Portable smoke detection device easy to store

Abstract

The invention relates to the field of smoke detection, in particular to a portable smoke detection device easy to store, which comprises a smoke particulate matter light scattering detection module, an electrochemical gas sensing detection module and a central processing linkage optimization module, the smoke particulate matter light scattering detection module is used for acquiring a particle concentration signal value in to-be-detected air and realizing a particle concentration preliminary result through a particulate matter concentration algorithm; the electrochemical gas sensing detection module is used for acquiring a gas concentration signal value in air, and calculating and outputting a characteristic gas risk factor through a gas concentration algorithm; and the central processing linkage optimization module integrates and calculates a smoke comprehensive risk index through a linkage optimization algorithm according to the particle concentration preliminary result and the characteristic gas risk factor, and dynamically adjusts algorithm parameters according to real-time monitoring data to form closed-loop self-adaptive optimization.

Description

Technical Field

[0001] The invention relates to the field of smoke detection, in particular to a portable smoke detection device which is easy to store. Background Art

[0002] At present, with the continuous development of fire prevention and control technology, smoke detection technology has gradually become an important means in the field of fire warning. Existing portable smoke detection devices usually use a single smoke particle detection method or a single gas detection method, such as optical scattering method to detect smoke particle concentration, electrochemical sensor to detect specific gases, etc. However, the actual fire smoke composition is complex, and a single detection method is often difficult to comprehensively and accurately judge the fire hazard. In addition, the detection algorithms in the existing technology often ignore the combined effects of various environmental factors (such as particle morphology differences, airflow velocity changes, long-term stability of sensors, temperature and humidity interference), resulting in technical defects such as insufficient accuracy, high false alarm rate and weak robustness in the detection results.

[0003] Existing portable smoke detection technologies mostly use a single particle concentration or a single characteristic gas concentration measurement method, such as simple laser scattering particle detection or a single electrochemical gas sensor measurement method. However, particulate matter and harmful gases coexist in smoke, and single-mode detection can often only capture local information in the smoke risk and cannot fully reflect the actual risk situation, especially when there are fewer particles but higher gas concentrations or vice versa, which can easily lead to missed reports or false alarms. In addition, it is difficult for a single-mode detection system to coordinate the analysis of smoke particles and gas concentration data, resulting in insufficient accuracy in the assessment of the overall smoke risk, affecting the accuracy and practicality of smoke detection devices in complex application environments.

[0004] Existing smoke detection algorithms usually only consider a few environmental parameters, and fail to fully consider the shape of smoke particles, airflow velocity, temperature and humidity changes, and drift caused by long-term sensor operation in actual scenarios. The failure to include these important compensation parameters makes the algorithm susceptible to serious impacts from external environmental fluctuations, making it difficult to maintain long-term stable and reliable operation under actual complex working conditions. When the environment changes drastically, detection errors accumulate quickly and are difficult to correct automatically, which can easily lead to problems such as false alarms or even missed alarms, greatly reducing the reliability and practical application value of the detection system, and seriously restricting the high-precision application of smoke detection technology in complex scenarios.

[0005] Existing smoke detection technologies generally use fixed algorithm parameter settings and do not have a real-time dynamic optimization mechanism. When external environmental conditions change, this static algorithm cannot adaptively adjust and optimize the algorithm in a timely manner according to the real-time changes in environmental parameters and smoke characteristics. This results in the inability of existing detection systems to actively respond to the dynamic changes in smoke risks, causing the risk assessment results output by the algorithm to lag or be distorted, making it difficult to issue timely and accurate warnings in complex and changeable smoke monitoring scenarios. Therefore, the lack of real-time feedback closed-loop control and adaptive optimization mechanisms makes the adaptability and robustness of existing smoke detection devices in practical applications seriously insufficient, making it difficult to meet the high-precision requirements of actual safety management. Summary of the invention

[0006] The object of the present invention is to provide a portable smoke detection device that is easy to store, so as to solve the technical problems raised in the above-mentioned background technology.

