A method, medium and system for fire ignition prediction and variable-frequency patrol inspection

Abstract

The present invention provides a method, medium and system for fire prediction and variable-frequency patrol inspection, belonging to the field of fire protection technology, including: collecting thermal imaging images through an integrated intelligent fire extinguisher, detecting temperature change points and temperature abnormal points by using the frame difference method, constructing a time series matrix and decomposing it, and calculating a fire risk index matrix. Dynamically adjust the patrol inspection strategy of the pan-tilt according to the fire risk index, extend the pause time for high-risk areas and shorten the pause time for low-risk areas. When the fire risk index of a certain area exceeds a preset threshold, an initial fire is determined and an alarm is triggered. The patrol inspection strategy of the integrated intelligent fire extinguisher can be dynamically adjusted. Increase the inspection time for high-risk areas and reduce the inspection frequency for low-risk areas, so as to effectively concentrate monitoring resources on key parts. Once the risk index of a certain area exceeds the preset threshold, an initial fire can be determined and an alarm can be triggered immediately. It solves the problem that the prior art cannot dynamically adjust the patrol inspection strategy according to the fire risks of different areas.

Description

Technical Field

[0001] The present invention belongs to the field of fire protection technology, and more particularly, relates to a method, medium and system for predicting fire ignition and variable-frequency patrol inspection. Background Art

[0002] Fire accidents have always been one of the key issues of social concern. How to effectively prevent and control fire accidents is an important topic that all sectors must face. Existing fire prevention technologies mainly include two categories: fire protection and monitoring. Fire protection technology mainly deals with fire accidents that have occurred by means of equipping fire extinguishing equipment and establishing a fire brigade; while monitoring technology focuses on real-time detection and early warning of potential fire hazards. Currently, the more widely used monitoring technologies include smoke detection, temperature monitoring, video monitoring, etc.

[0003] Smoke detection technology can quickly detect the initial stage of a fire by real-time detection of the smoke concentration in the environment. However, this technology has certain limitations and it is difficult to accurately locate the specific location of the fire. Temperature monitoring technology analyzes the real-time change of the environmental temperature and issues an early warning when an abnormal temperature is detected. This method can better determine the location of the fire, but it has poor detection effect on potential fire hazards with slow temperature changes. Video monitoring technology uses a camera to take real-time pictures of the monitored area and detects abnormal situations that may cause a fire by analyzing video image information. However, this technology is limited by the field of view and imaging quality and it is difficult to fully cover the monitored area.

[0004] In addition, most of the existing monitoring technologies adopt fixed layout and cannot dynamically adjust the patrol inspection strategy according to the fire risks in different regions. Summary of the Invention

[0005] In view of this, the present invention provides a method, medium and system for predicting fire ignition and variable-frequency patrol inspection, which can solve the technical problem that in the prior art, fire patrol inspection often adopts a fixed rotation speed or frequency and there is no way to dynamically adjust the patrol inspection strategy according to the fire risks in different regions.

[0006] The present invention is implemented as follows:

[0007] In the first aspect of the present invention, a method for predicting fire ignition and variable-frequency patrol inspection is provided, which includes the following steps:

[0008] S10. Real-time obtain the thermal imaging image collected during the rotation of the integrated intelligent fire extinguisher; the integrated intelligent fire extinguisher is provided with a pan-tilt head, and a thermal imager is arranged on the pan-tilt head for collecting the thermal imaging image;

[0009] S20. Use the frame difference method to detect moving targets in adjacent thermal imaging images, and identify temperature change points and temperature anomaly points in the thermal imaging images. The temperature change points refer to the points where the temperature change between adjacent frames exceeds a preset first threshold. The temperature anomaly points refer to the points where the temperature is higher than the sum of the ambient average temperature and a preset second threshold.

[0010] S30. Combine the temperature change points and temperature anomaly points corresponding to all adjacent thermal imaging images into a temperature change point time series matrix and a temperature anomaly point time series matrix respectively.

[0011] S40. Decompose the temperature change point time series matrix by using the singular value decomposition method to obtain a temperature change point uniform change matrix and a temperature change point variable speed change matrix.

[0012] S50. Decompose the temperature anomaly point time series matrix by using the principal component analysis method to obtain a temperature anomaly point position stable matrix and a temperature anomaly point position change matrix.

[0013] S60. According to the temperature change point variable speed change matrix and the temperature anomaly point position change matrix, calculate the fire risk index matrix by using a preset fire risk matrix calculation equation. Each element in the fire risk index matrix is a vector, including coordinates and a fire risk index. The higher the fire risk index, the greater the possibility of an initial fire occurring in the area corresponding to the coordinates.

