Flame detection method and storage medium of ultraviolet-infrared fusion detection structure

Abstract

The application provides a flame detection method of an ultraviolet-infrared fusion detection structure and a storage medium, relates to the technical field of data processing, and comprises the following steps: acquiring an ultraviolet pulse signal, a first infrared wave band signal, a second infrared wave band signal and a background interference monitoring signal of a target scene; performing pulse density analysis on the ultraviolet pulse signal to obtain an ultraviolet characteristic judgment result; performing background component elimination on the first infrared wave band signal and the second infrared wave band signal according to the background interference monitoring signal to obtain a first infrared characteristic value and a second infrared characteristic value; and performing multispectral fusion logic operation according to the ultraviolet characteristic judgment result, the first infrared characteristic value and the second infrared characteristic value to generate a flame detection result. Background thermal radiation interference can be effectively eliminated, and the accuracy of flame identification is improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a flame detection method and storage medium using an ultraviolet-infrared fusion detection structure. Background Technology

[0002] Flame detection technology is a crucial safety measure in high-risk industries such as petrochemicals, power equipment, and military. Substances exhibit unique spectral characteristics during combustion, typically releasing significant radiant energy in the ultraviolet and infrared bands. Existing rapid flame detection methods primarily rely on optical sensors to capture signals in these characteristic bands, aiming to achieve rapid identification and early warning in the early stages of a fire by monitoring changes in ultraviolet pulse or infrared radiation intensity, thus preventing catastrophic consequences.

[0003] However, existing multi-band flame detection technologies have significant limitations in resisting interference in complex thermal radiation environments, failing to effectively distinguish and eliminate background thermal radiation interference from sources such as heaters, halogen lamps, or high-temperature objects. Therefore, when non-flame heat sources are present in the environment, existing technologies often suffer from high false alarm rates or necessitate repeated verification using complex software algorithms, leading to system response delays.

[0004] Therefore, how to effectively eliminate background thermal radiation interference to improve the accuracy of flame identification has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a flame detection method and storage medium with an ultraviolet-infrared fusion detection structure, which can effectively eliminate background thermal radiation interference, thereby improving the accuracy of flame identification.

[0006] A first aspect of the present invention provides a flame detection method with an ultraviolet-infrared fusion detection structure, comprising:

[0007] Acquire ultraviolet pulse signals, first infrared band signals, second infrared band signals, and background interference monitoring signals of the target scene;

[0008] Pulse density analysis was performed on the ultraviolet pulse signal to obtain the ultraviolet feature determination result;

[0009] Background components are removed from the first infrared band signal and the second infrared band signal respectively based on the background interference monitoring signal to obtain the first infrared feature value and the second infrared feature value;

[0010] Based on the ultraviolet feature determination result, the first infrared feature value, and the second infrared feature value, a multispectral fusion logic operation is performed to generate a flame detection result.

[0011] Optionally, in one possible implementation of the first aspect, acquiring the ultraviolet pulse signal, the first infrared band signal, the second infrared band signal, and the background interference monitoring signal of the target scene includes:

[0012] Acquire ultraviolet pulse signals, first infrared band signals, second infrared band signals, and background interference monitoring signals of the target scene;

[0013] The first infrared band signal corresponds to the carbon dioxide radiation characteristics, the second infrared band signal corresponds to the water molecule radiation characteristics, and the background interference monitoring signal corresponds to the environmental background thermal radiation characteristics.

[0014] Optionally, in one possible implementation of the first aspect, the step of performing pulse density analysis on the ultraviolet pulse signal to obtain the ultraviolet feature determination result includes:

[0015] The ultraviolet pulse density of the ultraviolet pulse signal per unit time is calculated based on the time window integration method;

[0016] If the ultraviolet pulse density is determined to be greater than a first preset threshold and the duration meets the preset time domain characteristics, then an ultraviolet feature determination result for direct alarm is generated.

[0017] If the ultraviolet pulse density is not greater than the first preset threshold, but is greater than the second preset threshold, then an ultraviolet feature flag bit that needs to be fused is generated.

