires infrared thermal images of the target area; generates a binary image based on the infrared thermal images; performs fire detection based on the binary image; after detecting a fire, determines the fire source type and fire area based on the infrared thermal images; and performs fire extinguishing operations based on the fire source type and fire area. Through this method, after a fire is detected, the fire source type and fire area can be accurately identified before fire extinguishing operations are performed. This allows for effective fire extinguishing based on the identified fire source type and fire area, thereby preventing fire reignition. Specifically, this can be implemented as follows.

[0028] It should be noted that in this embodiment, infrared thermal images of the target area need to be acquired first, and fire detection is performed based on the acquired infrared thermal images. The target area can be a pre-defined area where a fire is to be detected, which can be set according to the actual situation, or it can be the entire power plant area; this embodiment does not impose any restrictions on this.

[0029] Step S20: Generate a binarized image based on the infrared thermal imaging.

[0030] In this specific implementation, the infrared thermal image needs to be converted into a binary image first. The specific process is to divide the infrared thermal image into several square matrices, where the temperature value of each square is the average temperature value of the corresponding area; to perform differential calculation on the infrared thermal images of two consecutive frames based on the temperature value of each square to determine the temperature change difference characteristics; to determine the temperature anomaly area based on the temperature change difference characteristics; and to generate a binary image based on the temperature anomaly area.

[0031] It should be noted that infrared thermal imaging can be divided into a 32×18 grid matrix. The temperature within each grid is the average temperature value detected by infrared thermal imaging in that area. Assuming t is the data acquisition time and (x, y) are the grid coordinates, the temperature value of each grid is T(x, y, t). The differential calculation can be referred to the following formula:

[0032] Where T(x,y,t) is the average temperature value of the grid at coordinate (x,y) at time t. TDI For the temperature increase control threshold corresponding to the region type, I FDI (x,y,t) represents the difference label value; Temperature anomaly regions are determined based on the temperature change difference characteristics, and the binarized image is generated based on the temperature anomaly regions.

[0033] Considering the differences in physical environment and fire characteristics in different areas of a thermal power plant, this embodiment sets a temperature increase control threshold. Rule threshold and growth rate threshold Configure differentiated settings:

[0034] Electrical equipment areas are set at higher levels To avoid false triggering of normal operating temperature rise, a lower growth rate threshold is set in the coal pile area to capture the slow diffusion characteristics in the early stage of smoldering.

[0035] Further, the step of mapping the temperature anomaly region in the binarized image to a preset visible light reference image based on the pre-calibrated infrared-visible coordinate transformation matrix includes: The infrared thermal imager and the visible light camera under the same field of view are jointly calibrated to obtain the intrinsic parameter matrix, distortion coefficient and extrinsic parameter matrix of the infrared thermal imager and the visible light camera. The infrared-visible light coordinate transformation matrix is ​​constructed based on the intrinsic parameter matrix, distortion coefficients, and extrinsic parameter matrix. Extract the contour coordinate set of the temperature anomaly region in the infrared thermal image, and project the contour coordinate set onto the preset visible light reference image using the infrared-visible light coordinate transformation matrix to obtain the projection region; The cross-union ratio (CUI) is calculated between the projected area and the pre-marked device area masks in the preset visible light reference image. The device area type corresponding to the maximum CUI is determined as the fire source type.

[0036] Step S30: Fire detection is performed based on the binarized image.

[0037] In this specific implementation, after obtaining the aforementioned binarized image, to improve the accuracy of fire detection, this embodiment can utilize an opening operation to process the binarized image. The opening operation is used to eliminate isolated noise points in the binarized image, thereby obtaining a processed binarized image. After obtaining the processed binarized image, the specific process of fire detection involves calculating the irregularity index of the processed binarized image; if the irregularity index is greater than a set regularity image threshold, then the temperature diffusion area growth rate is determined based on the processed binarized image; if the temperature diffusion area growth rate is greater than a set growth rate threshold, then a fire is determined to exist.