[0007] Based on the above ideas, the present invention provides the following technical solutions: A portable smoke detection device that is easy to store, comprising: It includes smoke particle light scattering detection module, electrochemical gas sensor detection module and central processing linkage optimization module; The smoke particle light scattering detection module is used to obtain the particle concentration signal value in the air to be tested, and to achieve a preliminary result of the particle concentration through a particle concentration algorithm; The electrochemical gas sensing detection module is used to obtain the gas concentration signal value in the air, calculate and output the characteristic gas risk factor through the gas concentration algorithm; The central processing linkage optimization module integrates and calculates the comprehensive smoke risk index based on the preliminary results of particle concentration and characteristic gas risk factors through a linkage optimization algorithm, and dynamically adjusts algorithm parameters according to real-time monitoring data to form a closed-loop adaptive optimization.

[0008] By setting up three core modules, namely the smoke particle light scattering detection module, the electrochemical gas sensor detection module and the central processing linkage optimization module, comprehensive and accurate detection of smoke risks can be achieved. The smoke particle light scattering detection module quickly obtains preliminary data on particle concentration, and the electrochemical gas sensor detection module effectively captures real-time concentration information of various harmful gases. The central processing linkage optimization module deeply integrates and analyzes the data of particles and gases to form a comprehensive risk index; and automatically adjusts the algorithm parameters in real time according to environmental changes, so that the entire smoke detection system has a high degree of adaptability, accuracy and robustness, fundamentally improving the accuracy and reliability of smoke risk assessment.

[0009] Preferably, the specific process of the particle concentration algorithm is as follows: A1. Use a laser light source to illuminate the air area to be tested, obtain the scattered light signal and measure the signal intensity; A2. The intensity of the scattered light signal is processed by denoising and baseline correction to obtain a standardized signal; A3. Substitute the standardized signal into the particle concentration calculation formula to obtain the primary particle concentration result; A4. Output particle concentration to the central processing linkage optimization module for subsequent data integration.

[0010] The particle concentration algorithm uses a laser light source to illuminate the air area to be measured, and quickly identifies the particle concentration through high-precision light scattering signal measurement. Through the denoising and baseline correction steps, the influence of noise interference on the signal strength is greatly suppressed, and a high-purity standardized signal is obtained; then the data is converted through a specific particle concentration calculation formula, and finally an accurate primary result of the particle concentration is obtained. The overall process is clear and efficient, and the steps in the process are closely coordinated with each other, which greatly improves the real-time and accuracy of smoke particle detection and effectively avoids the error accumulation problem that may occur in traditional measurement methods.

[0011] Preferably, the particle concentration calculation formula is specifically: C=k 1 ×(X+Y+Z+αS+βV) Where X is the light scattering signal calibration factor; Y is the ambient temperature correction factor; Z is the humidity correction factor; S is the particle scattering angle characteristic parameter, which is used to accurately compensate for the influence of the shape differences of different smoke particles on the scattering intensity; V is the airflow velocity compensation factor, which is used to eliminate the error influence of particle measurement under different airflow velocities; α and β are weight coefficients obtained by experimental calibration; k 1 is the proportionality factor for light scattering particle concentration conversion.

[0012] By introducing the light scattering signal calibration factor (X), temperature correction factor (Y), humidity correction factor (Z), and innovatively adding the particle scattering angle characteristic parameter (S) and airflow velocity compensation factor (V), the measurement errors caused by the traditional algorithm when there are morphological differences and airflow velocity fluctuations are fully resolved. The S parameter specifically compensates for the scattered light intensity error in a refined manner based on the morphological differences of different smoke particles; the V parameter effectively eliminates the measurement deviation caused by different airflow velocity conditions. After adjusting the weight coefficients α and β, the primary result C of the particle concentration is more realistic and reliable, and the applicability of the algorithm in actual complex environments is significantly improved.

[0013] Preferably, the specific process of the gas concentration algorithm is as follows: B1. Use electrochemical sensor array to collect voltage signals of carbon monoxide, nitrogen oxides and volatile organic compounds in smoke in real time; B2. Filter and normalize the voltage signals of each gas sensor to obtain a characteristic voltage value; B3. Substituting the processed characteristic voltage value into the gas risk factor calculation formula to obtain the gas risk factor; B4. Output gas risk factors to the central processing linkage optimization module for subsequent integrated processing.

