Flame identification method based on multiband infrared signal fusion and flame detector

Abstract

The invention relates to the technical field of infrared flame detectors, and particularly discloses a flame recognition method based on multiband infrared signal fusion. The method comprises the steps that S1, a main detection channel periodically obtains real-time main infrared signals, and three reference channels periodically obtain real-time reference infrared signals; s2, when the peak value of the real-time main infrared signal is larger than a fire behavior threshold value, spectral analysis is conducted on the real-time main infrared signal, the peak value main frequency is extracted, and the peak value main frequency is the frequency corresponding to the frequency band with the maximum power spectral density; s3, judging whether the peak main frequency is in an early warning frequency interval or not, if so, performing spectral analysis on the three real-time reference infrared signals acquired by the three reference channels, and extracting the peak main frequency of each real-time reference infrared signal; and S4, judging whether the peak main frequency of at least one real-time reference infrared signal is in the early warning frequency interval or not, and if so, judging that a fire occurs. According to the method, flame identification of scenes such as kitchens using artificial fire sources can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of infrared flame detectors, and in particular to a flame recognition method and a flame detector based on multi-band infrared signal fusion. Background Art

[0002] Liquefied petroleum gas (LPG) is a widely used fuel in the restaurant industry. However, due to improper management and other factors, accidents such as LPG tank fires and explosions occur frequently. To improve fire safety in the restaurant industry and reduce fire risks during operations, it is necessary to conduct fire monitoring in areas where LPG is used to promptly detect unexpected fires and minimize fire losses.

[0003] When a flame burns, it produces a peak in the 4.4μm infrared band due to the effect of carbon dioxide. This is a distinct characteristic of flames, and the point-type infrared flame detectors currently used on the market also use this principle to achieve flame identification. Considering that interfering heat sources often exist in daily use environments, some interfering heat sources also emit infrared radiation in the 4.4μm band, which can interfere with flame identification. Therefore, some point-type infrared flame detectors use dual or triple bands to simultaneously identify infrared light intensities at other wavelengths, inferring the presence of interfering heat sources based on the infrared intensity of these other wavelengths.

[0004] CN115762042B discloses a detector that uses three narrow-band detection channels and one wide-band detection channel to jointly perform flame identification. The presence of a flame is determined by the ratio of the energy sum of the three narrow-band detection channels in a preset time window to the threshold value, and the influence of interfering heat sources is eliminated.

[0005] However, the flame of a gas stove during normal use will also produce a peak in the 4.4μm infrared band. It is difficult to distinguish the normal use of a gas stove from the accidental combustion of other non-fuel substances by comparing the infrared light intensity alone. Summary of the Invention

[0006] In order to solve the technical problem of the inability to accurately identify interfering heat sources in the prior art, the present application provides a flame recognition method and a flame detector based on multi-band infrared signal fusion, wherein the flame recognition method based on multi-band infrared signal fusion includes the following steps:

[0007] S1: The main detection channel periodically acquires real-time main infrared signals, and the three reference channels periodically acquire real-time reference infrared signals;

[0008] S2. When the peak value of the real-time main infrared signal is greater than the fire threshold, performing spectrum analysis on the real-time main infrared signal to extract the peak main frequency, where the peak main frequency is the frequency corresponding to the frequency band with the largest power spectrum density;

[0009] S3, determining whether the peak main frequency is within the warning frequency range, and if so, performing spectrum analysis on the three real-time reference infrared signals to extract the peak main frequency of each real-time reference infrared signal;

[0010] Through the above steps, normal gas use can be distinguished from accidental fire during flame recognition, and accidental fire can be recognized in an environment with artificial flames such as a kitchen.

[0011] Specifically, the following steps are performed to determine whether the peak value of the real-time main infrared signal is greater than the fire threshold:

[0012] S11, preprocessing the real-time main infrared signal, including bandpass filtering and baseline correction;

[0013] S12, performing peak detection on the pre-processed real-time main infrared signal to obtain all peak values ​​within the detection period;

[0014] S13. Filter peak values ​​greater than the fire threshold, calculate the ratio of the number of peak values ​​greater than the fire threshold to the total number of peak values, and if the ratio exceeds the warning ratio, determine that the peak value of the real-time main infrared signal is greater than the fire threshold.