[0038] It should be noted that the formula for calculating the irregularity index is r=I TCe / I TCt , among which, I TCe I represents the total number of edge pixels of connected components in the processed binary image. TCt This represents the total number of pixels in the connected component. If r > r S Then, the subsequent calculation of the temperature diffusion area growth rate is performed, where r S The threshold value for the regular shape can be set to 0.5, or other values ​​can be set according to actual needs; this embodiment does not impose any restrictions on this. The technical formula for the temperature diffusion area growth rate is g=(A(t)). A(t Δt)) / (A(t Δt)·Δt), where A(t) and A(t) Δt) represents t and t respectively. The temperature diffusion area Δt. The set growth rate threshold can be determined according to specific circumstances. For example, the set growth rate threshold for the coal conveyor belt area can be set to 0.1, and the set growth rate threshold for the coal stack area can be set to 0.05. In practical applications, it can be adjusted accordingly based on the actual situation. This embodiment does not impose any restrictions on this.

[0039] Specifically, the temperature anomaly threshold, the rule threshold, and the growth rate threshold are set differently according to the regional type of the target monitoring area; wherein, the growth rate threshold of the coal conveying area is greater than the growth rate threshold of the coal storage area, and the temperature anomaly threshold of the electrical equipment area is less than the temperature anomaly threshold of the coal conveying area.

[0040] The fire extinguishing strategy knowledge base is stored in the form of rule tables, which include fields for fire source type, fire extinguishing agent type, fire extinguishing method, fire level, fire extinguishing agent spray quantity, and spray duration. The step of determining the extinguishing agent type and extinguishing method based on the fire source type by querying the preset fire extinguishing strategy knowledge base includes: querying the rule table with the fire source type as the index, and matching the corresponding extinguishing agent type and extinguishing method.

[0041] The process of determining the fire level based on the fire area includes: If the fire area is less than the first area threshold, it is determined to be a level one fire; If the fire area is between the first area threshold and the second area threshold, it is determined to be a level two fire; If the fire area is greater than the second area threshold, it is determined to be a level three fire; The amount of extinguishing agent sprayed is positively correlated with the fire level, and the spraying duration is also positively correlated with the fire level.

[0042] Step S40: After detecting that a fire has occurred, determine the type of fire source and the fire area based on the infrared thermal imaging.

[0043] In the specific implementation, a preset visible light image is acquired in advance by a dual visible light camera. This image is essentially an image of the power plant operating stably without a fire, and it corresponds to each actual area. The detection process specifically involves: extracting temperature anomaly areas from the infrared thermal image; matching the temperature anomaly areas with the preset visible light image to determine the correlation between the temperature anomaly areas and the actual scene corresponding to the preset visible light image; determining the fire source type based on the correlation; determining the number of squares corresponding to the temperature anomaly areas; and determining the fire area based on the number of squares.

[0044] In this embodiment, the infrared thermal imager and the visible light camera are fixed on the same gimbal bracket, with a field-of-view overlap of no less than 85%. Before system deployment, joint calibration of the two cameras is required. Twenty pairs of infrared-visible images were acquired in different poses within the field of view using a checkerboard calibration board. The coordinates of the checkerboard corner points in the infrared and visible images were extracted. The intrinsic parameter matrix of the infrared camera was solved using the Zhang Zhengyou calibration method. Distortion coefficient and the intrinsic parameter matrix of a visible light camera Distortion coefficient Solving for the rotation matrix of the infrared camera relative to the visible light camera using corner matching. Translation vector The extrinsic parameter matrix is ​​obtained. .

[0045] For the contour coordinate set of temperature anomaly regions in infrared images Its projection coordinates in a visible light image Calculated using the following formula:

[0046] The intersection-over-union (IoU) ratio is calculated between the projected area and the pre-marked equipment area masks (such as coal conveyor belt masks, transformer masks, and coal pile masks) in the preset visible light reference image. The area type corresponding to the maximum IoU value is taken as the fire source type.

[0047] It should be noted that the correlation between the temperature anomaly area and the actual scene corresponding to the preset visible light image is important. For example, if the temperature anomaly area corresponds to the electrical equipment area, it can be identified as an electrical fire. Or, if the temperature anomaly area corresponds to the coal conveyor belt or coal pile area, it can be identified as a coal pile fire.

[0048] Furthermore, since the grid matrix has been divided as described above, the number of grids corresponding to the temperature anomaly area can be determined, and the final total fire area is the number of grids × the area of ​​a single grid.

