Fire smoke particle detection method and system for intelligent fire fighting

Abstract

The invention relates to the technical field of smoke particle detection, in particular to a fire smoke particle detection method and system for intelligent fire fighting, and the method comprises the steps: obtaining the fire smoke particle concentration and temperature of each position in each time window, acquiring a fire smoke particle abnormal fluctuation coefficient and a temperature rise saliency value of each position in each time window, further acquiring a smoke particle diffusion saliency of each position in each time window, and predicting the smoke particle diffusion saliency of an adjacent position of each position at the current moment. Obtaining a smoke particle state influence coefficient of each position at the current moment; and predicting the fire smoke concentration data of each position at the current moment, and optimizing the smoothing coefficient of the prediction algorithm according to the smoke particle state influence coefficient of each position at the current moment in the prediction process so as to obtain the fire smoke particle concentration through the predicted value. According to the invention, the accuracy of fire smoke particle concentration distribution detection can be improved.

Description

Technical Field

[0001] This application relates to the technical field of smoke particle detection, and particularly to a method and system for detecting fire smoke particles for intelligent fire protection. Background Art

[0002] Smoke is an important product of a fire and is also a basic parameter for fire detection. Fire smoke mainly comes from the incomplete and insufficient combustion of substances and is a high-temperature aerosol system composed of solid particles, carbon monoxide, carbon dioxide, decomposition products, etc. Optical smoke sensors are widely used in the field of fire smoke detection due to their simple production and low cost. Photoelectric smoke sensors emit light signals in the form of pulses. When the light signals encounter particulate matter in the air, scattering occurs, and the detection of the scattered light signals is used to achieve the detection of smoke concentration.

[0003] After a fire occurs, by real-time monitoring the smoke concentration in different areas, early signs of the fire can be quickly detected. And based on the smoke concentration data, the specific location and scope of the fire can be determined. By analyzing the changing trend of the smoke concentration in different areas, the spreading direction and speed of the fire can be predicted, which helps in the rational allocation of fire-fighting resources. During the occurrence of a building fire, the diffusion of smoke is easily affected by the building structure and complex airflows, which makes the diffusion speed and scope of the smoke highly uncertain, resulting in inaccurate detection of the smoke particle concentration. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a method and system for detecting fire smoke particles for intelligent fire protection, and the specific technical solutions adopted are as follows: The embodiment of this application provides a method for detecting fire smoke particles for intelligent fire protection, including the following steps: Obtain the fire smoke particle concentration and temperature data at each acquisition moment within each time window at each position; Perform time series decomposition on the fire smoke particle concentration at each position within each time window. According to the degree of data change of the trend term after time series decomposition and combined with the data fluctuation of the residual term, obtain the abnormal fluctuation coefficient of fire smoke particles at each position within each time window. Obtain the significant temperature rise value at each position within each time window according to the temperature change at each position within each time window. Combine the abnormal fluctuation coefficient of fire smoke particles and the significant temperature rise value to obtain the significant degree of smoke particle diffusion at each position within each time window; For each position, according to the significant degree of smoke particle diffusion at its neighboring positions in multiple time windows before the current moment, use a prediction algorithm to predict the significant degree of smoke particle diffusion at the neighboring positions at the current moment, so as to obtain the influence coefficient of the smoke particle state at each position at the current moment; Predict the fire smoke concentration data at the current moment for each location based on the average level of the fire smoke particle concentration within each time window before the current moment. During the prediction process, optimize the smoothing coefficient of the prediction algorithm according to the smoke particle state influence coefficient at each location at the current moment, so as to obtain the fire smoke particle concentration from the predicted value.

[0005] Preferably, the time window is a set preset duration.

[0006] Preferably, the fire smoke particle abnormal fluctuation coefficient of each location within each time window is as follows: For the trend term and residual term of the fire smoke particle concentration of each location within each time window, fit the trend term to obtain the corresponding curve, calculate the cumulative sum of the slopes of all data points in the curve, and obtain the product of the standard deviation and the mean of the residual term. Take the ratio of the cumulative sum to the product as the fire smoke particle abnormal fluctuation coefficient of each location within each time window.