[0015] By comparing the peak ratios, the influence of interference factors such as sampling noise on the judgment results can be reduced, thereby improving the accuracy of the judgment.

[0016] Furthermore, when the peak main frequency of the real-time main infrared signal is not in the fire warning range, the following steps are performed:

[0017] S31, calculating the main frequency matching degree, kurtosis and harmonic intensity of the real-time main infrared signal;

[0018] S32, performing Hilbert transform on the real-time main infrared signal to obtain an envelope signal of the real-time main infrared signal, and calculating a ratio of a standard deviation to a mean of the envelope signal;

[0019] S33, constructing a weighted decision model based on the main frequency matching degree, kurtosis, harmonic intensity, and the ratio of the standard deviation to the mean of the envelope signal;

[0020] S34. Calculate the fire condition matching degree using the weighted decision model. When the fire condition matching degree is greater than a first threshold, determine that a fire has occurred.

[0021] Envelope signal analysis can effectively extract the amplitude characteristics of flame flickering and quantify the amplitude. By combining it with the main frequency matching, kurtosis, and harmonic intensity, a comprehensive evaluation is performed on the characteristics of the collected real-time main infrared signal, avoiding misjudgment caused by a single indicator and improving the accuracy of flame recognition.

[0022] Furthermore, when the peak main frequencies of the three real-time reference infrared signals are all outside the warning frequency range, the following steps are performed:

[0023] S41, searching for a matching interference heat source model combination based on the real-time main infrared signal and the three real-time reference infrared signals, wherein the interference heat source model combination is composed of infrared characteristic models of multiple interference heat sources, and the infrared characteristic model is infrared light intensity information radiated by a single interference heat source measured by a main detection channel and three reference channels;

[0024] S42. If an interfering heat source model combination exists, no fire warning is issued; if not, it is determined that a fire has occurred.

[0025] The superposition principle of light intensity is used to determine whether the infrared light intensity in the current environment is composed of multiple interfering heat source models, thereby determining whether there is an unexpected fire and improving the sensitivity of flame recognition.

[0026] Specifically, the following steps are performed to find a matching interference heat source model combination:

[0027] S411, constructing a real-time infrared vector according to the real-time main infrared signal and the real-time reference infrared signal;

[0028] S412, constructing an interference heat source feature vector for the infrared feature model of each interference heat source;

[0029] S413, constructing a matching equation according to the real-time infrared vector and the plurality of interference heat source feature vectors;

[0030] S414. Determine whether the matching equation has a non-zero real number solution. If so, a matching interference heat source model combination exists.

[0031] Specifically, each component of the real-time infrared vector represents the proportion of the light intensity of the main detection channel and the three reference channels in the total light intensity, and the total light intensity is the sum of the light intensities collected by the main detection channel and the three reference channels.

[0032] Specifically, the interference heat source characteristic vector is obtained by the following steps:

[0033] S355. Placing an interfering heat source in a laboratory environment, wherein the laboratory environment is set so that, except for the interfering heat source, there are no other heat sources that can be detected by the main detection channel and the three reference channels;

[0034] S356. Using the main detection channel and three reference channels to collect infrared light intensity signals radiated by the interfering heat source, preprocessing and spectrum analyzing the infrared light intensity signals to obtain an infrared feature model;

[0035] S357. Extract the peak main frequency of the main detection channel and the light intensity ratio of the main detection channel and the three reference channels from the infrared characteristic model to construct an interference heat source feature vector.

[0036] The present invention also provides a flame detector that adopts the above-mentioned flame identification method, including: an infrared acquisition module and a data processing module, the infrared acquisition module includes a main detection channel and three reference channels, the main detection channel and the three reference channels are used to collect real-time infrared light intensity data radiated by various heat sources in the environment, and the data processing module is used to determine whether a fire occurs based on the real-time multi-band infrared light intensity data collected by the main detection channel and the three reference channels.