[0049] Step S50: Perform fire extinguishing operations based on the fire source type and fire area.

[0050] In practice, the specific process is as follows: determine the fire extinguishing method based on the type of fire source; determine the fire level based on the fire area; set the fire extinguishing parameters corresponding to the fire extinguishing method based on the fire level; and execute the fire extinguishing operation based on the fire extinguishing method and the fire extinguishing parameters.

[0051] It should be noted that, for example, the extinguishing method for electrical fires is to use dry powder fire extinguishers for localized fire suppression, while the extinguishing method for coal pile fires is to activate foam generators at the edge of the pile for oxygen isolation extinguishing. Different fire levels correspond to different fire area ranges. By matching the fire area with the fire area range, the specific fire level can be determined. The fire area range can be a fire area less than 5m². 2 If the fire area is between 5 and 20 square meters, it is classified as a Level 1 fire. 2 If the fire area exceeds 20m², it is classified as a level two fire. 2 If so, it is classified as a level three fire.

[0052] Furthermore, the process of setting the extinguishing parameters corresponding to the extinguishing method based on the fire level specifically includes determining the extinguishing agent type according to the extinguishing method; determining the parameter type according to the extinguishing agent type; and determining the extinguishing parameters according to the fire level and the parameter type, wherein the extinguishing parameters include the extinguishing agent injection volume and the extinguishing agent injection duration.

[0053] It should be noted that the aforementioned dry powder fire extinguishers or foam generators correspond to different extinguishing agents, such as dry powder extinguishing agents and alcohol-resistant foam extinguishing agents. Parameter types, such as extinguishing agent spray volume and extinguishing agent spraying duration, vary depending on the extinguishing agent. For example, alcohol-resistant foam extinguishing agents correspond to foam dosage, while water extinguishing corresponds to water flow rate. Furthermore, determining the specific extinguishing agent spray volume and spraying duration also requires consideration of the fire severity. For instance, the higher the fire severity, the larger the extinguishing agent spray volume and the longer the spraying duration. The specific spray volume and spraying duration can be set according to actual needs; this embodiment does not impose any restrictions on this.

[0054] This embodiment acquires infrared thermal images of the target area; generates a binary image based on the infrared thermal images; performs fire detection based on the binary image; after detecting a fire, determines the fire source type and fire area based on the infrared thermal images; and performs fire extinguishing operations based on the fire source type and fire area. Through this method, after a fire is detected, the fire source type and fire area can be accurately identified before fire extinguishing operations are performed, enabling effective fire extinguishing based on the identified fire source type and fire area, thereby preventing fire reignition.

[0055] Furthermore, this embodiment of the invention also proposes a storage medium storing a fire extinguishing program for a thermal power plant. When the fire extinguishing program for a thermal power plant is executed by a processor, it implements the steps of the fire extinguishing method for a thermal power plant as described above.

[0056] To verify the effectiveness of the method of this invention, field tests were conducted in the coal conveying system and coal yard area of ​​a 300MW thermal power plant. The test period was 30 days, and the performance of the method of this invention was compared with that of the traditional fixed threshold infrared monitoring method. False alarm rate: 12 times / month for traditional methods, 2 times / month for the method of this invention; Fire detection response time: Traditional methods average 45 seconds, while the method of this invention averages 18 seconds (including the time for dual criteria for fire confirmation). Simulated fire suppression success rate: 73% for traditional methods (due to 3 reignitions caused by incompatible extinguishing agent types), 100% for the method of this invention.

[0057] The above results show that the present invention significantly reduces the false alarm rate in the complex thermal environment of thermal power plants and improves the targeting of fire extinguishing strategies by using zoned differential detection and accurate identification of fire source types.

[0058] Reference Figure 2 , Figure 2 This is a structural block diagram of the first embodiment of the fire extinguishing device for thermal power plants of the present invention.