[0014] The gas concentration algorithm collects concentration signals of typical hazardous gases such as carbon monoxide, nitrogen oxides and volatile organic compounds in real time through an electrochemical sensor array, and improves signal stability and reliability through filtering and normalization processing, eliminating random noise interference of sensor signals. The characteristic voltage value is then accurately calculated through the gas risk factor calculation formula to accurately calculate the gas risk factor that reflects the actual risk level, so that a variety of different hazardous gas indicators are unified into a standard value that is easy to compare and evaluate, which is convenient for the subsequent central linkage module to conduct comprehensive evaluation and analysis, greatly improving the efficiency, accuracy and standardization of gas risk detection.

[0015] Preferably, the gas risk factor calculation formula is specifically: Q=k 2 ×(γM+δN) / (1+G′) Where M is the stability compensation coefficient of the electrochemical sensor, which is used to reduce the signal drift error caused by long-term operation; N is the environmental temperature and humidity cross-interference compensation coefficient, which is used to suppress the error interference of temperature and humidity changes on the sensor signal; G' is the normalized characteristic gas voltage signal value; γ and δ are weight coefficients obtained by experimental calibration; k 2 is the proportional coefficient of characteristic gas risk factor.

[0016] By introducing the electrochemical sensor stability compensation coefficient (M) and the environmental temperature and humidity cross-interference compensation coefficient (N), the drift error problem of the electrochemical sensor caused by long-term use and the sensor sensitivity fluctuation caused by changes in environmental temperature and humidity are effectively solved. After the characteristic gas voltage signal (G') is normalized, the individual differences between different sensors are effectively reduced. The weight coefficients γ and δ obtained by experimental calibration reflect the combined effect of the compensation coefficients M and N, further improving the stability and accuracy of the gas risk factor (Q) output by the gas concentration algorithm, so that the system always maintains high-precision detection performance during long-term operation or environmental changes.

[0017] Preferably, the specific process of the linkage optimization algorithm is as follows: C1. The central processing linkage optimization module obtains the particle concentration output by the particle concentration algorithm and the gas risk factor output by the gas concentration algorithm; C2. Preprocess the acquired particle concentration and gas risk factor, remove abnormal data points, and form stable data input; C3. Calculate the comprehensive smoke risk index by combining particle concentration and gas risk factor using linkage optimization integration formula; C4. Dynamically and adaptively adjust system parameters based on real-time feedback data to optimize the adaptability and effectiveness of the results.

[0018] The central processing linkage module receives and preprocesses the particle concentration and gas risk factor data, actively removes outliers or interference points, and ensures the accuracy and stability of the input data. Then, the linkage optimization integration formula is used to fuse and calculate the two different types of risk information to output a more objective and comprehensive smoke comprehensive risk index (R). At the same time, the algorithm dynamically adjusts the parameters in the system according to real-time feedback data, so that the algorithm has adaptive characteristics and can automatically correct as the environment changes, forming a closed-loop self-optimization structure. The above process significantly improves the adaptability of the overall system to environmental complexity, avoiding the defect that static parameters in traditional methods cannot cope with dynamic environmental changes.

[0019] Preferably, the linkage optimization integration formula is: R=k 3 ×(μC+νQ) / (1+∣C−Q∣) In the formula, C is the output preliminary result of particle concentration; Q is the output gas risk factor; μ and ν in the numerator are the linkage integration weight factors of particle concentration and gas risk factor, respectively; |CQ| in the denominator indicates the difference between the particle concentration and the gas risk factor, which is used to adaptively adjust the R value to ensure that when the two values ​​are close, the comprehensive risk index R is maximized; k 3 It is the proportional coefficient of the comprehensive evaluation index of smoke risk.