[0037] Specifically, the main detection channel collects infrared light intensity in the 4.4 μm band, and the three reference channels collect infrared light intensity in the 5.3 μm, 3.8 μm, and 2.2 μm bands respectively.

[0038] The technical effects and advantages of the present invention are as follows: flame identification is performed by the above-mentioned method, spectrum analysis is performed on infrared signals in four bands, and the peak main frequency of the multi-band is used to determine whether there is combustion of other non-fuel substances, thereby distinguishing the normal use of the gas stove from accidental fire, and realizing flame identification in scenes where artificial fire sources are used, such as in the kitchen. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the overall process of the flame identification method of the present invention.

[0040] Figure 2 This is a flow chart for judging fire conditions based on a weighted decision model in the method of the present invention.

[0041] Figure 3 The present invention provides a flowchart for finding a matching interference heat source model combination in the method of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] Example 1

[0044] refer to Figure 1 A flame recognition method based on multi-band infrared signal fusion is provided in a first embodiment of the present invention to distinguish between flames generated by normal gas and flames generated by accidental fire during flame recognition, including the following steps:

[0045] S1: The main detection channel periodically acquires real-time main infrared signals, and the three reference channels periodically acquire real-time reference infrared signals;

[0046] S2. When the peak value of the real-time main infrared signal is greater than the fire threshold, the real-time main infrared signal is subjected to spectrum analysis to extract the peak main frequency, which is the frequency corresponding to the frequency band with the largest power spectrum density;

[0047] S3. Determine whether the peak main frequency is within the warning frequency range. If so, perform spectrum analysis on the three real-time reference infrared signals obtained by the three reference channels to extract the peak main frequency of each real-time reference infrared signal.

[0048] S4. Determine whether the peak main frequency of at least one real-time reference infrared signal is within the warning frequency range. If so, determine that a fire has occurred and issue a fire warning.

[0049] When a flame burns, it not only produces a peak in the 4.4μm band but also often flickers due to factors such as eddy currents. The flicker frequency is often between 1 and 30Hz. This is what distinguishes flames from other heat sources. Therefore, when the peak value of the real-time main infrared signal exceeds the fire threshold, the real-time main infrared signal is determined to have flickering. If so, it indicates the presence of a flame in the environment. Next, it is necessary to further determine whether the flame is an accidental fire to distinguish between normal gas use and accidental fires.

[0050] During normal gas use, the gas burns almost completely, resulting in a peak in the 4.4μm band. Although gas use often generates high-temperature fumes or water vapor, and the infrared radiation emitted by these gases peaks near the 2.9μm band, there is no flickering, and the infrared radiation fluctuates slowly. Accidental fires are often accompanied by the combustion of non-fuel materials, and different materials emit different infrared radiation when burning. Therefore, in addition to peaks near the 4.4μm band, these fires may also produce peaks in other bands. For example, the infrared radiation emitted by high-temperature carbon black produced during polyethylene melting peaks at 3.4μm, while the infrared radiation emitted by burning polyvinyl chloride peaks at around 5.7μm. The infrared radiation emitted by burning materials such as cotton and linen peaks at around 2.9μm. Therefore, it is necessary to analyze the light intensity signals at other wavelengths to determine whether flickering is also present. If flickering is also present in the real-time infrared signals collected on other reference channels, it indicates the combustion of other non-fuel materials, and the fire can be determined to be an accidental fire.

[0051] Therefore, through the above steps, normal gas use can be distinguished from accidental fire during flame recognition, and accidental fire can be recognized in an environment with artificial flames such as a kitchen.

[0052] Point-type infrared flame detectors use pyroelectric sensors to sample infrared rays. During the sampling process, due to factors such as the fluctuation of the infrared signal itself and interference from clutter in the circuit, the real-time infrared signal obtained is a frequently fluctuating curve. Therefore, directly identifying flames based on the peak value in the curve will result in large errors. The original infrared signal needs to be processed to obtain the peak value that can be used for flame identification.