[0059] like Figure 2 As shown, the fire extinguishing device for thermal power plants proposed in this embodiment of the invention includes: The acquisition module 10 is used to acquire infrared thermal imaging sequences of the target monitoring area of ​​the thermal power plant, the target monitoring area including the coal conveying area, the electrical equipment area and / or the coal storage area; The binarization processing module 20 is used to spatially divide the infrared thermal imaging sequence according to a preset grid matrix, calculate the temperature difference value between adjacent frames of each grid, compare the temperature difference value with the temperature anomaly threshold of the corresponding region type, and generate a binarized image based on the comparison result. The fire determination module 30 is used to perform morphological opening operation on the binarized image to eliminate isolated noise points, calculate the irregularity index of the connected component after processing, and when the irregularity index is greater than a preset rule threshold, calculate the temperature diffusion area growth rate of the connected component, and determine whether a fire has occurred based on whether the temperature diffusion area growth rate is greater than a preset growth rate threshold. The fire source identification module 40 is used to map the temperature anomaly area in the binarized image to a preset visible light reference image based on a pre-calibrated infrared-visible light coordinate transformation matrix after determining that a fire has occurred, determine the fire source type according to the preset scene label corresponding to the mapping position, and calculate the fire area according to the number of squares occupied by the temperature anomaly area in the grid matrix and the area of ​​a single square. The fire extinguishing control module 50 is used to query a preset fire extinguishing strategy knowledge base based on the fire source type to determine the type of extinguishing agent and the fire extinguishing method, determine the fire level based on the fire area, query the fire extinguishing strategy knowledge base based on the type of extinguishing agent, the fire extinguishing method and the fire level to determine the amount of extinguishing agent sprayed and the spraying duration, and control the automatic fire extinguishing device in the corresponding area to perform fire extinguishing operations.

[0060] The fire suppression strategy knowledge base is stored in the system database as a relational rule table, with the following table structure:

[0061] The system queries the rule table using the fire source type and fire level as a joint index, automatically matches the extinguishing parameters, and generates control commands to be sent to the automatic fire extinguishing device.

[0062] This embodiment acquires infrared thermal images of the target area; generates a binary image based on the infrared thermal images; performs fire detection based on the binary image; after detecting a fire, determines the fire source type and fire area based on the infrared thermal images; and performs fire extinguishing operations based on the fire source type and fire area. Through this method, after a fire is detected, the fire source type and fire area can be accurately identified before fire extinguishing operations are performed, enabling effective fire extinguishing based on the identified fire source type and fire area, thereby preventing fire reignition.

[0063] In some embodiments, the processing module 20 is used to divide the infrared thermal image into several square matrices, wherein the temperature value of each square is the average temperature value of the corresponding area. The difference between two consecutive frames of infrared thermal imaging is calculated based on the temperature value of each square to determine the temperature change difference characteristics. Temperature anomaly regions are determined based on the aforementioned temperature change differences; A binarized image is generated based on the temperature anomaly region.

[0064] In some embodiments, the judgment module 30 is used to process the binarized image using an opening operation to obtain a processed binarized image, wherein the opening operation is used to eliminate isolated noise points in the binarized image; Calculate the irregularity index of the processed binarized image; If the irregularity index is greater than the set regular image threshold, the temperature diffusion area growth rate is determined based on the processed binarized image. If the growth rate of the temperature diffusion area is greater than the set growth rate threshold, then a fire is determined to exist.

[0065] In some embodiments, the detection module 40 is used to extract temperature anomaly regions from the infrared thermal image; The temperature anomaly region is matched with a preset visible light image to determine the correlation between the actual scene corresponding to the temperature anomaly region and the preset visible light image. The type of fire source is determined based on the aforementioned correlation; Determine the number of squares corresponding to the temperature anomaly area; The fire area is determined based on the number of squares.

[0066] In some embodiments, the control module 50 is used to determine the fire extinguishing method according to the type of fire source; The fire level is determined based on the fire area. The fire extinguishing parameters corresponding to the fire extinguishing method are set based on the fire level. Firefighting operations are performed based on the firefighting method and the firefighting parameters.

[0067] In some embodiments, the control module 50 is configured to determine the type of extinguishing agent according to the extinguishing method; The parameter type is determined based on the type of extinguishing agent. Fire extinguishing parameters are determined based on the fire level and the parameter type, including the extinguishing agent injection quantity and the extinguishing agent injection duration.

[0068] This application embodiment also provides a fire extinguishing device for a thermal power plant, including a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other through the communication bus. The memory is used to store fire extinguishing programs for the thermal power plant. When the processor executes the programs stored in the memory, it implements the aforementioned fire extinguishing method for the thermal power plant.