[0020] By combining the results of particle concentration (C) and gas risk factor (Q), the numerical difference |CQ| is innovatively introduced as an important parameter of the denominator in the formula, thereby giving a higher weight when the two risk factors are similar, so that the comprehensive smoke risk index (R) can more accurately reflect the real dangerous situation. The integrated weight factors μ and ν have been rigorously calibrated experimentally to accurately control the relative contribution of particle and gas risks to the comprehensive risk. This structure ensures that the comprehensive risk evaluation is more accurate and detailed, especially under complex environmental conditions where particle and gas risks are interrelated, showing great adaptability and reliability, and significantly improving the intelligence level of smoke risk assessment.

[0021] Compared with the prior art, the present invention has the following beneficial effects: The smoke particle light scattering detection module and the electrochemical gas sensor detection module work together to collect smoke particle concentration and multiple characteristic harmful gas concentration data, and use a dedicated algorithm to independently complete the preliminary analysis. Then the central processing linkage optimization module comprehensively analyzes the two data modes, and realizes the deep fusion of particle and gas risk information through the linkage optimization algorithm to form a comprehensive smoke risk index (R). This dual-modal fusion method captures smoke risk factors from multiple dimensions, overcomes the problems of one-sided data and insufficient precision in traditional single measurement methods, and makes smoke assessment results more comprehensive, objective, and accurate, thereby significantly improving the reliability of smoke monitoring and early warning.

[0022] In the particle concentration algorithm and gas concentration algorithm, a variety of environmental compensation parameters with clear physical meanings are introduced (such as scattering angle characteristic parameter S, airflow velocity compensation factor V, electrochemical sensor stability compensation coefficient M and temperature and humidity cross-interference compensation coefficient N), supplemented by experimental calibration weight coefficients (α, β, γ, δ). Through these sophisticated compensation mechanisms, the algorithm can effectively adapt to changes in temperature, humidity, airflow velocity and particle morphology in the environment, greatly reducing the adverse effects of long-term operation and external environmental fluctuations on measurement accuracy, and greatly improving the accuracy, stability and durability of smoke detection devices in complex environments.

[0023] The central processing linkage optimization module has a closed-loop adaptive adjustment function for real-time feedback data. The linkage optimization algorithm can dynamically and automatically optimize the core parameters of the algorithm according to the changes in real-time monitoring data. By introducing the difference between "particle concentration C" and "gas risk factor Q" |CQ| as an important adjustment basis, the linkage optimization integration formula realizes dynamic weight distribution to adapt to real-time risk changes under different dangerous conditions. This dynamic optimization design ensures that the system has excellent dynamic response performance and strong robustness, which is especially suitable for the changeable and complex scene requirements in practical applications. It effectively makes up for the limitations of static parameter settings in traditional algorithms and greatly improves the application value and environmental adaptability of smoke detection devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The module schematic diagram of a portable smoke detection device that is easy to store is shown in the figure. DETAILED DESCRIPTION

[0025] A portable smoke detection device that is easy to store, comprising: It includes smoke particle light scattering detection module, electrochemical gas sensor detection module and central processing linkage optimization module; The smoke particle light scattering detection module is used to obtain the particle concentration signal value in the air to be tested, and to achieve a preliminary result of the particle concentration through a particle concentration algorithm; The electrochemical gas sensing detection module is used to obtain the gas concentration signal value in the air, calculate and output the characteristic gas risk factor through the gas concentration algorithm; The central processing linkage optimization module integrates and calculates the comprehensive smoke risk index based on the preliminary results of particle concentration and characteristic gas risk factors through a linkage optimization algorithm, and dynamically adjusts algorithm parameters according to real-time monitoring data to form a closed-loop adaptive optimization.

[0026] By setting up three core modules, namely the smoke particle light scattering detection module, the electrochemical gas sensor detection module and the central processing linkage optimization module, comprehensive and accurate detection of smoke risks can be achieved. The smoke particle light scattering detection module quickly obtains preliminary data on particle concentration, and the electrochemical gas sensor detection module effectively captures real-time concentration information of various harmful gases. The central processing linkage optimization module deeply integrates and analyzes the data of particles and gases to form a comprehensive risk index; and automatically adjusts the algorithm parameters in real time according to environmental changes, so that the entire smoke detection system has a high degree of adaptability, accuracy and robustness, fundamentally improving the accuracy and reliability of smoke risk assessment.