[0014] S70. Dynamically adjust the inspection strategy of the pan-tilt head according to the calculated fire risk index matrix: for areas with a high fire risk index, increase the pause duration corresponding to the integrated intelligent fire extinguishing rotation process; for areas with a low fire risk index, reduce the pause duration corresponding to the integrated intelligent fire extinguishing rotation process.

[0015] S80. When the fire risk index of a certain area exceeds a preset initial fire determination threshold, determine that an initial fire has occurred in that area, record the coordinates of the initial fire position, and trigger an alarm.

[0016] Specifically, the step S10 specifically includes: Real-time collect thermal imaging images of the monitored area from the thermal imager set on the pan-tilt head of the integrated intelligent fire extinguisher. This thermal imager can capture the surface temperature distribution information of the objects in the monitored area and convert it into thermal imaging images. During the variable frequency inspection process, the thermal imager will continuously collect real-time thermal imaging images, providing a data basis for subsequent temperature change analysis.

[0017] Among them, the specific steps of the step S20 include: using the frame difference method to perform moving target detection on adjacent thermal imaging images, and identifying temperature change points and temperature anomaly points in the thermal imaging images. Specifically, first, two temperature thresholds are set. For the judgment of temperature change points, if the temperature difference of a certain coordinate point at adjacent times exceeds the first threshold, then this point is considered a temperature change point; for the judgment of temperature anomaly points, if the temperature of a certain coordinate point is higher than the current ambient average temperature plus the second threshold, then this point is considered a temperature anomaly point. Through this step, areas with large temperature changes and areas with high temperatures can be extracted from the thermal imaging images, laying a foundation for subsequent fire risk analysis.

[0018] Among them, the specific steps of the step S30 include: combining the temperature change points and temperature anomaly points corresponding to all adjacent thermal imaging images into a temperature change point time series matrix and a temperature anomaly point time series matrix respectively. The temperature change point time series matrix records the temperature change information of each coordinate point in the time series, and the temperature anomaly point time series matrix records the absolute temperature value information of each temperature anomaly point in the time series. The purpose of this step is to organize the temperature change point and temperature anomaly point information extracted in the previous step into two two-dimensional matrices, preparing for subsequent matrix decomposition analysis.

[0019] Among them, the specific steps of the step S40 include: decomposing the temperature change point time series matrix by using the singular value decomposition method to obtain a temperature change point uniform change matrix and a temperature change point variable speed change matrix. Singular value decomposition is a commonly used matrix decomposition method, which can decompose the temperature change point time series matrix into two components: one represents the uniform change characteristic of the temperature change points, and the other represents the variable speed change characteristic of the temperature change points. The purpose of this step is to extract two modes of temperature change from the time series, providing a basis for subsequent fire risk analysis.

[0020] Among them, the specific steps of the step S50 include: decomposing the temperature anomaly point time series matrix by using the principal component analysis method to obtain a temperature anomaly point position stable matrix and a temperature anomaly point position change matrix. Principal component analysis is a commonly used data dimensionality reduction and feature extraction method, which can decompose the temperature anomaly point time series matrix into two components: one represents the stable characteristic of the temperature anomaly point position, and the other represents the change characteristic of the temperature anomaly point position. The purpose of this step is to extract two modes of position change from the time series of temperature anomaly points, providing a basis for subsequent fire risk analysis.

[0021] Among them, the specific steps of step S60 include: calculating the fire risk index matrix according to the temperature change point variable speed change matrix and the temperature anomaly point position change matrix by using a preset fire risk matrix calculation equation. This fire risk matrix calculation equation comprehensively considers multiple factors such as the temperature change rate, temperature deviation degree, temperature change trend, and the second derivative of the temperature field, and can more comprehensively reflect the possibility of an initial fire occurring in a certain area. Through this step, the fire risk index of each area can be calculated based on the temperature change characteristics extracted previously, providing a basis for subsequent intelligent patrol decision-making.

[0022] Among them, the specific steps of step S70 include: dynamically adjusting the patrol strategy of the integrated intelligent fire extinguisher according to the calculated fire risk index matrix. Specifically, for areas with a high fire risk index, increase the pause duration of the integrated intelligent fire extinguisher in this area; for areas with a low fire risk index, reduce the pause duration of the integrated intelligent fire extinguisher in this area. Through this step, the patrol strategy of the integrated intelligent fire extinguisher can be dynamically adjusted according to the real-time calculated fire risk situation, so as to better focus on high-risk areas and detect initial fire situations in a timely manner.