[0069] The communication bus mentioned in the fire-fighting equipment of the aforementioned thermal power plant can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc.

[0070] The communication interface is used for communication between the fire-fighting equipment in the aforementioned thermal power plant and other equipment.

[0071] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0072] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0073] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0074] It should be noted that, in this document, relational terms such as "first" and "second" are used only 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. Furthermore, 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. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0075] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0076] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to 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. Such 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.

[0077] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0078] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0079] In addition, for technical details not described in detail in this embodiment, please refer to the fire extinguishing method for thermal power plants provided in any embodiment of the present invention, which will not be repeated here.

[0080] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system 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 system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0081] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0082] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0083] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

[0084] It is understood that the system provided in the embodiments of the present invention corresponds to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant content can be referred to the corresponding parts of the above methods.

Claims

1. A fire extinguishing method for a thermal power plant, characterized in that, The fire extinguishing methods for thermal power plants include: Acquire infrared thermal imaging sequences of target monitoring areas in a thermal power plant, including coal conveying areas, electrical equipment areas, and / or coal storage areas. The infrared thermal imaging sequences are acquired by an infrared thermal imager at a preset sampling period. The infrared thermal imaging sequence is spatially divided according to a preset grid matrix. The temperature difference value between adjacent frames of each grid is calculated. The temperature difference value is compared with the temperature anomaly threshold of the corresponding region type. A binarized image is generated based on the comparison result. Morphological opening is performed on the binarized image to eliminate isolated noise points. The irregularity index of the connected components after processing is calculated. When the irregularity index is greater than a preset rule threshold, the temperature diffusion area growth rate of the connected components is calculated. Whether a fire has occurred is determined based on whether the temperature diffusion area growth rate is greater than a preset growth rate threshold. After a fire is determined to have occurred, the temperature anomaly region in the binarized image is mapped to a preset visible light reference image based on a pre-calibrated infrared-visible light coordinate transformation matrix. The fire source type is determined according to the preset scene label corresponding to the mapping position, and the fire area is calculated based on the number of squares occupied by the temperature anomaly region in the grid matrix and the area of ​​a single square. Based on the fire source type, the fire extinguishing agent type and extinguishing method are determined by querying the preset fire extinguishing strategy knowledge base. Based on the fire area, the fire level is determined. Based on the fire extinguishing agent type, extinguishing method and fire level, the fire extinguishing strategy knowledge base is queried to determine the fire extinguishing agent spray volume and spray duration. The automatic fire extinguishing device in the corresponding area is then controlled to perform fire extinguishing operation.

2. The fire extinguishing method for thermal power plants as described in claim 1, characterized in that, The step of spatially dividing the infrared thermal imaging sequence according to a preset grid matrix and calculating the temperature difference between adjacent frames for each grid includes: The infrared thermal image is divided into an M×N grid matrix, and the temperature value of each grid is the average value of the pixel temperature in the corresponding area. Based on the temperature value of each square, a difference calculation is performed on two consecutive frames of infrared thermal imaging to obtain the temperature change difference characteristics. The difference calculation satisfies the following: Where T(x,y,t) is the average temperature value of the grid at coordinate (x,y) at time t. TDI For the temperature increase control threshold corresponding to the region type, I FDI (x,y,t) represents the difference label value; Temperature anomaly regions are determined based on the temperature change difference characteristics, and the binarized image is generated based on the temperature anomaly regions.

3. The fire extinguishing method for thermal power plants as described in claim 1, characterized in that, The method of mapping temperature anomaly regions in the binarized image to a preset visible light reference image based on a pre-calibrated infrared-visible coordinate transformation matrix includes: The infrared thermal imager and the visible light camera under the same field of view are jointly calibrated to obtain the intrinsic parameter matrix, distortion coefficient and extrinsic parameter matrix of the infrared thermal imager and the visible light camera. The infrared-visible light coordinate transformation matrix is ​​constructed based on the intrinsic parameter matrix, distortion coefficients, and extrinsic parameter matrix. Extract the contour coordinate set of the temperature anomaly region in the infrared thermal image, and project the contour coordinate set onto the preset visible light reference image using the infrared-visible light coordinate transformation matrix to obtain the projection region; The cross-union ratio (CUI) is calculated between the projected area and the pre-marked device area masks in the preset visible light reference image. The device area type corresponding to the maximum CUI is determined as the fire source type.