[0027] Specifically, the specific process of the particle concentration algorithm is as follows: A1. Use a laser light source to illuminate the air area to be tested, obtain the scattered light signal and measure the signal intensity; A2. The intensity of the scattered light signal is processed by denoising and baseline correction to obtain a standardized signal; A3. Substitute the standardized signal into the particle concentration calculation formula to obtain the primary particle concentration result; A4. Output particle concentration to the central processing linkage optimization module for subsequent data integration.

[0028] The particle concentration algorithm uses a laser light source to illuminate the air area to be measured, and quickly identifies the particle concentration through high-precision light scattering signal measurement. Through the denoising and baseline correction steps, the influence of noise interference on the signal strength is greatly suppressed, and a high-purity standardized signal is obtained; then the data is converted through a specific particle concentration calculation formula, and finally an accurate primary result of the particle concentration is obtained. The overall process is clear and efficient, and the steps in the process are closely coordinated with each other, which greatly improves the real-time and accuracy of smoke particle detection and effectively avoids the error accumulation problem that may occur in traditional measurement methods.

[0029] Specifically, the particle concentration calculation formula is: C=k 1 ×(X+Y+Z+αS+βV) Where X is the light scattering signal calibration factor; Y is the ambient temperature correction factor; Z is the humidity correction factor; S is the particle scattering angle characteristic parameter, which is used to accurately compensate for the influence of the shape differences of different smoke particles on the scattering intensity; V is the airflow velocity compensation factor, which is used to eliminate the error influence of particle measurement under different airflow velocities; α and β are weight coefficients obtained by experimental calibration; k 1 is the proportionality factor for light scattering particle concentration conversion.

[0030] By introducing the light scattering signal calibration factor (X), temperature correction factor (Y), humidity correction factor (Z), and innovatively adding the particle scattering angle characteristic parameter (S) and airflow velocity compensation factor (V), the measurement errors caused by the traditional algorithm when there are morphological differences and airflow velocity fluctuations are fully resolved. The S parameter specifically compensates for the scattered light intensity error in a refined manner based on the morphological differences of different smoke particles; the V parameter effectively eliminates the measurement deviation caused by different airflow velocity conditions. After adjusting the weight coefficients α and β, the primary result C of the particle concentration is more realistic and reliable, and the applicability of the algorithm in actual complex environments is significantly improved.

[0031] Implementation steps: (1) Turn on the laser diode to emit a collimated laser beam with a wavelength of 650 nm to continuously irradiate the smoke particles in the air area to be detected; (2) The light signal scattered by smoke particles is received in real time through the photodiode array, the original scattered light intensity signal value P is measured, and the pure scattered light signal P' is obtained through hardware filtering and software algorithm denoising; (3) Environmental parameter calibration is performed based on the standard calibration algorithm. Temperature (T), humidity (H), light source stability factor (X), temperature correction factor (Y), humidity correction factor (Z), etc. are taken into consideration. The light scattering signal is further baseline calibrated to obtain the final standardized scattered light signal P'. (4) Substitute the standardized scattered light signal P' obtained above into the following formula to calculate the preliminary result of particle concentration C: The particle concentration C can reflect the precise state of the particle concentration on site in real time and be used for the subsequent assessment of smoke risks, with significant effects of high real-time performance, low error and high accuracy.

[0032] The principle and specific effect of the particle concentration formula: This formula combines the optical scattering theory (Mie scattering theory) with the actual engineering environment compensation principle. Parameters X, Y, and Z are corrected for instrument stability and environmental temperature and humidity factors respectively; parameter S is calibrated and compensated for the change in light scattering intensity caused by particle shape differences using the statistical characteristics of different scattering angles; the airflow velocity compensation parameter V eliminates the impact of airflow velocity differences on measurement stability. By introducing the above correction factors, the measurement error of the traditional method under the conditions of particle shape diversity and airflow velocity changes is greatly reduced, achieving more accurate and reliable particle concentration measurement results.