[0018] Optionally, in one possible implementation of the first aspect, before the step of removing background components from the first infrared band signal and the second infrared band signal respectively based on the background interference monitoring signal to obtain the first infrared feature value and the second infrared feature value, the method further includes:

[0019] The first infrared band signal, the second infrared band signal, and the background interference monitoring signal are subjected to moving average filtering.

[0020] Optionally, in one possible implementation of the first aspect, the step of performing multispectral fusion logic operations based on the ultraviolet feature determination result, the first infrared feature value, and the second infrared feature value to generate a flame detection result includes:

[0021] The first infrared feature value and the second infrared feature value are compared with preset thresholds respectively to generate a binarized first infrared feature flag and second infrared feature flag;

[0022] Based on the first infrared feature marker, the second infrared feature marker, and the binarized ultraviolet feature determination result, a triple Boolean fusion logic is used to generate the flame detection result.

[0023] Optionally, in one possible implementation of the first aspect, the step of generating the flame detection result using triple Boolean fusion logic based on the first infrared feature marker, the second infrared feature marker, and the binarized ultraviolet feature determination result includes:

[0024] When both the ultraviolet feature determination result and the first infrared feature flag are true, a flame detection result is generated;

[0025] When both the ultraviolet feature determination result and the second infrared feature flag are true, a flame detection result is generated.

[0026] When both the first infrared feature marker and the second infrared feature marker are determined to be true, a flame detection result is generated.

[0027] Optionally, in one possible implementation of the first aspect, it also includes:

[0028] In response to the flame detection result, the flame area is acquired, and the activation device is determined based on the flame area.

[0029] Optionally, in one possible implementation of the first aspect, determining the activation device based on the flame region includes:

[0030] Identify the regional outline of the flame area and obtain the spray range of each fire extinguishing device;

[0031] The activation device is determined based on the spray range and area contour.

[0032] Optionally, in one possible implementation of the first aspect, the determination of the activation device based on the spray range and area contour includes:

[0033] The fire extinguishing device corresponding to the spray range that intersects with the area outline is used as the activation device.

[0034] A second aspect of the present invention provides a storage medium storing a computer program, which, when executed by a processor, is used to implement the first aspect of the present invention and various methods possibly involved in the first aspect.

[0035] The beneficial effects of this invention are as follows:

[0036] 1. This invention introduces background interference monitoring signals corresponding to environmental background thermal radiation characteristics by acquiring the ultraviolet pulse signal of the target scene and the first and second infrared band signals corresponding to the radiation characteristics of carbon dioxide and water molecules. Existing technologies mostly rely on single or ordinary multi-band monitoring, which makes it difficult to eliminate environmental heat source interference and can distinguish between flames and high-temperature objects such as heaters.

[0037] 2. The present invention can automatically determine the fire extinguishing equipment to be activated based on the location of the subsequent flame. Attached Figure Description

[0038] Figure 1 A flowchart of the flame detection method using the ultraviolet-infrared fusion detection structure provided by the present invention;

[0039] Figure 2 This is a schematic diagram showing the connection relationship of the flame detection device provided by the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein.

[0042] It should be understood that in the various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0043] It should be understood that in this invention, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0044] It should be understood that in this invention, "multiple" refers to two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "Contains A, B, and C", "Contains A, B, and C" means that all three A, B, and C are contained; "Contains A, B, or C" means that one of A, B, and C is contained; "Contains A, B, and / or C" means that any one, two, or three of A, B, and C are contained.

[0045] It should be understood that in this invention, "B corresponding to A", "B corresponding to A", "A and B correspond", or "B and A correspond" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information. Matching A and B is defined as a similarity between A and B that is greater than or equal to a preset threshold.

[0046] Depending on the context, "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection."

[0047] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0048] This invention provides a flame detection method with an ultraviolet-infrared fusion detection structure, such as... Figure 1 As shown, steps S1-S4 are included:

[0049] S1, acquire the ultraviolet pulse signal, the first infrared band signal, the second infrared band signal and the background interference monitoring signal of the target scene.