[0007] Preferably, the acquisition of the significant temperature rise value of each location within each time window further includes: Fit the fire smoke concentration data of each location within each time window, and obtain the acquisition moment of the data point corresponding to the maximum curvature value in the fitted curve. Calculate the range of the temperature data at the acquisition moment of the data point corresponding to the maximum curvature value and the N moments before and after it. Take the ratio of the range to N as the significant temperature rise value of each location within each time window.

[0008] Preferably, the smoke particle diffusion significance of each location within each time window is the product of the fire smoke particle abnormal fluctuation coefficient and the significant temperature rise value of each location within each time window.

[0009] Preferably, the acquisition of the smoke particle state influence coefficient of each location at the current moment includes: for each location, set its adjacent locations, and take the average value of the predicted values of the smoke particle diffusion significance at the adjacent locations at the current moment as the smoke particle state influence coefficient of each location at the current moment.

[0010] Preferably, the method for obtaining the adjacent locations of each location is: taking the locations within a circular area with a preset radius centered on each location as the adjacent locations of each location.

[0011] Preferably, the prediction of the fire smoke concentration data at the current moment for each location further includes: Obtain the mean value of the fire smoke concentration data of each location within each of the preset number of time windows before the current moment, and use it as the input of the exponential smoothing algorithm to predict the fire smoke concentration of each location at the current moment.

[0012] Preferably, the optimization of the smoothing coefficient of the prediction algorithm further includes: Normalize the influence coefficients of the smoke particle states at each position at the current moment, and use the obtained normalization result as the smoothing coefficient of the exponential smoothing algorithm.

[0013] The embodiment of the present application also provides a fire smoke particle detection system for intelligent fire protection, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned fire smoke particle detection method for intelligent fire protection are implemented.

[0014] As can be seen from the above, the fire smoke particle detection method and system for intelligent fire protection provided by the present application at least have the following beneficial effects: By deeply analyzing the change characteristics of the fire smoke particle concentration data collected during the pyrolysis and smoldering processes in the early stage of a fire, as well as the correlation characteristics between the fire smoke concentration state and temperature changes, and further combining the mutual influence of the smoke particle concentrations between adjacent positions in a fire building under the rapid diffusion state, the continuous diffusion coefficient of the smoke particle concentration is calculated. Its advantage is that compared with the method that only relies on smoke sensor detection, it considers the diffusion degree characteristics of the smoke particle concentration generated in the early stage of combustible combustion, can predict the change characteristics of the smoke particle concentration, and helps to improve the accuracy of the fire smoke particle concentration distribution detection. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a step flow chart of a fire smoke particle detection method for intelligent fire protection provided by the present application. Detailed Embodiments

[0017] In order to further elaborate on the technical means and effects adopted by the present application to achieve the intended invention purpose, the following will, in combination with the drawings and preferred embodiments, describe in detail the specific embodiments, structures, features, and effects of a fire smoke particle detection method and system for intelligent fire protection proposed according to the present application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise specified or limited, terms such as "including", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the presence of additional identical elements in the article or device including the element. In addition, the term "and / or" used herein includes any and all combinations of any one of the one or more related listed items. All technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs.

[0019] The following specifically describes the specific solutions of a fire smoke particle detection method and system for intelligent fire protection provided by this application in conjunction with the accompanying drawings.

[0020] Please refer to Figure 1 , which shows a step flowchart of a fire smoke particle detection method for intelligent fire protection provided by an embodiment of this application, including the following steps: Step 1: Obtain the fire smoke particle concentration and temperature data at each acquisition moment in each time window at each location.

[0021] Combustion of substances can be divided into three stages, namely pyrolysis, smoldering and open fire. In the early stage of a fire, that is, during the pyrolysis and smoldering processes of substances, the main characteristics are the release of gases and aerosols. The aerosol is smoke, which is fine particles suspended in the air, and the aerosols generated by different substances during the pyrolysis and smoldering stages of combustion are concentrated within a certain particle diameter range. The particle diameters of water vapor, dust and oil fume particles are larger than the particle sizes of the particles generated by substance combustion. The essence of an optoelectronic smoke sensor is to judge the smoke concentration by measuring the scattered light intensity of smoke particles. Inside the sensor, the intensity of the received scattered light increases as the concentration of the particles increases. Conventional optoelectronic smoke sensors only detect whether there is a certain concentration of particles, and non-fire smokes such as water vapor, dust and oil fume particles will also produce similar scattered light.

