Smoke alarm water vapor false alarm prevention system based on double-transmitter and double-waveband

Abstract

The invention belongs to the technical field of smoke alarm false alarm prevention, and particularly discloses a smoke alarm water vapor false alarm prevention system based on double emission and double wave bands, which comprises a signal emission module, a signal receiving analysis module, a propagation environment correction module, a light path pollution compensation module and a judgment early warning module. According to the invention, a dual-band detection technology and an intelligent environment adaptation mechanism are innovatively established, the anti-interference capability is enhanced by adopting a dual-light-source cooperative detection and environment parameter real-time calibration technology, and the influence of environmental factors on the detection performance is reduced in combination with a light pollution self-compensation mechanism; and meanwhile, accurate identification is realized by analyzing the physical characteristic difference of smoke and water vapor, and the risk of environmental misjudgment is remarkably reduced while a real fire behavior is quickly responded by establishing a dynamic grading early warning model, so that the key technical problems that smoke detection is easily interfered and water vapor is confused in a complex scene are systematically solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of anti-false alarm of smoke alarms. Specifically, it relates to a water vapor anti-false alarm system for smoke alarms based on dual-transmitter and dual-band. Background Art

[0002] In daily life, smoke alarms, as important fire warning devices, play a crucial role. However, traditional smoke alarms are often interfered by water vapor, resulting in frequent false alarms, which bring many troubles to people's lives. For example, in the kitchen where a large amount of water vapor is generated during cooking or in the bathroom with high humidity, unnecessary alarms often occur.

[0003] The prior art, such as a high-sensitivity smoke alarm, system and method disclosed in a Chinese invention patent application with the application number 201910813667.6, solves the problem of smoke false alarms caused by temperature changes and dust interference through the signal comparison technology of setting a smoke detection chamber and a reference chamber, combined with the hierarchical detection mechanism of multiple smoke detection chambers.

[0004] Another prior art, such as an anti-false alarm security cloud operation service management system disclosed in a Chinese invention patent application with the application number 202210148127.2, solves the problem of false alarms in the security system caused by single-sensor false triggering or environmental interference through multi-sensor redundancy design, such as the collaborative alarm mechanism of dual smoke alarms and the cloud management platform.

[0005] Regarding the first technical solution, the water vapor anti-false alarm of the smoke alarm mainly relies on the physical isolation comparison between the reference chamber and the smoke detection chamber, and excludes temperature interference through signal differences, but does not directly design a compensation logic for the optical characteristics of water vapor. Regarding the second technical solution, multi-sensor redundancy is used to reduce the false alarm probability, but the signal feature differences between water vapor and smoke are not deeply analyzed, and only repeated detection at the hardware level is relied on. Obviously, there are still the following problems in combination with the above two technical solutions: 1. The prior art does not monitor environmental parameters such as temperature, humidity, and air pressure in real time, and cannot dynamically adjust signal characteristics, resulting in insufficient ability to distinguish water vapor and smoke in complex environments.

[0006] 2. The prior art does not design a compensation mechanism for optical path pollution, and the false alarm rate may increase significantly after long-term use.

[0007] 3. The prior art mainly relies on signal strength or redundant detection, and the dimension is relatively single, making it difficult to accurately distinguish the subtle differences between water vapor and smoke.

[0008] 4. The prior art does not perform timing and path processing on the emission band, and there are other potential influencing factors in subsequent analysis, which leads to weak signal anti-interference ability and resolution ability.

[0009] In summary, the existing technologies still have limitations such as poor environmental adaptability, sensitivity to optical pollution, and rough feature analysis in preventing false alarms caused by water vapor. Summary of the Invention

[0010] In view of this, a water vapor false alarm prevention system for a smoke alarm based on dual - transmitter and dual - band is proposed to solve the limitations in aspects such as poor environmental adaptability, sensitivity to optical pollution, and rough feature analysis in preventing false alarms caused by water vapor in the existing technologies.

[0011] The object of the present invention can be achieved through the following technical solutions: The present invention provides a water vapor false alarm prevention system for a smoke alarm based on dual - transmitter and dual - band. The system includes: A signal transmission module that emits optical signals through two independent transmitters. After synchronizing the emission phases of the two - path optical signals through a timing control circuit, the two - path signals are combined into the same path for propagation through an optical beam combiner.

[0012] A signal reception and analysis module that respectively receives optical signals through two independent photoelectric sensors, extracts multi - dimensional features such as the scattering intensity ratio, time - domain waveform, and frequency - domain energy distribution of the received signals, and establishes a mapping relationship model between the signal features and the target object features.

[0013] A propagation environment correction module that real - time monitors the temperature, humidity, air pressure, and electromagnetic noise intensity in the signal propagation path, and accordingly dynamically corrects the multi - dimensional features of the received signals to generate first multi - dimensional features.

[0014] An optical path pollution compensation module that evaluates the degree of optical pollution according to the optical signal attenuation rate, and dynamically adjusts the first multi - dimensional features of the received signals to generate second multi - dimensional features.

[0015] A judgment and warning module that outputs the target object features through the mapping relationship model according to the second multi - dimensional features. If the target object is water vapor, no warning is triggered. If the target object is smoke, a hierarchical warning is executed in combination with the number of times the threshold is exceeded within a preset time.