[0023] Among them, the specific steps of step S80 include: when the fire risk index of a certain area exceeds the preset initial fire determination threshold, determine that an initial fire has occurred in this area, record the coordinates of the initial fire location, and trigger an alarm. By analyzing historical fire risk index data, a reasonable initial fire determination threshold can be determined. Once the fire risk index of a certain area exceeds this threshold, it means that an initial fire is likely to have occurred in this area. The system will record the coordinate position information of this area and trigger an alarm in a timely manner and take further fire extinguishing measures. The purpose of this step is to make a final determination of the initial fire for the detected high-risk areas, and to give an alarm and response to the initial fire accident in a timely manner.

[0024] Among them, the fire risk matrix calculation equation is specifically expressed as follows:

[0025] The fire risk matrix calculation equation is specifically expressed as follows:

[0026]

[0027] In the formula, R(x, y, t) is the fire risk index at coordinates (x, y) at time t; T(x, y, t) is the temperature value at coordinates (x, y) at time t; T avg (t) is the average ambient temperature at time t; θ(x, y, t) is the phase angle of temperature change; α, β, γ, δ are weight coefficients; i is the imaginary unit; is the Laplace operator.

[0028] Parameter acquisition method:

[0029] T(x, y, t) is directly measured by a thermal imager.

[0030] T avg (t) is obtained by calculating the average temperature of the entire thermal imaging image.

[0031] It is obtained by calculating the temperature difference between adjacent time frames.

[0032] θ(x, y, t) is obtained by calculating the phase of the temperature change through Fourier transform.

[0033] It is obtained by calculating the second derivative of the temperature field through the finite difference method.

[0034] α, β, γ, δ are obtained by training based on historical data through a machine learning method (such as support vector machine regression).

[0035] Determination formula for temperature change points:

[0036] ΔT(x, y, t) = |T(x, y, t) - T(x, y, t - 1)| > λ1;

[0037] Determination formula for temperature abnormal points:

[0038] T(x, y, t) - (T avg (t) + λ2) > 0;

[0039] In the formula, ΔT(x, y, t) is the temperature change amount; λ1 is the first threshold; λ2 is the second threshold.

[0040] Temperature change point time series matrix:

[0041]

[0042] Temperature abnormal point time series matrix:

[0043]

[0044] Singular value decomposition in step S40:

[0045]

[0046] In the formula, is the uniform change matrix of temperature change points; is the variable speed change matrix of temperature change points.

[0047] Principal component analysis in step S50:

[0048]

[0049] In the formula, is the stable matrix of the temperature anomaly point position; is the variable matrix of the temperature anomaly point position.

[0050] The steps for obtaining the first threshold specifically include:

[0051] Collect historical temperature change data and calculate the mean μ ΔT and the standard deviation σ ΔT ;

[0052] Select an appropriate adjustment coefficient k1, usually between 1.5 and 3;

[0053] Apply the formula λ1 = μ ΔT + k1σ ΔT to calculate the first threshold.

[0054] The default value of the first threshold is 5°C;

[0055] The steps for obtaining the second threshold specifically include:

[0056] Analyze historical temperature data to determine the highest temperature T max and the average temperature T avg ;

[0057] Select an appropriate adjustment coefficient k2, usually between 0.1 and 0.3;

[0058] Apply the formula λ2 = k2(T max - T avg ) to calculate the second threshold.

[0059] The default value of the second threshold is 10°C;

[0060] The steps for determining the initial fire judgment threshold specifically include:

[0061] Collect historical fire risk index data and calculate its mean μ R and the standard deviation σ R ;

[0062] Select an appropriate adjustment coefficient k3, usually between 2.5 and 3.5;

[0063] Apply the formula λ3 = μ R + k3σ R to calculate the initial fire judgment threshold.

[0064] The default value of the initial fire judgment threshold is 0.8;

[0065] For areas with a high fire risk index, the pause duration corresponding to the rotation process of the integrated intelligent fire extinguishing is extended; for areas with a low fire risk index, the pause duration corresponding to the rotation process of the integrated intelligent fire extinguishing is reduced. Specifically:

[0066] Set a basic pause duration t base , usually 2 seconds;

[0067] Calculate the average fire risk index R avg , the maximum fire risk index R max and the minimum fire risk index R min in the current scanning period;

[0068] For areas with a high fire risk index (R(x,y,t)>R avg ), the pause duration is calculated as:

[0069]

[0070] For areas with a low fire risk index (R(x,y,t)≤R avg ), the pause duration is calculated as:

[0071]

[0072] Set the upper limit of the pause duration to 5 seconds and the lower limit to 0.5 seconds. If the calculation result exceeds this range, the corresponding upper or lower limit value is taken.