[0022] The dual-wavelength optoelectronic smoke alarm emits light sources of two different wavelengths. As the size of the particulate matter changes, the scattering intensity ratio of the light sources of different wavelengths will change, thereby identifying different types of smoke. Therefore, in order to obtain the concentration of fire smoke particles generated during a fire, this embodiment uses a dual-wavelength optoelectronic smoke alarm to collect the fire smoke concentration data at each location in the room and the corridor. The temperature during the fire spread process has a certain degree of influence on the detection of smoke particles, and thus temperature data is collected through a temperature sensor at each smoke alarm location. In this embodiment, taking any one of the electric smoke alarms in a building fire as an example, starting from the collection of fire smoke concentration data, every 5 minutes is set as a time window, and in this embodiment, the time intervals for collecting fire smoke particle data and temperature data are both 0.1 seconds.

[0023] Step 2: Perform time series decomposition on the fire smoke particle concentration at each location within each time window. According to the degree of data change in the trend term after time series decomposition and in combination with the data fluctuation of the residual term, obtain the abnormal fluctuation coefficient of the fire smoke particles at each location within each time window. Obtain the significant temperature rise value at each location within each time window based on the temperature change at each location within each time window. Combine the abnormal fluctuation coefficient of the fire smoke particles and the significant temperature rise value of each time window to obtain the significant degree of smoke particle diffusion at each location within each time window.

[0024] When a fire breaks out at a certain location in a building, the combustible material will first generate combustible gas, then a large amount of smoke, and then the combustible material will start to burn in the presence of sufficient combustion-supporting gas and emit a large amount of heat, causing the temperature of the current environment to rise further and further spreading the fire. It can be seen that a lot of smoke will be generated in the initial stage of the fire. At this time, the temperature of the environment has not reached the highest. The small particle aerosols generated by the combustion of the substance will be dispersed into the air, and the dual-wavelength optoelectronic smoke alarms installed indoors usually detect the small particle aerosols at this stage. After detecting that the concentration of small particle aerosol particulate matter exceeds the threshold, a fire alarm will be issued. When the open fire has not completely burned up, the rising rate of the smoke concentration gradually increases, and there will also be small-scale unstable fluctuations during the increase process of the smoke concentration. The higher the increasing rate of the smoke concentration, the faster the smoke will spread during a fire. After reaching the open fire combustion process, the fire will spread rapidly, and the heat generated by the combustion will continuously increase the environmental temperature. During the temperature increase process, the smoke concentration in the environment will rise to the highest and remain relatively stable. When the temperature starts to increase at a high rate and the smoke concentration just reaches the highest state, it indicates that the smoke particles in the fire state will start to spread rapidly in all directions at this time. Therefore, this embodiment deeply considers the change characteristics of the smoke particle concentration in the early stage of a fire and the correlation between the smoke concentration state and the degree of temperature rise, so as to detect the smoke particles.

[0025] In addition, as the smoke concentration increases, the smoke will spread around at a certain speed, which will affect the detection of smoke particles in the surrounding environment. Based on this feature, it is helpful to accurately identify and predict the concentration of fire smoke particles.

[0026] First, obtain the relevant change characteristics of the smoke concentration data during the rising process. For each position, in this embodiment, taking the u-th position as an example, the fire smoke particle concentration data collected in each time window. Since the rising process of the smoke concentration is not smooth and there are certain fluctuations, the rising rate and the degree of non-smooth fluctuations of the smoke concentration can reflect the corresponding fire development state. Therefore, for the fire smoke particle concentration data of the u-th position in each time window, in order to obtain the overall change trend characteristics of the smoke particle data, this embodiment uses the STL (Seasonal and Trend decomposition using Loess) time series decomposition algorithm to decompose the fire smoke particle data of the u-th position in each time window, and obtains the corresponding trend term and residual term.

[0027] For the fire smoke particle concentration data of the u-th position in the i-th time window, where the obtained trend term is discrete data. To facilitate the analysis of the change rate at each data point in the trend term, the least squares method is used to fit the trend term to obtain the corresponding curve, and the slope value at each data point of the curve is obtained. When the smoke concentration increases rapidly, it is usually in the smoldering process in the early stage of material combustion, and the increasing rate of the smoke concentration can reflect the degree of the fire. Moreover, the higher the increasing rate of the fire smoke concentration, the faster the diffusion of the smoke at that position. Then, the slope at each data point in the curve is obtained, and the sum of all the slopes is used as the smoke concentration trend significance of the u-th position in the i-th time window. The smoke concentration trend significance reflects the change rate of detecting fire smoke particles.