[0016] Compared with the existing technologies, the beneficial effects of the present invention are as follows: (1) By adopting the dual - band collaborative emission and synchronous control technology, the present invention enhances the signal anti - interference ability, and can still maintain high - precision signal analysis even in strong electromagnetic interference or complex reflection environments, significantly superior to the environmental adaptability of traditional single - band detection systems.

[0017] (2) By combining multi - dimensional analysis of scattering intensity, time - domain waveform, and frequency - domain energy, the present invention can accurately capture the physical property differences between smoke and water vapor, significantly improving the discrimination ability of fine particles and effectively distinguishing the scattering characteristics of different forms of substances.

[0018] (3) By monitoring environmental parameters in real time and making dynamic multi-dimensional feature corrections, the present invention significantly improves the accuracy of signal feature analysis. Furthermore, it effectively eliminates the influence of environmental interference on the detection results, greatly reduces the risk of misjudging water vapor as smoke, and ensures stable detection performance under complex climate conditions.

[0019] (4) By evaluating the degree of optical pollution and making secondary dynamic corrections to multi-dimensional features, the present invention can automatically compensate for signal distortion caused by mirror pollution. Even after long-term use, it can still maintain stable detection accuracy, solve the problem that there is no compensation mechanism designed for optical path pollution currently, and significantly reduce the false alarm problem caused by dust accumulation in the equipment.

[0020] (5) By combining the dual verification mechanisms of target type recognition and duration, the present invention can not only quickly respond to real fires but also effectively filter out instantaneous interferences. At the same time, through the hierarchical warning strategy, while ensuring sensitivity, it greatly reduces the false alarm rate and meets the high-standard fire safety response requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0022] Figure 1 It is a schematic diagram of the connection of the system module structure of the present invention.

[0023] Figure 2 It is a schematic diagram of the overall implementation step flow of the present invention.

[0024] Figure 3 It is a specific implementation flowchart of the signal transmission module of the present invention.

[0025] Figure 4 It is a specific implementation flowchart of the signal reception and analysis module of the present invention.

[0026] Figure 5 It is a specific implementation flowchart of the propagation environment correction module of the present invention.

[0027] Figure 6 It is a specific implementation flowchart of the optical path pollution compensation module of the present invention.

[0028] Figure 7 It is a specific implementation flowchart of the judgment and warning module of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0029] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0030] Please refer to Figure 1 and Figure 2 As shown, the present invention provides a water vapor false alarm prevention system for a smoke detector based on dual-emitter dual-band, and the system includes: a signal transmission module, a signal reception and analysis module, a propagation environment correction module, an optical path pollution compensation module, and a judgment and early warning module.

[0031] Among the above, the signal reception and analysis module is respectively connected to the signal transmission module, the propagation environment correction module, and the judgment and early warning module, and the optical path pollution compensation module is respectively connected to the propagation environment correction module and the judgment and early warning module.

[0032] Please refer to Figure 3 As shown, the signal transmission module emits optical signals through two independent transmitters. After synchronizing the emission phases of the two optical signals through a timing control circuit, the two signals are combined into the same path for propagation through an optical combiner.

[0033] It can be understood that the two independent transmitters are an infrared transmitter and a visible light transmitter respectively. The infrared transmitter emits near-infrared band such as 850nm, and the visible light transmitter emits visible light band such as 450nm.

[0034] Specifically, the specific synchronization of the emission phases is performed as follows: 1) Real-time collect the phases of the two emission signals and calculate the phase difference between the two emission signals.

[0035] 2) If the phase difference exceeds the preset threshold range, convert the phase difference into a voltage or digital signal through an error signal generator, and record it as an error signal.

[0036] 3) Adjust the signal phase according to the error signal until the phase difference is within the preset threshold range.

[0037] It should be added that the error signal generated by the circuit is input into the error amplifier for amplification processing. The amplified error signal is then transmitted to the integrator. The integrator performs an integration operation on the error signal to accumulate the change trend of the error signal. The signal output by the integrator is used to control the voltage-controlled oscillator (VCO). When the error signal is positive, the oscillation frequency of the VCO increases, and when the error signal is negative, the oscillation frequency of the VCO decreases. The signal output by the VCO is connected to the phase shifter. The phase shifter adjusts the phase of the optical signal that needs to be phase-adjusted according to the change in the frequency of the signal output by the VCO. In this way, it is ensured that the phases of the two optical signals always remain in an accurately synchronized state, ensuring the stable operation of the entire water vapor false alarm prevention system of the smoke detector.

[0038] Another specifically, an example process of combining two signals into the same propagation path through an optical beam combiner is as follows: Denote the two independent transmitters as transmitter one and transmitter two respectively. Transmitter one and transmitter two emit signals with orthogonal polarization states, such as horizontally polarized light and vertically polarized light . After passing through the polarization beam splitter prism, the horizontally polarized light is directly transmitted, and the vertically polarized light is reflected. The two converge into the same light beam at the exit of the prism, with the polarization state remaining orthogonal and the propagation direction being the same.

[0039] It can be understood that by integrating the dual-band signals into the same path, the two signals experience exactly the same environmental interference and optical path contamination, providing the same-environment comparison data for the subsequent signal analysis module. The receiving end can accurately distinguish smoke and water vapor by comparing the scattering intensity ratio, time-domain / frequency-domain characteristic differences of the dual-band signals, reducing the influence of environmental noise on discrimination from the hardware level. Moreover, the single-path design after beam combination simplifies the optical path layout of the system, improves the miniaturization and reliability of the device, and can be applied to scenarios sensitive to volume.