[0053] Specifically, in step S1, the following steps are performed to determine whether the peak value of the real-time main infrared signal is greater than the fire threshold:

[0054] S11. Preprocessing the real-time main infrared signal, including bandpass filtering and baseline correction, to suppress high-frequency noise and low-frequency drift, and remove the DC component in the ambient thermal radiation, retaining only the changing part;

[0055] S12, performing peak detection on the pre-processed real-time main infrared signal to obtain all peak values ​​within the detection period;

[0056] S13. Filter peak values ​​greater than the fire threshold, calculate the ratio of the number of peak values ​​greater than the fire threshold to the total number of peak values, and if the ratio exceeds the warning ratio, determine that the peak value of the real-time main infrared signal is greater than the fire threshold.

[0057] After experiments and practical applications, the ratio can be set to 60%, which can achieve a good balance between accuracy and real-time performance.

[0058] Specifically, as a preferred embodiment, the main detection channel of the present invention collects infrared light intensity in the 4.4 μm band, and the three reference channels collect infrared light intensity in the 5.3 μm, 3.8 μm, and 2.2 μm bands respectively.

[0059] Considering that other interfering heat sources will also generate infrared rays in the 4.4μm main band, and there is a high probability that there will be fluctuations of different frequencies when radiating infrared rays (not flickering, and the fluctuation frequency is not between 1-30Hz), it may have a certain impact on the spectrum analysis results of the real-time main infrared signal, resulting in a misjudgment of the fire situation.

[0060] refer to Figure 2 When the peak main frequency of the real-time main infrared signal is not in the fire warning range, perform the following steps:

[0061] S31, calculating the main frequency matching degree, kurtosis and harmonic intensity of the real-time main infrared signal;

[0062] S32, performing Hilbert transform on the real-time main infrared signal to obtain an envelope signal of the real-time main infrared signal, and calculating a ratio of a standard deviation to a mean of the envelope signal;

[0063] S33, constructing a weighted decision model based on the main frequency matching degree, kurtosis, harmonic intensity, and the ratio of the standard deviation to the mean of the envelope signal;

[0064] S34. Calculate the fire condition matching degree through a weighted decision model. When the fire condition matching degree is greater than a first threshold, determine that a fire has occurred.

[0065] Envelope signal analysis can effectively extract the amplitude characteristics of flame flickering and quantify the amplitude. By combining it with the main frequency matching, kurtosis, and harmonic intensity, a comprehensive evaluation is performed on the characteristics of the collected real-time main infrared signal, avoiding misjudgment caused by a single indicator and improving the accuracy of flame recognition.

[0066] As a preferred implementation, the main frequency matching degree can be obtained by the following steps:

[0067] S311, perform spectrum analysis on the real-time main infrared signal to determine the peak main frequency, which can be specifically performed according to the following formula:

[0068]

[0069] Where N is the number of sampling points, X[n] is the envelope signal sampling point, which is obtained by performing Hilbert transform on the real-time main infrared signal, W[n] is the Hanning window function, P[k] is the power spectral density at frequency index k, and j is the imaginary unit;

[0070] Peak main frequency f dom Calculated by the following formula:

[0071]

[0072] That is, the frequency value when the power spectrum density is the largest is the peak main frequency f dom Ω is the characteristic frequency band of the flame, which can generally be defined as [1Hz, 30Hz]. It means searching for possible flame flicker frequency components within this range and eliminating interference signals. Similarly, the peak main frequency of the real-time reference infrared signal can also be obtained through this step;

[0073] S312: Calculate the main frequency matching degree according to the peak main frequency. Specifically, the calculation can be performed according to the following formula:

[0074]

[0075] In the formula, [f L , f H ] is the target frequency band, that is, the flicker frequency range of the ideal flame combustion, generally taken as fL =5Hz, f H =15Hz, S is the Gaussian attenuation scale parameter, which can be set to 5Hz in most application scenarios.