[0028] In addition, the rising of the smoke may be affected by air flow changes or insufficient concentration, resulting in non-smooth fluctuations. The greater the degree of non-smooth fluctuations, the less concentrated the distribution of smoke particles at that position. On the contrary, when the smoke concentration rises steadily, it indicates that the smoke particles in the air are densely distributed, and the fire at that position is relatively serious. And the residual term can reflect the non-stationary fluctuation characteristics of the data. Therefore, in this embodiment, by calculating the standard deviation and mean of the residual term, the data fluctuation situation of the residual term is analyzed. In this embodiment, for the convenience of understanding and expression, for the u-th position in the i-th time window, the product of the standard deviation and the mean of the residual term is used as the smoke concentration random fluctuation coefficient of the u-th position in the i-th time window. The smoke concentration random fluctuation coefficient reflects the change characteristics during the rising process of fire smoke particles.

[0029] Further, the ratio of the smoke concentration trend significance of each position in each time window to the smoke concentration random fluctuation coefficient is used as the abnormal fluctuation coefficient of fire smoke particles at each position in each time window. Denote the abnormal fluctuation coefficient of fire smoke particles at the u-th position in the i-th time window as . The larger the obtained abnormal fluctuation coefficient of fire smoke particles, the more it indicates that the smoke particle concentration at the corresponding position within this time window is in a stage of rapid abnormal growth.

[0030] Further, as the fire spreads, the fire smoke concentration at a certain position gradually reaches the maximum value. And within the local range where the maximum value is reached, the corresponding temperature data may be in a stage of rapid growth, indicating that a significant open fire may occur at the corresponding position soon. Therefore, in this embodiment, the fire smoke concentration data at the u-th position in each time window is fitted, and the acquisition moment of the data point corresponding to the maximum curvature value in the fitted curve of the fire smoke concentration data is obtained. Then, calculate the range of the temperature data at the acquisition moment corresponding to the maximum curvature value and the N moments before and after it, where N takes the value of 10 and the implementer can set it by themselves. Further, the ratio of the said range to N is used as the temperature rise significance value at each position in each time window. Denote the temperature rise significance value at the u-th position in the i-th time window as , which is used to reflect the change degree of the environmental temperature when the fire smoke concentration reaches the highest value state. If the corresponding abnormal fluctuation coefficient of fire smoke particles within the time window is larger and the temperature rise significance value is higher, it means that the diffusion state of the smoke particles at this position within the corresponding time window is more serious.

[0031] Further, this embodiment combines the abnormal fluctuation coefficient of fire smoke particles and the temperature rise significance value in each time window to obtain the smoke particle diffusion significance at each position in each time window. The smoke particle diffusion significance at each position in each time window is the product of the abnormal fluctuation coefficient of fire smoke particles and the temperature rise significance value at each position in each time window. For the convenience of understanding, in this embodiment, the specific calculation formula is: , where is the smoke particle diffusion significance at the u-th position in the i-th time window. The said smoke particle diffusion significance reflects the change of smoke concentration during the early pyrolysis and smoldering processes of the fire and the correlation characteristics between the smoke concentration state and the temperature change. And the larger the smoke particle diffusion significance, the more likely the smoke particle concentration at this position may further increase.

[0032] Step 3: For each position, according to the smoke particle diffusion significance at its neighboring positions in multiple time windows before the current moment, use a prediction algorithm to predict the smoke particle diffusion significance at the neighboring positions at the current moment, so as to obtain the smoke particle state influence coefficient at each position at the current moment.

[0033] Due to the relatively high temperature and low density of smoke particles, they will diffuse upward due to the action of thermal buoyancy. Affected by the building structure and natural ventilation conditions, the diffusion path of smoke is relatively complex. In a fire building, the smoke usually shows the characteristics of diffusing around at a certain rate and preferentially diffusing upward and to positions with a large temperature difference. Therefore, there is a high possibility that smoke detectors at adjacent positions will affect each other.