4. The fire extinguishing method for thermal power plants as described in claim 1 or 3, characterized in that, The formula for calculating the irregularity index is as follows: Among them, I TCe I is the total number of edge pixels of the connected region. TCt The total number of pixels in the connected domain; The formula for calculating the growth rate of the temperature diffusion area is: Where A(t) and A(t) Δt) represents time t and t' respectively. The area of ​​temperature diffusion at time Δt.

5. The fire extinguishing method for thermal power plants as described in claim 1, characterized in that, The temperature anomaly threshold, the rule threshold, and the growth rate threshold are set differently according to the regional type of the target monitoring area; wherein, the growth rate threshold of the coal conveying area is greater than the growth rate threshold of the coal storage area, and the temperature anomaly threshold of the electrical equipment area is less than the temperature anomaly threshold of the coal conveying area.

6. The fire extinguishing method for thermal power plants as described in claim 1, characterized in that, The fire extinguishing strategy knowledge base is stored in the form of rule tables, which include fields for fire source type, fire extinguishing agent type, fire extinguishing method, fire level, fire extinguishing agent spray quantity, and spray duration. The step of determining the extinguishing agent type and extinguishing method based on the fire source type by querying the preset fire extinguishing strategy knowledge base includes: querying the rule table with the fire source type as the index, and matching the corresponding extinguishing agent type and extinguishing method.

7. The fire extinguishing method for thermal power plants as described in claim 1, characterized in that, The process of determining the fire level based on the fire area includes: If the fire area is less than the first area threshold, it is determined to be a level one fire; If the fire area is between the first area threshold and the second area threshold, it is determined to be a level two fire; If the fire area is greater than the second area threshold, it is determined to be a level three fire; The amount of extinguishing agent sprayed is positively correlated with the fire level, and the spraying duration is also positively correlated with the fire level.

8. A fire extinguishing device for thermal power plants, characterized in that, include: The acquisition module is used to acquire infrared thermal imaging sequences of the target monitoring area of ​​the thermal power plant, the target monitoring area including the coal conveying area, the electrical equipment area and / or the coal storage area; The binarization processing module is used to spatially divide the infrared thermal imaging sequence according to a preset grid matrix, calculate the temperature difference value between adjacent frames of each grid, compare the temperature difference value with the temperature anomaly threshold of the corresponding region type, and generate a binarized image based on the comparison result. The fire determination module is used to perform morphological opening operations on the binarized image to eliminate isolated noise points, calculate the irregularity index of the connected components after processing, and when the irregularity index is greater than a preset rule threshold, calculate the temperature diffusion area growth rate of the connected components, and determine whether a fire has occurred based on whether the temperature diffusion area growth rate is greater than a preset growth rate threshold. The fire source identification module is used to map the temperature anomaly area in the binarized image to a preset visible light reference image based on a pre-calibrated infrared-visible light coordinate transformation matrix after a fire is determined. The fire source type is determined according to the preset scene label corresponding to the mapping position, and the fire area is calculated according to the number of squares occupied by the temperature anomaly area in the grid matrix and the area of ​​a single square. The fire extinguishing control module is used to query a preset fire extinguishing strategy knowledge base based on the fire source type to determine the type of extinguishing agent and the fire extinguishing method, determine the fire level based on the fire area, query the fire extinguishing strategy knowledge base based on the extinguishing agent type, fire extinguishing method and fire level to determine the extinguishing agent spray volume and spray duration, and control the automatic fire extinguishing device in the corresponding area to perform fire extinguishing operation.

9. A fire extinguishing device for thermal power plants, characterized in that, The device includes: a memory, a processor, and a fire extinguishing program for a thermal power plant stored in the memory and executable on the processor, the fire extinguishing program being configured to implement the steps of the fire extinguishing method for a thermal power plant as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a fire extinguishing program for a thermal power plant, which, when executed by a processor, implements the steps of the fire extinguishing method for a thermal power plant as described in any one of claims 1 to 7.

Images