[0073] The second aspect of the present invention provides a computer-readable storage medium, wherein program instructions are stored in the computer-readable storage medium, and when the program instructions run on a computer, they are used to execute the above-mentioned fire prediction variable-frequency patrol method.

[0074] The third aspect of the present invention provides a fire prediction variable-frequency patrol system, which includes the above-mentioned computer-readable storage medium.

[0075] Compared with the prior art, the beneficial effects of the fire prediction variable-frequency patrol method, medium and system provided by the present invention are:

[0076] 1. Real-time and efficient detection of fire hazards. This method uses a thermal imager to collect temperature distribution information in the monitored area in real time, and accurately identifies areas with abnormal temperature changes and high temperatures using the frame difference method and threshold judgment, providing a reliable basis for subsequent fire warnings. Compared with single temperature monitoring or video surveillance, this method can more comprehensively and accurately detect potential fire hazards.

[0077] 2. Intelligent inspection strategy optimization. This method calculates the fire risk index of each area through matrix analysis of temperature change characteristics, and dynamically adjusts the inspection strategy of the integrated intelligent fire extinguisher according to risk assessment. Increase the inspection time for high-risk areas and reduce the inspection frequency for low-risk areas, so as to effectively focus monitoring resources on key parts. This intelligent inspection strategy based on fire risk can greatly improve the early warning efficiency of the monitoring system.

[0078] 3. Timely and rapid detection and alarm of initial fires. Once the fire risk index of a certain area exceeds the preset threshold, this method can quickly determine that an initial fire has occurred in this area, record the fire location and immediately trigger an alarm. This initial fire determination mechanism based on quantitative risk assessment can detect fire hazards in a timely manner and respond quickly, providing valuable emergency support for the fire department.

[0079] 4. Flexible and adaptable integrated design. This method uses the integrated intelligent fire extinguisher as the core execution unit, integrating functions such as thermal imaging monitoring, risk analysis, and inspection decision-making. This integrated design not only facilitates system deployment and maintenance, but also can flexibly meet the monitoring requirements of different environments, improving the overall applicability and reliability.

[0080] In summary, the thermal imaging fire prediction and variable frequency inspection method proposed by the present invention is significantly superior to existing fire protection and monitoring technologies in terms of real-time monitoring, intelligent analysis, and rapid response. It solves the technical problem that in the prior art, fire protection inspections often adopt fixed rotation speeds or frequencies, and there is no way to dynamically adjust the inspection strategy according to the fire risks of different areas. Description of the Drawings

[0081] Figure 1 It is a flowchart of the method provided by the present invention;

[0082] Figure 2 It is a specific structural schematic diagram of the integrated intelligent fire extinguisher in Embodiment 2;

[0083] Figure 3 It is a schematic diagram of the inspection area of the integrated intelligent fire extinguisher in Embodiment 2;

[0084] Figure 4 It is a thermal imaging schematic diagram of the internal temperature distribution of the warehouse in Embodiment 2;

[0085] Figure 5 It is a distribution schematic diagram of temperature change points and temperature anomaly points in Embodiment 2;

[0086] Figure 6 It is a distribution schematic diagram of the fire risk index of each area in Embodiment 2;

[0087] Figure 7It is a schematic diagram showing the change of the inspection path and pause duration of the integrated intelligent fire extinguisher in Embodiment 2. Detailed implementation manners

[0088] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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.

[0089] As Figure 1 shown, it is a flowchart of a fire prediction variable-frequency inspection method provided by the first aspect of the present invention. This method includes the following steps:

[0090] S10. Real-time obtain the thermal imaging images collected during the rotation of the integrated intelligent fire extinguisher; the integrated intelligent fire extinguisher is equipped with a pan-tilt, and a thermal imager is arranged on the pan-tilt for collecting thermal imaging images;

[0091] S20. Use the frame difference method to perform moving target detection on adjacent thermal imaging images, and identify the temperature change points and temperature anomaly points in the thermal imaging images; the temperature change points refer to the points where the temperature change between adjacent frames exceeds a preset first threshold; the temperature anomaly points refer to the points where the temperature is higher than the sum of the ambient average temperature and a preset second threshold;