[0076] Specifically, the kurtosis of the real-time main infrared signal can be calculated using the following formula:

[0077]

[0078] Where X is the envelope signal, μ is the mean value of the envelope signal, σ is the standard deviation of the envelope signal, E[(X-μ) 4 ] is (X-μ) 4 The expected value of the two is C v The calculation is as follows:

[0079]

[0080] In practical applications, the acquisition of light intensity signals is mostly performed by discrete sampling, so the kurtosis K S The calculation can be done using the following formula:

[0081]

[0082] Where, is the mean value of the envelope signal, and N is the number of sampling points.

[0083] Generally, the light intensity that the detector can receive decreases as the distance between the heat source and the detector increases. In order to eliminate the influence of distance on the judgment result, the kurtosis is normalized to obtain the unit kurtosis K. F :

[0084]

[0085] K L The lower limit of the typical flame peak degree is usually K L =3,K H The upper limit of the typical flame peak is usually K H =8.

[0086] Specifically, the harmonic intensity H S Calculated by the following formula:

[0087]

[0088] Where ∈ is a small constant to prevent the divisor from being zero, H2 is the double frequency of the main frequency (i.e. 2×f dom ) component, H3 (i.e. 3×f dom ) is the harmonic intensity of the triple frequency component of the main frequency, F is the fundamental wave energy, and is calculated by the following formula:

[0089]

[0090] Where, f s is the sampling frequency, and Δf is the search bandwidth.

[0091] The harmonic intensity of the double frequency component and the triple frequency component is calculated by the following formula:

[0092]

[0093] Wherein, when m=2, it is the double frequency component, and when m=3, it is the triple frequency component.

[0094] Based on the above analysis, the weighted decision model can be constructed as follows:

[0095] S F =αC v +βM f +γK F +δH s

[0096] Where α, β, γ, and δ are weight coefficients of each item, and α is generally taken as 0.4, β as 0.3, γ as 0.2, and δ as 0.1.

[0097] S F That is the fire matching degree. Generally, when the fire matching degree S F When it is >0.65 (the first threshold), it can be determined that a fire has occurred.

[0098] In step S4, the fire is determined by determining whether the peak main frequency of at least one real-time reference infrared signal is within the warning frequency range. This can lead to misjudgment. In some special cases (such as the burning of a small flame), while the real-time main infrared signal can clearly detect flickering characteristics, other bands cannot effectively identify clear flickering characteristics. Therefore, further flame identification is required.

[0099] Specifically, refer to Figure 3 , when the peak main frequencies of the three real-time reference infrared signals are all outside the warning frequency range, perform the following steps:

[0100] S41. Searching for a matching interference heat source model combination based on the real-time main infrared signal and the three real-time reference infrared signals. The interference heat source model combination is composed of infrared characteristic models of multiple interference heat sources. The infrared characteristic model is infrared light intensity information radiated by a single interference heat source measured by the main detection channel and the three reference channels.

[0101] S42. If an interfering heat source model combination exists, no fire warning is issued; if not, it is determined that a fire has occurred.

[0102] The increase in light intensity conforms to the principle of linear superposition; the light intensities generated by each light source are linearly superimposed in the sensor and do not affect each other. Because the infrared signals radiated by different interfering heat sources have different distributions across the four bands, when identifying flames, a separate infrared signature model can be established for the infrared signal generated by each common interfering heat source. When there is no unexpected fire, the real-time light intensity distribution collected should be linearly combined using the infrared signature models of multiple interfering heat sources.

[0103] Specifically, refer to Figure 3 , searching for matching interference heat source model combinations can be performed using vector operations:

[0104] S411, constructing a real-time infrared vector according to the real-time main infrared signal and the real-time reference infrared signal;

[0105] S412, constructing an interference heat source feature vector for the infrared feature model of each interference heat source;

[0106] S413, constructing a matching equation based on the real-time infrared vector and multiple interference heat source feature vectors;

[0107] S414. Determine whether the matching equation has a non-zero real number solution. If so, a matching interference heat source model combination exists.