[0034] Taking the smoke sensor at any position as an example, considering that the air between adjacent positions can flow to each other, this embodiment will analyze in combination with the fire smoke particle data of its adjacent positions. First, set the adjacent positions of each position, which can be set by the implementer in the actual application scenario, and this embodiment does not make special restrictions on this. Preferably, in this embodiment, similarly, taking the u-th position as an example, the u-th position is used as the central position, and each position within a circular area with a radius of R is used as the adjacent position of the u-th position, where the value of R can be set by the implementer, and in this embodiment, it is set to 1 meter.

[0035] Further, for the u-th position, arrange the smoke particle diffusion saliencies of its adjacent positions in ascending order of time under M consecutive time windows before the current moment, and respectively obtain the saliency value sequences corresponding to each adjacent position. In this embodiment, M is taken as 10. The higher the smoke particle diffusion saliency corresponding to the adjacent position, the greater the influence on the smoke particle state of the central position. Thus, predict the smoke particle diffusion saliency of each adjacent position at the current moment.

[0036] Specifically, for the u-th position, this embodiment uses the single exponential smoothing algorithm to respectively predict the saliency value sequences corresponding to each adjacent position, outputs the predicted values of the smoke particle diffusion saliency of each adjacent position at the current moment, takes the average value of the predicted values of the smoke particle diffusion saliency of all adjacent positions at the current moment, and uses it as the smoke particle state influence coefficient of the central position at the current moment. The obtained smoke particle state influence coefficient reflects the degree of influence of the smoke detection at the central position by the surrounding smoke state.

[0037] So far, repeat the above process of this embodiment to obtain the smoke particle state influence coefficients of each position at the current moment.

[0038] Step Four: Predict the fire smoke concentration data of each position at the current moment according to the average level of the fire smoke particle concentration in each time window before the current moment of each position. During the prediction process, optimize the smoothing coefficient of the prediction algorithm according to the smoke particle state influence coefficients of each position at the current moment to obtain the fire smoke particle concentration through the predicted values.

[0039] Furthermore, after a fire occurs, the indoor air flow changes become more complex, and the smoke concentration data collected by the smoke particle sensor is vulnerable to the interference of air flow changes, resulting in inaccurate data detected by the sensor. The smoke diffusion characteristics can to a certain extent reflect the influence of air flow changes on the smoke concentration. Therefore, by combining the influence characteristics of smoke diffusion in a local area, the accurate prediction of smoke particle data can be realized.

[0040] Specifically, first, calculate the mean value of the fire smoke concentration data at each position within each of the M time windows before the current moment. Further, use the single exponential smoothing algorithm to perform predictive analysis on the smoke concentration data at each position at the current moment. During the prediction process, optimize the smoothing coefficient of the exponential smoothing algorithm. Considering that when the obtained smoke particle state influence coefficient is larger, it indicates that the change degree of the smoke concentration data at this position in the short term is larger, and a larger smoothing coefficient needs to be set; when the obtained smoke particle state influence coefficient is smaller, it means that the influence of the smoke concentration data change in the short term is smaller, and a smaller smoothing coefficient can be set. Therefore, in this embodiment, the Sigmoid function is used to normalize the smoke particle state influence coefficient at each position at the current moment, and the obtained normalized result is used as the smoothing coefficient. The mean value of the fire smoke concentration data at each position within each of the M time windows before the current moment is used as the input of the single exponential smoothing algorithm to predict the fire smoke concentration data at each position at the current moment, and the obtained predicted value is used as the correction result of the fire smoke particle detection.

[0041] In this embodiment, by deeply analyzing the change characteristics of the fire smoke particle concentration data collected during the pyrolysis and smoldering processes in the early stage of the fire, as well as the correlation characteristics between the fire smoke concentration state and the temperature change, and combining the mutual influence between adjacent smoke sensors in the building fire, calculate the smoke particle state influence coefficient, which reflects the influence degree of smoke particle diffusion on the detection of surrounding smoke particles, and optimize the smoothing coefficient based on the smoke particle state influence coefficient, and then correct the smoke concentration data, which helps to improve the accuracy of particulate matter concentration detection.

[0042] Based on the same inventive concept as the above method, the embodiment of the present application also provides a fire smoke particle detection system for intelligent fire protection, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above methods of a fire smoke particle detection method for intelligent fire protection.