[0040] In the embodiments of the present invention, the signal anti-interference ability is enhanced by adopting the dual-band cooperative emission and synchronous control technology. Even in a strong electromagnetic interference or complex reflection environment, high-precision signal analysis can still be maintained, which is significantly superior to the environmental adaptability of traditional single-band detection systems.

[0041] Please refer to Figure 4 As shown, the signal receiving and analyzing module receives the optical signals through two independent photoelectric sensors respectively, and then extracts the multi-dimensional characteristics of the scattering intensity ratio, time-domain waveform, and frequency-domain energy distribution of the received signals, and establishes a mapping relationship model between the signal characteristics and the target object characteristics.

[0042] In the embodiments of the present invention, by combining the multi-dimensional analysis of scattering intensity, time-domain waveform, and frequency-domain energy, the physical property differences between smoke and water vapor can be accurately captured, significantly improving the discrimination ability of fine particles and effectively distinguishing the scattering characteristics of different forms of substances.

[0043] Specifically, the specific extraction process of multi-dimensional features includes: converting two optical signals into digital signals, and calculating the time-domain integral or frequency-domain energy of the two-band signals to generate a scattering intensity ratio.

[0044] After performing wavelet transform on the received signal, it is decomposed into multiple time-frequency sub-bands, and the waveform rise time, fall time, and pulse width of each sub-band are extracted as time-domain waveform features.

[0045] After performing Fourier transform on the received signal, a spectrogram is generated, the energy proportion of a preset frequency band is calculated, and the energy proportion, spectral peak value, and full width at half maximum are used as frequency-domain energy distribution features.

[0046] It should be added that the specific calculation process of the scattering intensity ratio is as follows: A1. Time-domain integration: Integrate the signal of each band within a preset time window, such as 10 ms, to calculate its total energy: , is the voltage signal at the th time point, represents the total energy, represents time, and represent the start time and end time of the preset time window respectively.

[0047] A2. Frequency-domain energy: Extract the amplitude of the target frequency band through FFT, such as avoiding the power noise frequency band, and calculate the effective energy , , and represent the minimum frequency value and maximum frequency value corresponding to the target frequency band respectively, represents the voltage signal.

[0048] Based on the above calculation rules, the total energy and effective energy of the two bands are calculated respectively. When calculating the scattering intensity by the time-domain integration method, the scattering intensity ratio is the ratio of the total energy of the two signals. When calculating the scattering intensity by the frequency-domain energy method, the scattering intensity ratio is the ratio of the effective energy of the two signals.

[0049] Exemplarily, the preset frequency band can specifically be, for example, 1 - 10 kHz, 10 - 100 kHz.

[0050] Another specifically, the specific establishment process of the mapping relationship model is as follows: A1. Build a sealing experiment chamber and configure temperature and humidity sensors, air pressure sensors, electromagnetic interference shielding devices, gas generators, and humidifiers.

[0051] A2. Set several smoke concentration experimental groups and several humidity experimental groups.

[0052] Among them, the smoke concentration can be set to four groups of experiments, including 0, 50%, 100% and 200% of the trigger concentration; the humidity experiment can be set to four groups of experiments, including 20%RH, 50%RH, 80%RH and 100%RH.

[0053] A3. In the smoke concentration experiment, the time domain waveform, scattered light intensity and voltage signals of the two photoelectric sensors are recorded at the set sampling frequency. After repeated experiments, the time domain characteristics, frequency domain characteristics and scattering intensity ratio of each experiment are extracted. The smoke concentration is used as the target label, and each feature is bound to the smoke concentration.

[0054] A4. In the humidity experiment, water vapor is used as the target label. The humidity experiment is carried out in the same way as the smoke concentration experiment. The time domain characteristics, frequency domain characteristics and scattering intensity ratio of each experiment are bound to water vapor.

[0055] Furthermore, the target object label binding also includes the following steps: B1. The importance of each feature is calculated by a random forest algorithm, feature values ​​whose importance is lower than a preset threshold are eliminated, and a primary screening data set of each feature is constructed.

[0056] B2. Calculate the correlation between each feature and the target object label, and remove the feature values ​​with correlation below the preset threshold from the first screening data set to obtain the second screening data set.

[0057] B3. The minimum and maximum values ​​in the secondary screening data set are combined into a value range, and the value range of each feature is bound to the corresponding target object label.

[0058] It is understandable that the importance of each feature is calculated by the random forest algorithm by calculating the Gini impurity reduction value, and the Gini impurity reduction value is used as the importance. For example, the tree size of the random forest is set to 500, the maximum depth is dynamically adjusted according to the number of features, and the node splitting criterion is Gini impurity. The calculation formula for the Gini impurity reduction value is an existing calculation formula and is no longer shown in examples.

[0059] It should be added that compared with other algorithms, random forest quantifies the importance of features through the Gini impurity reduction value of multiple decision trees. It can not only effectively capture the nonlinear correlation and interaction between complex features such as scattering intensity ratio, time domain waveform and frequency domain energy, but also has strong robustness to high-dimensional noise, avoiding overfitting interference.