[0033] Specifically, the specific process of the gas concentration algorithm is as follows: B1. Use electrochemical sensor array to collect voltage signals of carbon monoxide, nitrogen oxides and volatile organic compounds in smoke in real time; B2. Filter and normalize the voltage signals of each gas sensor to obtain a characteristic voltage value; B3. Substituting the processed characteristic voltage value into the gas risk factor calculation formula to obtain the gas risk factor; B4. Output gas risk factors to the central processing linkage optimization module for subsequent integrated processing.

[0034] The gas concentration algorithm collects concentration signals of typical hazardous gases such as carbon monoxide, nitrogen oxides and volatile organic compounds in real time through an electrochemical sensor array, and improves signal stability and reliability through filtering and normalization processing, eliminating random noise interference of sensor signals. The characteristic voltage value is then accurately calculated through the gas risk factor calculation formula to accurately calculate the gas risk factor that reflects the actual risk level, so that a variety of different hazardous gas indicators are unified into a standard value that is easy to compare and evaluate, which is convenient for the subsequent central linkage module to conduct comprehensive evaluation and analysis, greatly improving the efficiency, accuracy and standardization of gas risk detection.

[0035] Specifically, the gas risk factor calculation formula is: Q=k 2 ×(γM+δN) / (1+G′) Where M is the stability compensation coefficient of the electrochemical sensor, which is used to reduce the signal drift error caused by long-term operation; N is the environmental temperature and humidity cross-interference compensation coefficient, which is used to suppress the error interference of temperature and humidity changes on the sensor signal; G' is the normalized characteristic gas voltage signal value; γ and δ are weight coefficients obtained by experimental calibration; k 2 is the proportional coefficient of characteristic gas risk factor.

[0036] By introducing the electrochemical sensor stability compensation coefficient (M) and the environmental temperature and humidity cross-interference compensation coefficient (N), the drift error problem of the electrochemical sensor caused by long-term use and the sensor sensitivity fluctuation caused by changes in environmental temperature and humidity are effectively solved. After the characteristic gas voltage signal (G') is normalized, the individual differences between different sensors are effectively reduced. The weight coefficients γ and δ obtained by experimental calibration reflect the combined effect of the compensation coefficients M and N, further improving the stability and accuracy of the gas risk factor (Q) output by the gas concentration algorithm, so that the system always maintains high-precision detection performance during long-term operation or environmental changes.

[0037] Specific implementation process: (1) The electrochemical sensor array detects the concentrations of carbon monoxide (CO), nitrogen oxides (NO_x) and volatile organic compounds (VOC) in the smoke in real time and generates a characteristic voltage signal (G); (2) After the sensor voltage signal G is processed by hardware anti-interference, it is finely processed using a digital filtering algorithm (such as Kalman filtering) to eliminate the noise caused by the environment and the sensor itself, and obtain a stable and clear characteristic voltage value (G'); (3) The electrochemical sensor long-term stability compensation coefficient M (sensor long-term calibration drift factor) and the ambient temperature and humidity cross-interference compensation coefficient N (measured by the ambient temperature and humidity sensor) are introduced to correct the error effects of environmental and device factors on the gas signal; (3) Substitute into the specific formula to obtain the characteristic gas risk factor Q: The obtained gas risk factor Q reflects the comprehensive threat level of various typical hazardous gases in the current air environment, effectively reflects the actual smoke risk status, and significantly improves the sensitivity and accuracy of smoke risk identification of the overall device.

[0038] The principle and specific effect of the gas concentration algorithm formula: This formula is based on the working principle of electrochemical sensors and the gas diffusion mechanism. It uses M (sensor stability drift compensation) and N (temperature and humidity interference factor) to finely correct the interference error caused by sensor performance drift and environmental conditions changes during long-term operation. The weight coefficients γ and δ reflect the degree of compensation and are obtained through scientific calibration to balance the sensor performance attenuation and environmental influences. G' normalization processing effectively solves the problem of consistency differences between different sensors. This formula significantly improves the accuracy and long-term stability of the system's detection of characteristic gases.