[0092] S30. Combine all the temperature change points and temperature anomaly points corresponding to the adjacent thermal imaging images into a temperature change point time series matrix and a temperature anomaly point time series matrix respectively;

[0093] S40. Decompose the temperature change point time series matrix by using the singular value decomposition method to obtain a temperature change point uniform change matrix and a temperature change point variable speed change matrix;

[0094] S50. Decompose the temperature anomaly point time series matrix by using the principal component analysis method to obtain a temperature anomaly point position stable matrix and a temperature anomaly point position change matrix;

[0095] S60. According to the temperature change point variable speed change matrix and the temperature anomaly point position change matrix, calculate the fire risk index matrix by using a preset fire risk matrix calculation equation; each element in the fire risk index matrix is a vector, including coordinates and a fire risk index. The higher the fire risk index, the greater the possibility of an initial fire occurring in the area corresponding to the coordinates;

[0096] S70. Dynamically adjust the inspection strategy of the pan-tilt according to the calculated fire risk index matrix: for the areas with a high fire risk index, increase the corresponding pause duration during the rotation of the integrated intelligent fire extinguisher; for the areas with a low fire risk index, reduce the corresponding pause duration during the rotation of the integrated intelligent fire extinguisher;

[0097] S80. When the fire risk index of a certain area exceeds the preset initial fire determination threshold, it is determined that an initial fire has occurred in this area, the coordinates of the initial fire location are recorded, and an alarm is triggered.

[0098] The specific implementation manners of the above steps are described in detail as follows:

[0099] The specific implementation manner of step S10 is: obtain in real time the thermal imaging images collected during the rotation of the integrated intelligent fire extinguisher. The integrated intelligent fire extinguisher is designed to be installed with a pan-tilt, and a thermal imager is equipped on the pan-tilt. The thermal imager can capture the surface temperature distribution information of the objects in the monitored area and convert it into thermal imaging images. During the variable-frequency patrol inspection, the thermal imager will continuously collect real-time thermal imaging images, providing a data basis for subsequent temperature change analysis.

[0100] The specific implementation manner of step S20 is: use the frame difference method to detect moving targets in adjacent thermal imaging images, and identify the temperature change points and temperature abnormal points in the thermal imaging images. The so-called frame difference method refers to detecting the temperature change area in the image by calculating the temperature difference between two adjacent frames of thermal imaging images. Specifically, first set two temperature thresholds λ1 and λ2. For the judgment of temperature change points, if the temperature difference |ΔT(x,y,t)| = |T(x,y,t) - T(x,y,t - 1)| of a certain coordinate (x,y) at time t is greater than the first threshold λ1 compared with the previous moment t - 1, then this point is considered a temperature change point. For the judgment of temperature abnormal points, if the temperature T(x,y,t) of a certain coordinate (x,y) at time t is higher than the average ambient temperature T avg (t) plus the second threshold λ2, then this point is considered a temperature abnormal point. The purpose of this step is to extract the areas with large temperature changes and the areas with high temperatures from the thermal imaging images, laying a foundation for subsequent fire risk analysis. Regarding the setting of the two temperature thresholds λ1 and λ2, the following method can be referred to: first collect historical temperature change data, calculate the mean μ ΔT and standard deviation σ ΔT , then select an appropriate adjustment coefficient k1 (usually taken between 1.5 and 3), and apply the formula λ1 = μ ΔT + k1σ ΔT to calculate the first threshold λ1; analyze the historical temperature data, determine the highest temperature T max and the average temperature T avg , select the adjustment coefficient k2 (usually taken between 0.1 and 0.3), and apply the formula λ2 = k2(T max - T avg ) to calculate the second threshold λ2. The default value of λ1 is 5 degrees Celsius, and the default value of λ2 is 10 degrees Celsius.

[0101] The specific implementation of step S30 is as follows: Combine the temperature change points and temperature anomaly points corresponding to all adjacent thermal imaging images into a temperature change point time series matrix and a temperature anomaly point time series matrix respectively. The temperature change point time series matrix M change is constructed as follows: Assume that the resolution of the thermal imaging image is m×n pixels and the length of the captured time series is n frames, then M change is an m×n matrix, where the (i,j)-th element ΔT(x i ,y i ,t j ) represents the temperature change amount of the coordinate (x i ,y i ) at the j-th moment compared with the previous moment. The temperature anomaly point time series matrix M abnormal is constructed as follows: Assume that the number of temperature anomaly points is k, then M abnormal is a k×n matrix, where the (p,q)-th element T(x p ,y p ,t q ) represents the absolute temperature value of the p-th temperature anomaly point at the q-th moment. The purpose of this step is to organize the temperature change point and temperature anomaly point information extracted in the previous step into two two-dimensional matrices to prepare for the subsequent matrix decomposition analysis.