[0050] In some embodiments, step S1 (acquiring the ultraviolet pulse signal, the first infrared band signal, the second infrared band signal, and the background interference monitoring signal of the target scene) includes:

[0051] Acquire ultraviolet pulse signals, first infrared band signals, second infrared band signals, and background interference monitoring signals of the target scene;

[0052] The first infrared band signal corresponds to the carbon dioxide radiation characteristics, the second infrared band signal corresponds to the water molecule radiation characteristics, and the background interference monitoring signal corresponds to the environmental background thermal radiation characteristics.

[0053] It's important to note that when a flame burns, it produces carbon dioxide and water vapor, both of which emit strong radiation signals in specific infrared wavelengths (4.35 micrometers and 2.7 micrometers). However, many everyday heat sources, such as heaters and light bulbs, also emit infrared light. Older methods often struggled to distinguish between fire and ordinary heat sources, leading to false alarms. Our approach uses four different wavelengths. In addition to examining ultraviolet light and the infrared radiation specific to flames, the most crucial element is the addition of a dedicated background signal: 4.8 micrometers. This wavelength is not sensitive to fire but is highly sensitive to ambient heat sources.

[0054] Among them, the ultraviolet pulse signal is a high-intensity radiation light signal released during flame combustion, generally referring to light signals with wavelengths in the range of 185 nanometers to 260 nanometers, which is significantly different from the ultraviolet interference signals of artificial light sources such as sunlight and tungsten filament lamps; the first infrared band signal is a radiation signal unique to the production of carbon dioxide during flame combustion, generally referring to infrared light with a wavelength of 4.35 micrometers; the second infrared band signal is a radiation signal emitted when water vapor is produced during flame combustion, generally referring to infrared light with a wavelength of 2.7 micrometers; the background interference monitoring signal is a signal that is not sensitive to flame radiation but is sensitive to environmental heat source radiation, generally referring to infrared light with a wavelength of 4.8 micrometers, which is specifically used for reference and comparison, that is, the fourth monitoring dimension in this method.

[0055] Furthermore, the optical lens assembly is a combination of lenses, windows, or narrowband filters mounted in front of the sensor. Its function is to filter out stray light from the outside, allowing only four specific wavelengths of light to pass through and illuminate the corresponding sensors.

[0056] Understandably, we use four different sensors, each corresponding to one of the four types of light mentioned above. When the equipment is operating, these four sensors simultaneously monitor the target area. One sensor counts the number of ultraviolet flashes, two sensors specifically capture the intensity of infrared radiation emitted by carbon dioxide and water vapor in the flame, and the last sensor focuses on ordinary thermal radiation in the environment. These four light signals are converted into digital signals and simultaneously read by the equipment, serving as the basis for subsequent data analysis to determine whether a fire has occurred.

[0057] S2, perform pulse density analysis on the ultraviolet pulse signal to obtain the ultraviolet feature determination result.

[0058] In some embodiments, step S2 (performing pulse density analysis on the ultraviolet pulse signal to obtain ultraviolet feature determination results) includes:

[0059] The ultraviolet pulse density of the ultraviolet pulse signal per unit time is calculated based on the time window integration method;

[0060] The ultraviolet pulse density is calculated using the following formula.

[0061]

[0062] in, For the integration time window, The ultraviolet pulse density is positively correlated with the flame combustion intensity. For the first The number of effective pulses within a cycle. When the condition is met... Furthermore, the pulse frequency and duration conform to the time-domain characteristics, i.e. Upon activation, an alarm is immediately triggered, enabling close-range, high-intensity flame detection. If the ultraviolet signal frequency does not reach the set threshold A but reaches the threshold a, Immediately, a multispectral feature fusion decision is made, in which... The second preset threshold, The first preset threshold, This refers to the current moment.

[0063] If the ultraviolet pulse density is determined to be greater than a first preset threshold and the duration meets the preset time domain characteristics, then an ultraviolet feature determination result for direct alarm is generated.

[0064] If the ultraviolet pulse density is not greater than the first preset threshold, but is greater than the second preset threshold, then an ultraviolet feature flag bit that needs to be fused is generated.