[0039] Specifically, the specific process of the linkage optimization algorithm is as follows: C1. The central processing linkage optimization module obtains the particle concentration output by the particle concentration algorithm and the gas risk factor output by the gas concentration algorithm; C2. Preprocess the acquired particle concentration and gas risk factor, remove abnormal data points, and form stable data input; C3. Calculate the comprehensive smoke risk index by combining particle concentration and gas risk factor using linkage optimization integration formula; C4. Dynamically and adaptively adjust system parameters based on real-time feedback data to optimize the adaptability and effectiveness of the results.

[0040] The central processing linkage module receives and preprocesses the particle concentration and gas risk factor data, actively removes outliers or interference points, and ensures the accuracy and stability of the input data. Then, the linkage optimization integration formula is used to fuse and calculate the two different types of risk information to output a more objective and comprehensive smoke comprehensive risk index (R). At the same time, the algorithm dynamically adjusts the parameters in the system according to real-time feedback data, so that the algorithm has adaptive characteristics and can automatically correct as the environment changes, forming a closed-loop self-optimization structure. The above process significantly improves the adaptability of the overall system to environmental complexity, avoiding the defect that static parameters in traditional methods cannot cope with dynamic environmental changes.

[0041] Specifically, the linkage optimization integration formula is: R=k 3 ×(μC+νQ) / (1+∣C−Q∣) In the formula, C is the output preliminary result of particle concentration; Q is the output gas risk factor; μ and ν in the numerator are the linkage integration weight factors of particle concentration and gas risk factor, respectively; |CQ| in the denominator indicates the difference between the particle concentration and the gas risk factor, which is used to adaptively adjust the R value to ensure that when the two values ​​are close, the comprehensive risk index R is maximized; k 3It is the proportional coefficient of the comprehensive evaluation index of smoke risk.

[0042] By combining the results of particle concentration (C) and gas risk factor (Q), the numerical difference |CQ| is innovatively introduced as an important parameter of the denominator in the formula, thereby giving a higher weight when the two risk factors are similar, so that the comprehensive smoke risk index (R) can more accurately reflect the real dangerous situation. The integrated weight factors μ and ν have been rigorously calibrated experimentally to accurately control the relative contribution of particle and gas risks to the comprehensive risk. This structure ensures that the comprehensive risk evaluation is more accurate and detailed, especially under complex environmental conditions where particle and gas risks are interrelated, showing great adaptability and reliability, and significantly improving the intelligence level of smoke risk assessment.

[0043] Implementation steps: (1) The central processing module receives the particle concentration C and gas risk factor Q synchronously in real time, and removes abnormal values ​​and noise data through data smoothing and filtering algorithms; (2) Using particle concentration C and gas risk factor Q to establish a multimodal risk fusion mechanism, the comprehensive risk index R is calculated using a linkage optimization integration formula; (3) After the comprehensive risk index R is output, adaptive parameter adjustment is continuously performed according to real-time feedback data to achieve closed-loop dynamic optimization, effectively improving the adaptability of the overall detection device to actual complex environments and the accuracy of risk assessment.

[0044] The principle and specific effect of the linkage optimization formula: This formula uses particle concentration and gas risk factor as dual input signals, dynamically adjusts the risk fusion weight based on the difference between the two, and forms a fusion optimization mechanism of "the smaller the difference, the greater the weight", ensuring that the comprehensive risk index accurately reflects the actual situation. The formula structure ensures that when the particle and gas risk values ​​tend to be close, the weight of the comprehensive risk index increases significantly, thereby sensitively and accurately capturing the potential trend of smoke hazard changes. This linkage mechanism not only improves the real-time performance of smoke risk assessment, but also realizes the intelligent adaptive adjustment of algorithm parameters, which has outstanding innovation and practical value.