[0102] The specific implementation of step S40 is as follows: Decompose the temperature change point time series matrix M change by using singular value decomposition to obtain a temperature change point uniform change matrix and a temperature change point variable speed change matrix. Singular value decomposition is a commonly used matrix decomposition method, which can decompose any m×n matrix M into the form of M = U∑V T , where U is an m×n orthogonal matrix, Σ is an m×n diagonal matrix, and V is an n×n orthogonal matrix. For the temperature change point time series matrix M change , it can be decomposed into where represents the uniform change component of the temperature change point, and represents the variable speed change component of the temperature change point. The purpose of this step is to extract two modes of temperature change from the time series: one is a relatively stable temperature change, and the other is a violently fluctuating temperature change, providing a basis for the subsequent fire risk analysis.

[0103] The specific implementation of step S50 is as follows: For the temperature anomaly point time series matrix M abnormalDecompose by means of principal component analysis to obtain the stable matrix of the temperature anomaly point positions and the changing matrix of the temperature anomaly point positions. Principal component analysis is a commonly used method for data dimensionality reduction and feature extraction. It can represent an n-dimensional data set as a number of mutually orthogonal principal components. For the time series matrix M of temperature anomaly points abnormal , it can be decomposed into where represents the stable component of the temperature anomaly point positions, represents the changing component of the temperature anomaly point positions. The purpose of this step is to extract two patterns of position changes from the time series of temperature anomaly points: one is the relatively stable position distribution, and the other is the continuously changing position distribution, providing a basis for subsequent fire risk analysis.

[0104] The specific implementation of step S60 is: According to the variable speed changing matrix of temperature change points and the changing matrix of temperature anomaly point positions, calculate the fire risk index matrix using a preset fire risk matrix calculation equation. The specific form of the fire risk matrix calculation equation is:

[0105]

[0106] where, R(x, y, t) is the fire risk index at coordinates (x, y) at time t; T(x, y, t) is the temperature value at this coordinate point at this moment; T avg (t) is the average ambient temperature at this moment; θ(x, y, t) is the phase angle of temperature change; α, β, γ, δ are weight coefficients. This fire risk matrix calculation formula comprehensively considers factors such as the temperature change rate, temperature deviation degree, temperature change trend, and the second derivative of the temperature field, and can more comprehensively reflect the possibility of an initial fire occurring in a certain area. Among them, T(x, y, t) is directly measured by a thermal imager, and T avg (t) is obtained by calculating the average temperature of the entire thermal imaging image, is obtained by calculating the temperature difference between adjacent time frames, θ(x, y, t) is obtained by calculating the phase of temperature change through Fourier transform, is obtained by calculating the second derivative of the temperature field through the finite difference method. The 4 weight coefficients α, β, γ, δ need to be obtained through training based on historical data by machine learning methods (such as support vector machine regression). The purpose of this step is to comprehensively calculate the fire risk index of each area according to the previously extracted temperature change characteristics, providing a basis for subsequent intelligent patrol decision-making.

[0107] The specific implementation of step S70 is as follows: According to the calculated fire risk index matrix, dynamically adjust the inspection strategy of the pan-tilt. Specifically, for areas with a high fire risk index, increase the pause duration of the integrated intelligent fire extinguisher in that area; for areas with a low fire risk index, reduce the pause duration of the integrated intelligent fire extinguisher in that area. Set the basic pause duration t base to 2 seconds, and calculate the average fire risk index R avg , the maximum fire risk index R max and the minimum fire risk index R min within the current scanning period. For areas with a high fire risk index (R(x,y,t)>R avg ), the pause duration is calculated as For areas with a low fire risk index (R(x,y,t)≤R avg ), the pause duration is calculated as The upper limit of the pause duration is set to 5 seconds, and the lower limit is set to 0.5 seconds. If the calculation result exceeds this range, the corresponding upper or lower limit value is taken. The purpose of this step is to dynamically adjust the inspection strategy of the integrated intelligent fire extinguisher according to the real-time calculated fire risk situation, so as to better focus on high-risk areas and detect incipient fires in a timely manner.