[0060] Regarding step B2, the correlation degree between each feature and the target object label can be calculated by the Spearman rank correlation coefficient or the mutual information method, etc. In a specific embodiment, the mutual information method can be preferably used. Mutual information can capture any form by quantifying the statistical dependence between features and target variables. In the smoke detection scenario, features such as the scattering intensity ratio and the time-domain waveform often show complex non-linear relationships with the target label, such as exponential decay and threshold mutation. The mutual information method can more comprehensively evaluate the discriminative power of features.

[0061] Further, when establishing the mapping relationship model, an interference mapping relationship model is also included. The specific construction process is as follows: C1. Take oil mist particles and dust particles as interference object types, and set each interference experimental group according to the interference object concentration gradient and the particle size segmentation interval under a fixed smoke concentration and a fixed humidity.

[0062] Exemplarily, the particle size of the oil mist particles can be set to 0.5 - 2 μm, the concentration can be set to 0.5 mg / m³ and 1.0 mg / m³, the particle size of the dust particles can be set to 1 - 5 μm, the concentration can be set to 0.5 mg / m³ and 1.0 mg / m, and each interference experimental group is set accordingly.

[0063] C2. Record the misjudgment rates of the smoke concentration experimental group and the humidity experimental group when there is no interference object and when there is an interference object respectively. The misjudgment rate is the ratio of the number of misjudgments to the total number of experiments.

[0064] C3. After repeating the experiment several times for each interference experimental group, calculate the average value of the misjudgment rate and use it as the actual misjudgment rate of the corresponding interference experimental group.

[0065] C4. Calculate the average misjudgment rate of the smoke concentration experimental group and the humidity experimental group without interference objects after repeating the experiment several times respectively, and obtain the average misjudgment rates of these two experimental groups, which are used as their benchmark misjudgment rates.

[0066] C5. Analyze the benchmark misjudgment rate and the actual misjudgment rate comprehensively to obtain the anti-interference scores of the smoke concentration experimental group and the humidity experimental group under each interference object type.

[0067] It can be understood that to verify the anti-interference performance of the system in a complex environment, it is necessary to simulate the multi-source interference factors that may exist in the actual scenario. By controlling the interference object concentration gradient and the particle size segmentation variables, the cross-influence of different interference intensities on the detection model can be systematically evaluated, and a quantitative relationship between interference features and misjudgment rates can be established, providing data support for the subsequent compensation algorithm.

[0068] It should be noted that oil mist particles and dust particles have typical aerosol characteristics and appear most frequently in industrial / natural environments. The two have significant differences from smoke in optical characteristics such as refractive index and hygroscopicity, which can effectively verify the system's ability to distinguish heterogeneous suspended matter and at the same time cover the modeling requirements for two typical interference scenarios, namely oily and inorganic.

[0069] Among them, the anti-interference score can be analyzed and calculated through the following formula: , represents the anti-interference score, represents the actual misjudgment rate, represents the reference misjudgment rate, is the natural constant. When , this indicates that the actual misjudgment rate meets or exceeds the reference anti-interference ability standard. At this time, the anti-interference score can take the maximum value, which is assigned as 1 for subsequent quantitative comparison for convenience. When , it indicates that the interference is large and the anti-interference ability fails to meet the standard. The anti-interference score decreases as the difference between the actual misjudgment rate and the reference misjudgment rate increases. To accurately and intuitively reflect this trend, an exponential function is used for representation. When , the value range of is equivalent to , gradually approaches 0 as increases, that is, when the actual misjudgment rate exceeds the reference, the more it exceeds, the lower the anti-interference score. The anti-interference ability weakens as the degree of the misjudgment rate exceeding the reference increases.

[0070] Furthermore, the embedded interference mapping relationship model is used to adjust the trigger threshold of the target label. The specific adjustment process includes: D1. If the anti-interference scores of both oil mist particles and dust are higher than or equal to the corresponding set threshold, no trigger threshold adjustment is performed.

[0071] D2. If the anti-interference score of either oil mist particles or dust is lower than the corresponding set threshold, take the absolute value of the difference between its anti-interference score and the corresponding set threshold as the corresponding amplification ratio.

[0072] D3. If both are lower than the set threshold, set a compensation amplification ratio, and obtain the final amplification ratio by combining the amplification ratios corresponding to oil mist particles and dust and the compensation amplification ratio.

[0073] D4. Calculate the adjusted trigger threshold range according to the amplification ratio and the preset reference trigger threshold range, and adjust the value range of each feature based on this range.

[0074] In a specific embodiment, the compensation amplification ratio is preset according to the actual scenario, such as empirical values or experimental values. The final amplification ratio is obtained by combining the amplification ratios corresponding to oil mist particles and dust and the compensation amplification ratio. The final amplification ratio can be obtained by setting the weights of the amplification ratios corresponding to oil mist particles, dust and the compensation amplification ratio, and performing weighted summation. Exemplarily, the weights of the amplification ratios corresponding to oil mist particles, dust and the compensation amplification ratio can be respectively set to 0.2, 0.5 and 0.3.

[0075] In a preferred embodiment of the present invention, if the anti-interference score is lower than the set threshold, it indicates that the misjudgment rate of the system is relatively high in the interference environment, and it is necessary to increase the trigger threshold for smoke concentration detection. For example, the reference trigger threshold range is ±10% of the original value range. When the amplification ratio is 50%, it is adjusted from ±10% of the original value range to ±15% of the original value range to reduce the false alarm risk. And to prevent extreme adjustment, the maximum threshold range is set to ±20%.