[0065] It's important to note that in the instant a fire occurs, especially a violent combustion like an oil and gas explosion, extremely strong ultraviolet radiation is released. The old method used a microcontroller to queue and process the data, which was too slow. Therefore, the processing equipment in this method monitors the ultraviolet radiation in real time. If the ultraviolet intensity suddenly spikes, it doesn't waste time waiting for infrared signal analysis results; it directly determines it as a fire and triggers an alarm. This approach allows for extremely rapid response during a deflagration.

[0066] Among them, the time window integration method is a method for statistically analyzing signal strength. It generally involves setting an extremely short time period, such as a few milliseconds, and then counting the number of electrical pulses received within that time period. Ultraviolet pulse density is an indicator for measuring the intensity of ultraviolet radiation, generally referring to the number of effective pulses received per unit time. The first preset threshold is a pre-set value for determining whether an immediate alarm is needed. It can be manually set based on actual conditions and generally refers to the pulse value standard corresponding to a strong fire or deflagration. The second preset threshold is a preset value for determining whether a fire is suspected. It can also be manually set and generally refers to the pulse value standard corresponding to an early, weak fire. The preset time domain characteristic is a confirmation mechanism to prevent false alarms. It generally requires high-intensity signals to appear continuously a specific number of times or for a specific duration to eliminate momentary interference from lighters, etc.

[0067] Understandably, during implementation, the electrical pulses output by the ultraviolet sensor are directly connected to the pins of the FPGA chip. An internal counter in the FPGA counts the number of pulses received every very short time window, such as 10 milliseconds. If the chip detects an unusually high number of pulses, exceeding a first preset threshold, and this high number persists for several consecutive time windows, the chip determines it's a deflagration and instantly outputs an alarm signal. If the pulse count isn't as high, but still exceeds a second preset threshold, the chip determines it might be a small flame, records this information, marks it, and then notifies the infrared processing unit for verification. This completes the tiered judgment process.

[0068] S3, based on the background interference monitoring signal, the background components of the first infrared band signal and the second infrared band signal are removed respectively to obtain the first infrared feature value and the second infrared feature value.

[0069] Background component removal is a data purification calculation process that subtracts a certain proportion of background interference signals from the flame characteristic signal. The first and second infrared characteristic values ​​are obtained after the above subtraction operation, representing the pure carbon dioxide and water molecule radiation intensity after removing environmental interference.

[0070] For example, background radiation compensation. This utilizes sensor data in the 4.8μm band. Background interference was removed from the flame characteristic bands of 4.35 μm and 2.7 μm to obtain a purer flame radiation intensity. and :

[0071]

[0072] in, For a purer flame characteristic wavelength, 4.35μm. To achieve a purer flame characteristic wavelength of 2.7μm, compensation coefficients α and β are calibrated experimentally, or can be preset artificially. Background radiation compensation can significantly reduce interference from heaters, infrared spotlights, etc.

[0073] Before the step of removing background components from the first infrared band signal and the second infrared band signal respectively based on the background interference monitoring signal to obtain the first infrared feature value and the second infrared feature value, the method further includes:

[0074] The first infrared band signal, the second infrared band signal, and the background interference monitoring signal are subjected to moving average filtering.

[0075] It's important to note that the raw infrared signals returned by sensors often contain a lot of jumbled fluctuation noise, making calculations directly using this rough data inaccurate. More importantly, heat sources in the environment, such as heaters and halogen lamps, also emit infrared radiation, which can easily be mistaken for fire. Therefore, the data is first smoothed through filtering. Then, using the 4.8-micron band as a reference, the background interference signal is used to subtract the false signals generated by environmental heat sources from the total signal, retaining only the true flame signal and effectively filtering out environmental interference.

[0076] Moving average filtering is a calculation method that smooths out data. It generally involves adding up several recently collected data points to calculate an average, and using this average to represent the current value, thereby smoothing out occasional noise.

[0077] To suppress environmental noise, the three-band infrared signals are processed using the following formula through moving average filtering:

[0078]

[0079] Among them, by taking The arithmetic mean of consecutive sampled values ​​can effectively suppress random noise and preserve the true trend of infrared radiation variation. This is the average radiation intensity after filtering. For the first The original value of the sampling, Infrared band identification, For sampling sequence number, This is the upper limit for the number of consecutive sampled values.