Claims

1. A portable smoke detection device that is easy to store, characterized in that: include: It includes smoke particle light scattering detection module, electrochemical gas sensor detection module and central processing linkage optimization module; The smoke particle light scattering detection module is used to obtain the particle concentration signal value in the air to be tested, and to achieve a preliminary result of the particle concentration through a particle concentration algorithm; The electrochemical gas sensing detection module is used to obtain the gas concentration signal value in the air, calculate and output the characteristic gas risk factor through the gas concentration algorithm; The central processing linkage optimization module integrates and calculates the comprehensive smoke risk index based on the preliminary results of particle concentration and characteristic gas risk factors through a linkage optimization algorithm, and dynamically adjusts algorithm parameters according to real-time monitoring data to form a closed-loop adaptive optimization.

2. The portable smoke detection device that is easy to store according to claim 1, characterized in that: The specific process of the particle concentration algorithm is as follows: A1. Use a laser light source to illuminate the air area to be tested, obtain the scattered light signal and measure the signal intensity; A2. The intensity of the scattered light signal is processed by denoising and baseline correction to obtain a standardized signal; A3. Substitute the standardized signal into the particle concentration calculation formula to obtain the primary particle concentration result; A4. Output particle concentration to the central processing linkage optimization module for subsequent data integration.

3. The portable smoke detection device that is easy to store according to claim 2, characterized in that: The particle concentration calculation formula is specifically: C = k1 × (X + Y + Z + αS + βV); Where X is the light scattering signal calibration factor; Y is the ambient temperature correction factor; Z is the humidity correction factor; S is the particle scattering angle characteristic parameter, which is used to accurately compensate for the influence of the shape differences of different smoke particles on the scattering intensity; V is the airflow velocity compensation factor, which is used to eliminate the error influence of particle measurement under different airflow velocities; α and β are weight coefficients obtained by experimental calibration; k1 is the proportionality coefficient for light scattering particle concentration conversion.

4. The portable smoke detection device that is easy to store according to claim 3, characterized in that: The specific process of the gas concentration algorithm is as follows: B1. Use electrochemical sensor array to collect voltage signals of carbon monoxide, nitrogen oxides and volatile organic compounds in smoke in real time; B2. Filter and normalize the voltage signals of each gas sensor to obtain a characteristic voltage value; B3. Substituting the processed characteristic voltage value into the gas risk factor calculation formula to obtain the gas risk factor; B4. Output gas risk factors to the central processing linkage optimization module for subsequent integrated processing.

5. The portable smoke detection device that is easy to store according to claim 4, characterized in that: The gas risk factor calculation formula is specifically: Q = k2 × (γM + δN) / (1 + G′); Where M is the stability compensation coefficient of the electrochemical sensor, which is used to reduce the signal drift error caused by long-term operation; N is the environmental temperature and humidity cross-interference compensation coefficient, which is used to suppress the error interference of temperature and humidity changes on the sensor signal; G' is the normalized characteristic gas voltage signal value; γ and δ are weight coefficients obtained by experimental calibration; k2 is the proportional coefficient of characteristic gas risk factor.

6. The portable smoke detection device that is easy to store according to claim 5, characterized in that: The specific process of the linkage optimization algorithm is as follows: C1. The central processing linkage optimization module obtains the particle concentration output by the particle concentration algorithm and the gas risk factor output by the gas concentration algorithm; C2. Preprocess the acquired particle concentration and gas risk factor, remove abnormal data points, and form stable data input; C3. Calculate the comprehensive smoke risk index by combining particle concentration and gas risk factor using linkage optimization integration formula; C4. Dynamically and adaptively adjust system parameters based on real-time feedback data to optimize the adaptability and effectiveness of the results.

7. The portable smoke detection device that is easy to store according to claim 6, characterized in that: The linkage optimization integration formula is: R=k3×(μC+νQ) / (1+∣C−Q∣); In the formula, C is the output preliminary result of particle concentration; Q is the output gas risk factor; μ and ν in the numerator are the linkage integration weight factors of particle concentration and gas risk factor, respectively; |CQ| in the denominator indicates the difference between the particle concentration and the gas risk factor, which is used to adaptively adjust the R value to ensure that when the two values ​​are close, the comprehensive risk index R is maximized; k3 is the proportional coefficient of the comprehensive evaluation index of smoke risk.

Images