[0076] In a specific implementation, in a complex industrial environment, the optical properties of interfering substances such as fog and dust and the target smoke are prone to cross-interference, resulting in an increase in the misjudgment rate of traditional detection models. By embedding an interference mapping relationship model to adjust the trigger threshold of the target object label and quantify the influence of the concentration and particle size of different interfering substances on the detection accuracy, a dynamic threshold adjustment mechanism is established to solve the problem of insufficient adaptability of the fixed threshold in a changing scenario. It is convenient to effectively distinguish real smoke from typical interfering particles, reduce false alarms or missed alarms caused by environmental interference, and achieve precise decoupling of environmental interference and target signals.

[0077] Please refer to Figure 5 As shown, the propagation environment correction module monitors the temperature, humidity, air pressure and electromagnetic noise intensity in the signal propagation path in real time, and accordingly dynamically corrects the multi-dimensional features of the received signal to generate the first multi-dimensional features.

[0078] Specifically, the temperature is monitored in real time by a digital temperature sensor, the humidity is monitored in real time by a capacitive humidity sensor, the air pressure is obtained by an integrated air pressure sensor for the real-time air pressure value, and the electromagnetic noise intensity is monitored in real time by a broadband radio frequency probe.

[0079] Understandably, temperature changes affect the movement of air molecules and particulate matter, altering scattering characteristics, signal propagation speed, and attenuation, thereby affecting the scattering intensity ratio, time-domain waveform, and frequency-domain energy distribution. An increase in humidity raises the water vapor content, and its scattering and absorption effects change the scattering intensity ratio, affecting signal propagation and causing distortion in the time-domain waveform. Changes in air pressure affect air density, influencing signal scattering, propagation speed, and attenuation, and acting on the scattering intensity ratio and time-domain waveform. The intensity of electromagnetic noise causes signal intensity fluctuations, superimposing noise on the time-domain waveform to cause distortion and introducing additional energy components in the frequency domain to change the frequency-domain energy distribution. Dynamically correct the multi-dimensional characteristics of the received signal based on temperature, humidity, air pressure, and electromagnetic noise intensity in the signal propagation path.

[0080] Specifically, the multi-dimensional characteristics of dynamically correcting the received signal include: R1. Calculate the dynamically corrected scattering intensity ratio according to temperature and humidity through a preset temperature-humidity joint compensation formula.

[0081] R2. Calculate the dynamically corrected waveform rise time according to air pressure and electromagnetic interference intensity through an air pressure-electromagnetic interference joint correction formula, and correct the waveform fall time and pulse width in the same way to obtain the dynamically corrected time-domain waveform characteristics.

[0082] R3. Adjust the energy ratio according to temperature through a frequency-domain energy compensation model, and dynamically compensate the spectral peak and full width at half maximum using a frequency drift compensation formula. Combine these three to obtain the dynamically corrected frequency-domain energy distribution characteristics.

[0083] R4. Generate the first multi-dimensional feature after integrating the dynamically corrected scattering intensity ratio, time-domain waveform characteristics, and frequency-domain energy distribution characteristics.

[0084] Regarding the temperature-humidity joint compensation formula in step R1, it is specifically expressed as follows: , and represent the scattering intensity ratios before and after dynamic correction respectively, is the set temperature compensation coefficient, with a value of 0.002 / °C, is the set humidity compensation coefficient, with a value of -0.005 / %RH, is the set reference calibration temperature, with a value of 25°C, is the set reference calibration humidity, with a value of 50%RH, and represent the temperature and humidity in the signal propagation path respectively.

[0085] Among them, is the temperature influence term. If , this term is positive and makes increase. If , this term is negative and makes Decrease, reflecting the compensation relationship that the scattering intensity ratio increases with the temperature rise. is the humidity influence term. If , this term is negative, causing to decrease. If , this term is positive, causing to increase, reflecting the compensation relationship that the scattering intensity ratio decreases with the humidity rise.

[0086] It should be explained that when the humidity increases, water vapor may condense on the surface of dust or oil mist particles, changing the characteristics such as particle size and density. The scattering characteristics of larger particles are different from those of the original particles, resulting in a decrease in the overall scattering intensity ratio. Moreover, water vapor itself has a certain absorption or scattering effect on light, causing the scattering intensity ratio to decrease.

[0087] The specific expression of the combined correction formula for air pressure - electromagnetic interference in step R2 is as follows: , and respectively represent the waveform rise times before and after dynamic correction. is the standard atmospheric pressure. and respectively represent the air pressure and electromagnetic noise intensity in the signal propagation path. is the set air pressure influence factor, with a value of 0.001 / kPa. is the set electromagnetic interference suppression factor, with a value of 0.01 / dBμV / m. is the set maximum allowable electromagnetic noise intensity.

[0088] Among them, is the air pressure influence term. reflects the relative change in air pressure. If , this term is negative, and after being weighted by , the correction factor decreases, causing . Conversely, if this term is positive, the correction factor increases, causing . represents the electromagnetic noise intensity influence term. represents first judging whether the actual electromagnetic noise intensity exceeds the maximum allowable value. If it does not exceed, it means that the influence on the waveform time is small and can be ignored. If it exceeds, then calculate the exceeded part, and the more the exceeded part, the larger the correction factor after being weighted by , making .