[0108] Specifically, considering that the infrared signals radiated by different interfering heat sources have different phases, and the influence of the phase difference on the final light intensity should also be considered when the light intensity is superimposed, the real-time infrared vector can be constructed in the following way:

[0109] F S =(a1 min , a1 max , a2 min , a2 max , a3 min , a3 max , a4 min , a4 max ,f1)

[0110] Among them, a1 min , a1 max They represent the minimum and maximum proportions of the real-time main infrared signal's light intensity in the total light intensity collected by all channels, f1 represents the peak main frequency of the real-time main infrared signal, a2 min , a2 max , a3 min , a3 max , a4 min ,a4 max They respectively represent the maximum and minimum proportions of the light intensities of the three reference channels in the total light intensities collected by all channels.

[0111] The form of the interference heat source feature vector and the data represented by each component should be consistent with the real-time infrared vector. In practical applications, interference heat sources may include ovens, induction cookers, lighting fixtures, sunlight, people, gas stoves, etc. Each interference heat source can establish the above interference heat source feature vector. Based on the above heat source feature vector, the interference heat source model combination M can be constructed. S :

[0112]

[0113] Where, F n is the interference heat source characteristic vector of the nth interference heat source, φ n is the combination coefficient corresponding to the interference heat source.

[0114] Based on the above interference heat source model combination and real-time infrared vector, the following matching equation can be constructed:

[0115] F S -M S =0

[0116] When there is a matching combination of interference heat source models, the homogeneous linear equations have non-zero real solutions.

[0117] Specifically, the interference heat source feature vector is constructed by the following steps:

[0118] S355. Place an interfering heat source in a laboratory environment. In addition to the interfering heat source, there are no other heat sources in the laboratory environment that can be detected by the main detection channel and the three reference channels.

[0119] S356. Using the main detection channel and three reference channels to collect infrared light intensity signals radiated by the interfering heat source, preprocessing and spectrum analysis are performed on the infrared light intensity signals to obtain an infrared feature model;

[0120] S357. Extract the peak main frequency of the main detection channel and the light intensity ratio of the main detection channel and the three reference channels from the infrared feature model to construct the interference heat source feature vector.

[0121] The above method is used for flame recognition, and the spectrum analysis of infrared signals in four bands is performed. The peak main frequency of multiple bands is used to determine whether there is combustion of other non-fuel substances, thereby distinguishing the normal use of gas stoves from accidental fires, and realizing flame recognition in scenes where artificial fire sources are used, such as kitchens.

[0122] Example 2

[0123] Based on the flame identification method provided in the first embodiment, the present invention further provides a flame detector, comprising: an infrared acquisition module and a data processing module;

[0124] The infrared acquisition module includes a main detection channel and three reference channels. The main detection channel and the three reference channels are used to collect real-time infrared light intensity data radiated by various heat sources in the environment. The data processing module is used to determine whether a fire occurs based on the real-time multi-band infrared light intensity data collected by the main detection channel and the three reference channels.

[0125] Specifically, the main detection channel collects infrared light intensity in the 4.4μm band, and the three reference channels collect infrared light intensity in the 5.3μm, 3.8μm, and 2.2μm bands respectively.

[0126] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A flame recognition method based on multi-band infrared signal fusion, characterized in that: The following steps are involved: S1: The main detection channel periodically acquires real-time main infrared signals, and the three reference channels periodically acquire real-time reference infrared signals; S2. When the peak value of the real-time main infrared signal is greater than the fire threshold, performing spectrum analysis on the real-time main infrared signal to extract the peak main frequency, where the peak main frequency is the frequency corresponding to the frequency band with the largest power spectrum density; S3, determining whether the peak main frequency is within the warning frequency range, and if so, performing spectrum analysis on the three real-time reference infrared signals to extract the peak main frequency of each real-time reference infrared signal; S4. Determine whether the peak main frequency of at least one of the real-time reference infrared signals is within the warning frequency range. If so, determine that a fire has occurred.