[0108] The specific implementation of step S80 is as follows: When the fire risk index of a certain area exceeds the preset incipient fire determination threshold, it is determined that an incipient fire has occurred in that area, record the coordinates of the incipient fire location, and trigger an alarm. The steps to obtain the incipient fire determination threshold are as follows: First, collect historical fire risk index data and calculate its mean μ R and standard deviation σ R , then select an appropriate adjustment coefficient k3 (usually between 2.5 and 3.5), and apply the formula λ3 = μ R + k3σ R to calculate the incipient fire determination threshold λ3. The default value of λ3 is 0.8. Once the fire risk index of a certain area exceeds λ3, it means that an incipient fire is very likely to have occurred in that area. The system will record the coordinate position information of that area, trigger an alarm and take further fire extinguishing measures. The purpose of this step is to make a final incipient fire determination for the detected high-risk areas, and to give an alarm and respond to incipient fire accidents in a timely manner.

[0109] To better understand and implement the present invention, a specific embodiment 1 of the method of the first aspect of the present invention is provided below. The specific implementation of each step of this embodiment 1 is described in detail as follows: The specific implementation of step S10 is: Real-time acquisition of the thermal imaging images collected during the rotation of the integrated intelligent fire extinguisher. The integrated intelligent fire extinguisher is designed and installed with a pan-tilt head, and a thermal imager is equipped on the pan-tilt head. The thermal imager can capture the surface temperature distribution information of the objects in the monitored area and convert it into thermal imaging images. During the variable-frequency patrol inspection, the thermal imager will continuously collect real-time thermal imaging images, providing a data basis for subsequent temperature change analysis.

[0110] The specific implementation of step S20 is: Using the frame difference method to perform moving target detection on adjacent thermal imaging images, and identifying the temperature change points and temperature abnormal points in the thermal imaging images. The so-called frame difference method refers to detecting the temperature change area in the image by calculating the temperature difference between two adjacent frames of thermal imaging images. Specifically, first set two temperature thresholds λ1 and λ2. For the judgment of temperature change points, if the temperature difference |ΔT(x,y,t)| = |T(x,y,t) - T(x,y,t - 1)| of a certain coordinate (x,y) at time t is greater than the first threshold λ1 compared with the previous moment t - 1, then it is considered that this point is a temperature change point, which can be expressed by the following formula:

[0111] ΔT(x,y,t) = |T(x,y,t) - T(x,y,t - 1)| > λ1;

[0112] For the judgment of temperature abnormal points, if the temperature T(x,y,t) of a certain coordinate (x,y) at time t is higher than the average ambient temperature T avg (t) plus the second threshold λ2, then it is considered that this point is a temperature abnormal point, which can be expressed by the following formula:

[0113] T(x,y,t) - (T avg (t) + λ2) > 0;

[0114] The purpose of this step is to extract the areas with large temperature changes and the areas with high temperatures from the thermal imaging images, laying a foundation for subsequent fire risk analysis. Regarding the setting of the two temperature thresholds λ1 and λ2, the following method can be referred to: First, collect historical temperature change data, calculate the mean μ ΔT and the standard deviation σ ΔT , then select a suitable adjustment coefficient k1 (usually taken between 1.5 and 3), and apply the formula λ1 = μ ΔT + k1σ ΔT to calculate the first threshold λ1; analyze the historical temperature data to determine the highest temperature T max and the average temperature T avg, select the adjustment coefficient k2 (usually taken between 0.1 and 0.3), and apply the formula λ2 = k2(T max -T avg ) to calculate the second threshold λ2. The default value of λ1 is 5 degrees Celsius, and the default value of λ2 is 10 degrees Celsius.

[0115] The specific implementation of step S30 is as follows: Combine the temperature change points and temperature anomaly points corresponding to all adjacent thermal imaging images into a temperature change point time series matrix and a temperature anomaly point time series matrix respectively. The temperature change point time series matrix M change is constructed as follows: Assume that the resolution of the thermal imaging image is m×n pixels, and the length of the captured time series is n frames, then M change is an m×n matrix, where the (i,j)th element ΔT(x i ,y i ,t j ) represents the temperature change amount of the coordinate (x i ,y i ) at the jth moment compared with the previous moment, and can be represented by the following matrix:

[0116]

[0117] The temperature anomaly point time series matrix M abnormal is constructed as follows: Assume that the number of temperature anomaly points is k, then M abnormal is a k×n matrix, where the (p,q)th element T(x p ,y p ,t q ) represents the absolute temperature value of the pth temperature anomaly point at the qth moment, and can be represented by the following matrix:

[0118]

[0119] The purpose of this step is to organize the temperature change points and temperature anomaly point information extracted in the previous step into two two-dimensional matrices to prepare for the subsequent matrix decomposition analysis.