[0080] Understandably, the FPGA chip processes these three infrared data streams in two steps. The first step is filtering: the chip continuously captures data from several sampling points, for example, five, and calculates their arithmetic mean. After this processing, the originally jagged, fluctuating signal becomes a smooth curve. The second step is compensation: after obtaining the smoothed data, background radiation compensation is performed. For example, it subtracts the sensor data in the 4.8μm band from the signal values ​​at 4.35μm and 2.7μm, respectively. This subtraction operation acts like a filter, canceling out the signal components belonging to the background heat source, leaving only the characteristic values ​​truly belonging to the flame.

[0081] S4. Perform multispectral fusion logic operation based on the ultraviolet feature determination result, the first infrared feature value and the second infrared feature value to generate flame detection result.

[0082] It should be noted that single-band signals are susceptible to environmental interference, leading to false alarms. For example, sunlight can interfere with ultraviolet radiation, or heat sources can interfere with infrared radiation. To ensure accurate judgment, evidence seen by both ultraviolet and infrared radiation needs to be considered together for comprehensive evaluation. The advantage of this approach is that a fire is only identified when multiple characteristics appear simultaneously or corroborate each other, thus improving the reliability of the alarm.

[0083] In some embodiments, step S4 (performing multispectral fusion logic operations based on the ultraviolet feature determination result, the first infrared feature value, and the second infrared feature value to generate a flame detection result) includes:

[0084] The first infrared feature value and the second infrared feature value are compared with preset thresholds respectively to generate a binarized first infrared feature flag and second infrared feature flag;

[0085] It's important to note that infrared signature values ​​are continuously changing numbers, such as 0.5 or 3.8. These numbers are inconvenient for direct logical judgments. Therefore, these complex numbers are simplified into 0s and 1s. A value exceeding a threshold is recorded as 1 (indicating fire), and a value below that threshold is recorded as 0 (indicating no fire). This simplification makes subsequent circuit logic judgments very fast and less prone to errors.

[0086] The preset threshold can be the average value obtained after multiple experimental calibrations, or it can be a value preset by humans based on the actual situation.

[0087]

[0088] The above formula is the decision function for flame recognition, which converts the continuous signal from the sensor into a binary feature label. , , All of them are preset thresholds, that is The ultraviolet detection threshold is... The threshold value is set at 4.35μm in the infrared band. The threshold value for the 2.7μm infrared band is the average value obtained after multiple experimental calibrations. For indicator functions, It can be a binarized result of ultraviolet feature determination, that is, an ultraviolet feature marker. This is the value of the ultraviolet pulse density, which is calculated in step S2 using the time window integration method. It can be the first infrared signature. It can be a second infrared signature.

[0089] Based on the first infrared feature marker, the second infrared feature marker, and the binarized ultraviolet feature determination result, a triple Boolean fusion logic is used to generate the flame detection result.

[0090] In some embodiments, the step (generating flame detection results using triple Boolean fusion logic based on the first infrared feature marker, the second infrared feature marker, and the binarized ultraviolet feature determination result) includes:

[0091] When both the ultraviolet feature determination result and the first infrared feature flag are true, a flame detection result is generated;

[0092] When both the ultraviolet feature determination result and the second infrared feature mark are true, a flame detection result is generated.

[0093] When both the first infrared feature marker and the second infrared feature marker are determined to be true, a flame detection result is generated.

[0094] It is easy to understand that if any two combinations are true, then a flame detection result will be generated.

[0095] Based on the above embodiments, it also includes:

[0096] In response to the flame detection result, the flame area is acquired, and the activation device is determined based on the flame area.

[0097] In some embodiments, the step of (determining the activation device based on the flame area) includes:

[0098] Identify the regional outline of the flame area and obtain the spray range of each fire extinguishing device;

[0099] The activation device is determined based on the spray range and area contour.

[0100] In some embodiments, the step of (determining the activation device based on the spray range and area contour) includes:

[0101] The fire extinguishing device corresponding to the spray range that intersects with the area outline is used as the activation device.