[0089] It should be added that when the air pressure increases, the air density increases, the light scattering probability increases, and the waveform rise time tends to shorten. When the air pressure decreases, the air density decreases, the scattering weakens, the light intensity rises slowly, and the waveform rise time tends to lengthen. A relatively large electromagnetic noise intensity will cover up some effective signals, resulting in a response delay of the detector to the optical signal, thus making the waveform rise time longer.

[0090] The specific calculation formula for the frequency-domain energy compensation model in step R3 is as follows: , and are the energy ratios before and after dynamic correction respectively, is the set temperature attenuation factor, and the specific value can be -0.01 / °C. The specific frequency drift compensation formula is: , and represent the spectral peak values before and after adjustment respectively, represents the temperature drift coefficient, and the specific value can be 0.005 / °C.

[0091] It should be noted that temperature has an impact on the energy ratio, spectral peak value and full width at half maximum of the signal. In terms of the energy ratio, high temperature may exacerbate the attenuation of signals in certain frequency bands, thereby causing the energy ratio of these frequency bands in the overall signal to decrease. Regarding the spectral peak value, the frequency drift caused by temperature will change it. For example, the frequency of an oscillator will change with temperature fluctuations. When the temperature increases, the frequency peak moves towards the high-frequency direction, which will increase the frequency peak value. Conversely, when it moves towards the low-frequency direction, it will decrease the frequency peak value. And the full width at half maximum will be affected by the change in Q value caused by temperature. When the temperature increases, the Q value decreases, and the full width at half maximum will increase accordingly.

[0092] In the embodiment of the present invention, by real-time monitoring of environmental parameters and performing dynamic multi-dimensional feature correction, the accuracy of signal feature analysis is significantly improved. Furthermore, the influence of environmental interference on the detection result is effectively eliminated, the risk of misjudging water vapor as smoke is greatly reduced, and the stable detection performance under complex climate conditions is ensured.

[0093] Please refer to Figure 6 As shown, the optical path pollution compensation module evaluates the optical pollution degree according to the optical signal attenuation rate, and dynamically adjusts the first multi-dimensional feature of the received signal to generate the second multi-dimensional feature.

[0094] Specifically, the evaluation process of the optical pollution degree includes: U1. Transmit a dual-band optical signal with a known intensity, use this intensity as the initial intensity, and record the received signal intensities of the two bands.

[0095] U2. Calculate the optical attenuation rate by comprehensively considering the initial intensity, the received signal intensity, and the layout distance between the transmitter and the photoelectric sensor through the attenuation rate formula.

[0096] Among them, the optical attenuation rate can be calculated based on the Beer-Lambert law, which is an existing calculation formula and will not be shown here.

[0097] U3. If the optical attenuation rate of a certain wavelength band is less than the corresponding preset threshold, assign the optical pollution factor of this wavelength band as 0; otherwise, calculate the optical pollution factor by comprehensively considering the optical attenuation rate and the corresponding preset threshold.

[0098] Understandably, the preset threshold is a boundary value determined based on factors such as a large amount of experimental data, industry standards, or environmental background, and is used to measure the degree of optical pollution. When the optical attenuation rate of a certain wavelength band is less than the corresponding preset threshold, it means that the attenuation of light in this wavelength band is in a relatively normal and acceptable range, without being affected by obvious pollution or interference factors. Therefore, it can be reasonably considered that there is no optical pollution problem in this wavelength band, so the optical pollution factor is assigned as 0.

[0099] In a preferred embodiment of the present invention, the optical pollution factor is calculated by comprehensively considering the optical attenuation rate and the corresponding preset threshold. First, calculate the optical attenuation rate difference by subtracting the corresponding preset threshold from the optical attenuation rate. Then, take the optical attenuation rate difference as the input variable and input it into the exponential decay function to output the optical pollution factor, as , where represents the input variable.

[0100] It can be understood that the optical pollution factor can also be calculated through various methods such as normalization processing or the Sigmoid function. In the optical pollution scenario, as the optical attenuation rate difference increases, the degree of optical pollution does not tend to increase linearly. Instead, it changes rapidly in the early stage and stabilizes in the later stage. Therefore, the present invention preferably uses the exponential decay function as the processing function.

[0101] U4. Calculate the optical pollution degree by weighted summation according to the optical pollution factors of the dual wavelength bands and the preset weights.

[0102] Furthermore, the specific adjustment process of dynamically adjusting the first multi-dimensional feature of the received signal is as follows: Match the optical pollution degree with the optical pollution degree intervals corresponding to each optical pollution level to obtain the corresponding optical pollution level.

[0103] Extract the pollution compensation algorithm matching the current optical pollution level from the preset pollution compensation algorithm configuration table, and adjust the first multi-dimensional feature according to this algorithm to obtain the second multi-dimensional feature.

[0104] It should be added that the pollution compensation algorithm configuration table is specifically shown in Table 1.

[0105] Table 1 Pollution Compensation Algorithm Configuration Table

[0106]

[0107] In the above table, y, q, and g represent the scattering intensity ratio correction coefficient, the time-domain delay correction coefficient, and the frequency-domain energy attenuation coefficient respectively. When it is scattering correction, only the scattering intensity ratio is corrected. When it is scattering + time-domain correction, the scattering intensity ratio and the time-domain waveform characteristics are corrected. When it is scattering + time-domain + frequency-domain combined correction, the scattering intensity ratio, the time-domain waveform characteristics, and the frequency-domain energy distribution characteristics are corrected. Among them, the correction formula for scattering correction is: , represents the scattering correction ratio after being adjusted by the optical path pollution compensation. Taking the waveform rise time as an example, the formula for time-domain correction is shown as follows. The specific correction formula is: , represents the waveform rise time after being adjusted by the optical path pollution compensation. Taking the energy ratio as an example, the formula for frequency-domain correction is shown as follows. The specific correction formula is: , represents the energy ratio after being adjusted by the optical path pollution compensation.