[0043] It should be understood that the above-mentioned sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the specific embodiments of this specification have been described. Further, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0044] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0045] The above content is only the implementation manner of the present application and is not used to limit the scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the protection scope of the present application.

Claims

1. A method for detecting fire smoke particles for intelligent fire protection, characterized in that, Including the following steps: Obtain the fire smoke particle concentration and temperature data at each acquisition moment for each position within each time window; Perform time series decomposition on the fire smoke particle concentration for each position within each time window. According to the degree of data change in the trend term after time series decomposition and combined with the data fluctuation of the residual term, obtain the abnormal fluctuation coefficient of fire smoke particles for each position within each time window. Obtain the significant temperature rise value for each position within each time window based on the temperature change situation of each position within each time window. Combine the abnormal fluctuation coefficient of fire smoke particles and the significant temperature rise value to obtain the significant degree of smoke particle diffusion for each position within each time window; For each position, according to the significant degree of smoke particle diffusion in multiple time windows before the current moment for its neighboring positions, use a prediction algorithm to predict the significant degree of smoke particle diffusion for the neighboring positions at the current moment, so as to obtain the influence coefficient of the smoke particle state for each position at the current moment; According to the average level of the fire smoke particle concentration for each position within each time window before the current moment, predict the fire smoke concentration data for each position at the current moment. During the prediction process, optimize the smoothing coefficient of the prediction algorithm according to the influence coefficient of the smoke particle state for each position at the current moment, so as to obtain the fire smoke particle concentration through the predicted value.

2. The method for detecting fire smoke particles for intelligent fire protection according to claim 1, wherein The time window is a preset duration set.

3. A method for detecting fire smoke particles for intelligent fire protection according to claim 1, characterized in that, The abnormal fluctuation coefficient of fire smoke particles for each position within each time window: For the trend term and residual term of the fire smoke particle concentration for each position within each time window, fit the trend term to obtain the corresponding curve, calculate the sum of the slopes of all data points in the curve, and obtain the product of the standard deviation and the mean of the residual term. Take the ratio of the sum and the product as the abnormal fluctuation coefficient of fire smoke particles for each position within each time window.

4. The method for detecting fire smoke particles for intelligent fire protection according to claim 1, characterized in that, The obtaining of the significant temperature rise value for each position within each time window further includes: Fit the fire smoke concentration data for each position within each time window, and obtain the acquisition moment of the data point corresponding to the maximum curvature value in the fitted curve. Calculate the range of the temperature data at the acquisition moment corresponding to the maximum curvature value and its N moments before and after. Take the ratio of the range to N as the significant temperature rise value for each position within each time window.

5. The method for detecting fire smoke particles for intelligent fire protection according to claim 1, characterized in that, The significant degree of smoke particle diffusion for each position within each time window is the product of the abnormal fluctuation coefficient of fire smoke particles and the significant temperature rise value for each position within each time window.

6. The method for detecting fire smoke particles for intelligent fire protection according to claim 1, wherein, The obtaining of the influence coefficient of the smoke particle state for each position at the current moment includes: For each position, set its adjacent positions, and take the average value of the predicted values of the significant degree of smoke particle diffusion for the adjacent positions at the current moment as the influence coefficient of the smoke particle state for each position at the current moment.

7. A method for detecting fire smoke particles for intelligent fire protection according to claim 6, characterized in that, The method for obtaining the adjacent positions of each position is: Take the positions within a circular area with a preset radius centered on each position as the adjacent positions of each position.

8. The method for detecting fire smoke particles for intelligent fire protection according to claim 1, characterized in that, The prediction of the fire smoke concentration data for each position at the current moment further includes: Obtain the mean value of the fire smoke concentration data at each position within each of a preset number of time windows before the current moment, and use it as the input of the exponential smoothing algorithm to predict the fire smoke concentration at each position at the current moment.

9. A method for detecting fire smoke particles for intelligent fire protection according to claim 8, characterized in that, The further optimization of the smoothing coefficient of the prediction algorithm includes: Normalize the influence coefficient of the smoke particle state at each position at the current moment, and use the obtained normalization result as the smoothing coefficient of the exponential smoothing algorithm.

10. A fire smoke particle detection system for intelligent fire protection, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a fire smoke particle detection method for intelligent fire protection according to any one of claims 1-9.

Images