[0102] See Figure 2 The device of the present invention includes a power supply module, an optical lens assembly, a multi-band signal conditioning module, an FPGA core processing module, and an output module;

[0103] The power module connects to the multi-band signal conditioning module, the FPGA core processing module, and the output module to provide operating voltage;

[0104] The optical lens assembly is used to receive external light radiation signals;

[0105] The multi-band signal conditioning module connects the sensor corresponding to the optical lens assembly to the FPGA core processing module.

[0106] The FPGA core processing module connects to the multi-band signal conditioning module and the output module, and is used to synchronously acquire data from each band and execute in parallel the decision logic of rapid early warning in the ultraviolet channel, interference suppression in the infrared channel, and multispectral feature fusion.

[0107] The output module is used to output alarm signals.

[0108] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the methods provided in the various embodiments described above.

[0109] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0110] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0111] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A flame detection method using an ultraviolet-infrared fusion detection structure, characterized in that, include: Acquire ultraviolet pulse signals, first infrared band signals, second infrared band signals, and background interference monitoring signals of the target scene, including: Acquire ultraviolet pulse signals, first infrared band signals, second infrared band signals, and background interference monitoring signals of the target scene; The first infrared band signal corresponds to the carbon dioxide radiation characteristics, the second infrared band signal corresponds to the water molecule radiation characteristics, and the background interference monitoring signal corresponds to the environmental background thermal radiation characteristics. Pulse density analysis was performed on the ultraviolet pulse signal to obtain the ultraviolet feature determination result; Background components are removed from the first infrared band signal and the second infrared band signal respectively based on the background interference monitoring signal to obtain the first infrared feature value and the second infrared feature value; Based on the ultraviolet feature determination result, the first infrared feature value and the second infrared feature value, a multispectral fusion logic operation is performed to generate a flame detection result; The step of performing pulse density analysis on the ultraviolet pulse signal to obtain ultraviolet feature determination results includes: The ultraviolet pulse density of the ultraviolet pulse signal per unit time is calculated based on the time window integration method; If the ultraviolet pulse density is determined to be greater than a first preset threshold and the duration meets the preset time domain characteristics, then an ultraviolet feature determination result for direct alarm is generated. If the ultraviolet pulse density is not greater than the first preset threshold, but is greater than the second preset threshold, then an ultraviolet feature flag bit that needs to be fused is generated; Before the step of removing background components from the first infrared band signal and the second infrared band signal respectively based on the background interference monitoring signal to obtain the first infrared feature value and the second infrared feature value, the method further includes: The first infrared band signal, the second infrared band signal, and the background interference monitoring signal are subjected to moving average filtering. The step of performing multispectral fusion logic operations based on the ultraviolet feature determination result, the first infrared feature value, and the second infrared feature value to generate a flame detection result includes: The first infrared feature value and the second infrared feature value are compared with preset thresholds respectively to generate a binarized first infrared feature flag and second infrared feature flag; Based on the first infrared feature marker, the second infrared feature marker, and the binarized ultraviolet feature determination result, a triple Boolean fusion logic is used to generate the flame detection result. The flame detection result is generated using triple Boolean fusion logic based on the first infrared feature marker, the second infrared feature marker, and the binarized ultraviolet feature determination result, including: When both the ultraviolet feature determination result and the first infrared feature flag are true, a flame detection result is generated; When both the ultraviolet feature determination result and the second infrared feature flag are true, a flame detection result is generated. When both the first infrared feature marker and the second infrared feature marker are determined to be true, a flame detection result is generated.

2. The method according to claim 1, characterized in that... It also includes: In response to the flame detection result, the flame area is acquired, and the activation device is determined based on the flame area.

3. The method according to claim 2, characterized in that... , The activation device determined based on the flame area includes: Identify the regional outline of the flame area and obtain the spray range of each fire extinguishing device; The activation device is determined based on the spray range and area contour.

4. The method according to claim 3, characterized in that... , The activation device determined based on the spray range and area contour includes: The fire extinguishing device corresponding to the spray range that intersects with the area outline is used as the activation device.

5. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, is used to implement the method described in any one of claims 1 to 4.

Images