[0108] In the embodiment of the present invention, by evaluating the degree of optical pollution, multi-dimensional feature secondary dynamic correction can automatically compensate for signal distortion caused by mirror pollution. Even after long-term use, stable detection accuracy can still be maintained, solving the problem that there is no compensation mechanism designed for optical path pollution currently, and significantly reducing the false alarm problem caused by dust accumulation in the equipment.

[0109] Please refer to Figure 7 As shown, the judgment and early warning module outputs the target object features through the mapping relationship model according to the second multi-dimensional feature. If the target object is water vapor, no early warning is triggered. If the target object is smoke, hierarchical early warning is executed in combination with the number of times the threshold is exceeded within the preset time.

[0110] It should be added that the specific situation within the preset time of the judgment and early warning module is as follows: The alarm trigger smoke duration is matched from the factory settings of the smoke alarm according to the usage scenario where the smoke alarm is located as the preset time.

[0111] In a preferred embodiment of the present invention, assuming that the usage scenario of the smoke alarm is a factory, the alarm trigger smoke duration is set to 1 minute. When the number of times the threshold is exceeded reaches 3 times within 1 minute, a primary early warning is triggered to start the sound and light alarm. When the number of times the threshold is exceeded reaches 5 times within 1 minute, a secondary early warning is triggered and the ventilation system is started. When the number of times the threshold is exceeded reaches 10 times within 1 minute, a high-level early warning is triggered and an external fire protection system is linked.

[0112] In the embodiment of the present invention, by combining the dual verification mechanisms of target object type recognition and duration, it can not only quickly respond to real fires but also effectively filter out instantaneous interferences. At the same time, through the hierarchical early warning strategy, while ensuring sensitivity, the false alarm rate is greatly reduced, meeting the high-standard fire safety response requirements.

[0113] It should be noted that the above formula is a formula obtained by collecting a large amount of data for software simulation to approximate the real situation as closely as possible. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0114] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product.

[0115] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0116] In addition, the functional modules in each embodiment of this application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0117] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0118] Finally, the above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A water vapor false alarm prevention system for a smoke alarm based on dual - emitter and dual - band, characterized in that, The system includes: The signal transmission module transmits optical signals through two independent transmitters, and after the transmission phases of the two optical signals are synchronized by the timing control circuit, the two signals are combined into the same path for propagation through the optical combiner; The signal receiving and analyzing module receives optical signals through two independent photoelectric sensors, extracts the multi-dimensional characteristics of the scattering intensity ratio, time domain waveform and frequency domain energy distribution of the received signal, and establishes a mapping relationship model between the signal characteristics and the target object characteristics; The propagation environment correction module monitors the temperature, humidity, air pressure and electromagnetic noise intensity in the signal propagation path in real time, and dynamically corrects the multi-dimensional features of the received signal to generate the first multi-dimensional features. An optical path pollution compensation module evaluates the degree of optical pollution according to the optical signal attenuation rate, and dynamically adjusts the first multidimensional feature of the received signal to generate a second multidimensional feature; The judgment warning module outputs the target object characteristics through the mapping relationship model according to the second multidimensional characteristics. If the target object is water vapor, no warning is triggered. If the target object is smoke, a graded warning is executed in combination with the number of times the threshold exceeds the limit within a preset time.

2. The water vapor false alarm prevention system of the dual - transmitter and dual - band based smoke alarm according to claim 1, characterized in that: The specific synchronization of the transmission phase is performed as follows: Collect the phases of the two transmission signals in real time and calculate the phase difference between the two transmission signals; If the phase difference exceeds a preset threshold range, the phase difference is converted into a voltage or a digital signal by an error signal generator and recorded as an error signal; The signal phase is adjusted according to the error signal until the phase difference is within a preset threshold range.

3. The water vapor false alarm prevention system of the dual - transmitter and dual - band smoke alarm according to claim 1, characterized in that: The specific extraction process of the multidimensional features includes: Convert the two optical signals into digital signals, calculate the time domain integral or frequency domain energy of the two-band signals to generate the scattering intensity ratio; The received signal is decomposed into multiple time-frequency sub-bands after wavelet transformation, and the waveform rise time, fall time and pulse width of each sub-band are extracted as time domain waveform features; The received signal is Fourier transformed to generate a spectrum diagram, the energy proportion of the preset frequency band is calculated, and the energy proportion, spectrum peak and half-height width are used as frequency domain energy distribution characteristics.

4. The water vapor false alarm prevention system of the dual - transmitter and dual - band smoke alarm according to claim 1, characterized in that: The specific process of establishing the mapping relationship model is as follows: Build a sealed experimental chamber and configure it with temperature and humidity sensors, air pressure sensors, electromagnetic interference shielding devices, gas generators and humidifiers; Set up several smoke concentration experimental groups and several humidity experimental groups; In the smoke concentration experiment, the time domain waveform, scattered light intensity and voltage signals of two photoelectric sensors are recorded at the set sampling frequency. After repeated experiments, the time domain features, frequency domain features and scattering intensity ratio of each experiment are extracted. The smoke concentration is used as the target label, and each feature is bound to the smoke concentration. In the humidity experiment, water vapor is used as the target object label, and the humidity experiment is carried out in the same way as the smoke concentration experiment process. The time domain characteristics, frequency domain characteristics and scattering intensity ratio of each experiment are bound to water vapor.