2. The method according to claim 1, characterized in that The following steps are used to determine whether the peak value of the real-time main infrared signal is greater than the fire threshold: S11, preprocessing the real-time main infrared signal, including bandpass filtering and baseline correction; S12, performing peak detection on the pre-processed real-time main infrared signal to obtain all peak values ​​within the detection period; S13. Filter peak values ​​greater than the fire threshold, calculate the ratio of the number of peak values ​​greater than the fire threshold to the total number of peak values, and if the ratio exceeds the warning ratio, determine that the peak value of the real-time main infrared signal is greater than the fire threshold.

3. The method according to claim 1, characterized in that When the peak main frequency of the real-time main infrared signal is not in the fire warning range, the following steps are performed: S31, calculating the main frequency matching degree, kurtosis and harmonic intensity of the real-time main infrared signal; S32, performing Hilbert transform on the real-time main infrared signal to obtain an envelope signal of the real-time main infrared signal, and calculating a ratio of a standard deviation to a mean of the envelope signal; S33, constructing a weighted decision model based on the main frequency matching degree, kurtosis, harmonic intensity, and the ratio of the standard deviation to the mean of the envelope signal; S34. Calculate the fire condition matching degree using the weighted decision model. When the fire condition matching degree is greater than a first threshold, determine that a fire has occurred.

4. The method according to claim 1, wherein When the peak main frequencies of the three real-time reference infrared signals are all outside the warning frequency range, the following steps are performed: S41, searching for a matching interference heat source model combination based on the real-time main infrared signal and the three real-time reference infrared signals, wherein the interference heat source model combination is composed of infrared characteristic models of multiple interference heat sources, and the infrared characteristic model is infrared light intensity information radiated by a single interference heat source measured by a main detection channel and three reference channels; S42. If an interfering heat source model combination exists, no fire warning is issued; if not, it is determined that a fire has occurred.

5. The method according to claim 4, characterized in that Find a matching interference heat source model combination through the following steps: S411, constructing a real-time infrared vector according to the real-time main infrared signal and the real-time reference infrared signal; S412, constructing an interference heat source feature vector for the infrared feature model of each interference heat source; S413, constructing a matching equation according to the real-time infrared vector and the plurality of interference heat source feature vectors; S414. Determine whether the matching equation has a non-zero real number solution. If so, a matching interference heat source model combination exists.

6. The method according to claim 5, characterized in that Each component of the real-time infrared vector represents the proportion of the light intensity of the main detection channel and the three reference channels in the total light intensity. The total light intensity is the sum of the light intensities collected by the main detection channel and the three reference channels.

7. The method according to claim 5, characterized in that The interference heat source characteristic vector is obtained by the following steps: S355. Placing an interfering heat source in a laboratory environment, wherein the laboratory environment is set so that, except for the interfering heat source, there are no other heat sources that can be detected by the main detection channel and the three reference channels; S356. Using the main detection channel and three reference channels to collect infrared light intensity signals radiated by the interfering heat source, preprocessing and spectrum analyzing the infrared light intensity signals to obtain an infrared feature model; S357. Extract the peak main frequency of the main detection channel and the light intensity ratio of the main detection channel and the three reference channels from the infrared characteristic model to construct an interference heat source feature vector.

8. A flame detector, using the flame identification method according to any one of claims 1 to 7, characterized in that: include: Infrared acquisition module and data processing module; The infrared acquisition module includes a main detection channel and three reference channels, and the main detection channel and the three reference channels are used to collect real-time infrared light intensity data radiated by various heat sources in the environment; The data processing module is used to determine whether a fire occurs based on the real-time multi-band infrared light intensity data collected by the main detection channel and the three reference channels.

9. The flame detector according to claim 8, characterized in that: The main detection channel collects infrared light intensity in the 4.4 μm band, and the three reference channels collect infrared light intensity in the 5.3 μm, 3.8 μm, and 2.2 μm bands respectively.

Images