5. The water vapor false alarm prevention system of the dual - transmitter and dual - band smoke alarm according to claim 4, characterized in that: The target tag binding also includes the following steps: The importance of each feature is calculated through the random forest algorithm, and the feature values ​​with importance lower than the preset threshold are eliminated to construct a primary screening data set for each feature; Calculate the correlation between each feature and the target object label, and remove the feature values ​​with correlation below the preset threshold from the first screening data set to obtain the second screening data set; Form a value range with the minimum and maximum values in the secondary screening dataset, and bind the value ranges of each feature to the corresponding target object labels.

6. The water vapor false alarm prevention system of the dual - transmitter and dual - band smoke alarm according to claim 4, characterized in that: When establishing the mapping relationship model, it also includes embedding an interference mapping relationship model, and its specific construction process is as follows: Take oil mist particles and dust particles as interference object types, and set each interference experimental group according to the interference object concentration gradient and particle size segmentation interval under a fixed smoke concentration and fixed humidity. Record the misjudgment rates of the smoke concentration experimental group and the humidity experimental group without interference objects and with interference objects respectively. The misjudgment rate is the ratio of the number of misjudgments to the total number of experiments. After repeating the experiments several times for each interference experimental group, calculate the average value of the misjudgment rate, and use it as the actual misjudgment rate of the corresponding interference experimental group. Calculate the average misjudgment rate of the smoke concentration experimental group and the humidity experimental group without interference objects after repeating the experiments several times respectively, and obtain the average misjudgment rate of these two experimental groups, which is used as their benchmark misjudgment rate. Analyze the benchmark misjudgment rate and the actual misjudgment rate comprehensively to obtain the anti-interference scores of the smoke concentration experimental group and the humidity experimental group under each interference object type.

7. The water vapor false alarm prevention system of the dual - transmitter and dual - band smoke alarm according to claim 6, characterized in that: The embedded interference mapping relationship model is used to adjust the trigger threshold of the target object label, and its specific adjustment process includes: If the anti-interference scores of both oil mist particles and dust are higher than or equal to the corresponding set threshold, no trigger threshold adjustment is performed. If the anti-interference score of oil mist particles or dust is lower than the corresponding set threshold, take the absolute value of the difference between its anti-interference score and the corresponding set threshold as the corresponding amplification ratio. If both are lower than the set threshold, set a compensation amplification ratio, and comprehensively obtain the final amplification ratio based on the amplification ratios corresponding to oil mist particles and dust and the compensation amplification ratio. Calculate the adjusted trigger threshold range according to the amplification ratio and the preset benchmark trigger threshold range, and adjust the value ranges of each feature according to this range.

8. The water vapor false alarm prevention system of the dual - transmitter and dual - band based smoke alarm according to claim 1, characterized in that: The multi-dimensional features for dynamically correcting the received signal include: Calculate the dynamically corrected scattering intensity ratio according to the temperature and humidity through a preset temperature-humidity joint compensation formula. Calculate the dynamically corrected waveform rise time according to the air pressure and electromagnetic interference intensity through an air pressure-electromagnetic interference joint correction formula, and correct the waveform fall time and pulse width in the same way to obtain the dynamically corrected time-domain waveform features. Adjust the energy ratio according to the temperature through a frequency-domain energy compensation model, and dynamically compensate the spectral peak and full width at half maximum using a frequency drift compensation formula. Integrate these three to obtain the dynamically corrected frequency-domain energy distribution features. Generate the first multi-dimensional feature after integrating the dynamically corrected scattering intensity ratio, time-domain waveform features, and frequency-domain energy distribution features.

9. The water vapor false alarm prevention system for a smoke alarm based on dual transmitters and dual bands according to claim 1, characterized in that: The evaluation process of the optical pollution degree includes: Emit a dual-band optical signal with a known intensity, use this intensity as the initial intensity, and record the received signal intensities of the two bands. Calculate the optical attenuation rate through an attenuation rate formula by comprehensively considering the initial intensity, received signal intensity, and the layout distance between the transmitter and the optoelectronic sensor. If the optical attenuation rate of a certain band is less than the corresponding preset threshold, assign the optical pollution factor of this band as 0, otherwise, statistically obtain the optical pollution factor by comprehensively considering the optical attenuation rate and the corresponding preset threshold. Calculate the optical pollution degree according to the optical pollution factors of the dual band and the preset weights.

10. The water vapor false alarm prevention system of the dual - transmitter and dual - band smoke alarm according to claim 1, characterized in that: The specific adjustment process of the first multi-dimensional feature of the dynamically adjusted received signal is as follows: Match the optical pollution degree with the optical pollution degree intervals corresponding to each optical pollution level to obtain the corresponding optical pollution level; Extract the pollution compensation algorithm matching the current optical pollution level from the preset pollution compensation algorithm configuration table, and adjust the first multi-dimensional feature according to this algorithm to obtain the second multi-dimensional feature.

Images