[0120] The specific implementation of step S40 is as follows: Decompose the temperature change point time series matrix M change by using the singular value decomposition method to obtain the temperature change point uniform change matrix and the temperature change point variable speed change matrix. Singular value decomposition is a commonly used matrix decomposition method, which can decompose any m×n matrix M into the form of M = U∑V T , where U is an m×m orthogonal matrix, ∑ is an m×n diagonal matrix, and V is an n×n orthogonal matrix. For the temperature change point time series matrix M change , it can be decomposed into where Represents the uniform change component of the temperature change point, Represents the variable speed change component of the temperature change point, which can be expressed by the following mathematical formula:

[0121]

[0122] The purpose of this step is to extract two patterns of temperature change from the time series: one is the relatively stable temperature change, and the other is the violently fluctuating temperature change, providing a basis for subsequent fire risk analysis.

[0123] The specific implementation of step S50 is: for the time series matrix M of temperature anomaly points abnormal Adopt the method of principal component analysis for decomposition to obtain the stable matrix of temperature anomaly point positions and the variable matrix of temperature anomaly point positions. Principal component analysis is a commonly used method for data dimensionality reduction and feature extraction, which can represent an n-dimensional data set as several mutually orthogonal principal components. For the time series matrix M of temperature anomaly points abnormal , it can be decomposed into where Represents the stable component of the temperature anomaly point position, Represents the variable component of the temperature anomaly point position, which can be expressed by the following mathematical formula:

[0124]

[0125] The purpose of this step is to extract two patterns of position change from the time series of temperature anomaly points: one is the relatively stable position distribution, and the other is the continuously changing position distribution, providing a basis for subsequent fire risk analysis.

[0126] The specific implementation of step S60 is: according to the variable speed change matrix of temperature change points and the variable matrix of temperature anomaly point positions, use the preset fire risk matrix calculation equation to calculate the fire risk index matrix. The specific form of the fire risk matrix calculation equation is:

[0127]

[0128] where R(x, y, t) is the fire risk index at coordinates (x, y) at time t; T(x, y, t) is the temperature value at this coordinate point at this moment; T avg (t) is the average ambient temperature at this moment; θ(x, y, t) is the phase angle of temperature change; α, β, γ, δ are weight coefficients. This fire risk matrix calculation formula comprehensively considers factors such as the temperature change rate, temperature deviation degree, temperature change trend, and second derivative of the temperature field, and can more comprehensively reflect the possibility of an initial fire occurring in a certain area. Among them, T(x, y, t) is directly measured by a thermal imager, T avg(t) is obtained by calculating the average temperature of the entire thermal imaging image. It is obtained by calculating the temperature difference between adjacent time frames. θ(x, y, t) is obtained by calculating the phase of the temperature change through Fourier transform. It is obtained by calculating the second derivative of the temperature field using the finite difference method. The four weight coefficients α, β, γ, and δ need to be obtained through training based on historical data using machine learning methods (such as support vector machine regression). The purpose of this step is to comprehensively calculate the fire risk index of each area based on the temperature change characteristics extracted previously, providing a basis for subsequent intelligent patrol decisions.

[0129] The specific implementation of step S70 is as follows: According to the calculated fire risk index matrix, dynamically adjust the patrol strategy of the pan-tilt. Specifically, for areas with a high fire risk index, increase the pause duration of the integrated intelligent fire extinguisher in that area; for areas with a low fire risk index, reduce the pause duration of the integrated intelligent fire extinguisher in that area. Set the basic pause duration t base to 2 seconds, and calculate the average fire risk index R avg , the maximum fire risk index R max and the minimum fire risk index R min in the current scan cycle. For areas with a high fire risk index (R(x, y, t) > R avg ), the pause duration is calculated as:

[0130]

[0131] For areas with a low fire risk index (R(x, y, t) ≤ R avg ), the pause duration is calculated as:

[0132]

[0133] The upper limit of the pause duration is set to 5 seconds, and the lower limit is set to 0.5 seconds. If the calculation result exceeds this range, the corresponding upper or lower limit value is taken. The purpose of this step is to dynamically adjust the patrol strategy of the integrated intelligent fire extinguisher according to the real-time calculated fire risk situation, so as to better focus on high-risk areas and detect incipient fires in a timely manner.

[0134] The specific implementation of step S80 is as follows: When the fire risk index of a certain area exceeds the preset initial fire determination threshold, it is determined that an initial fire has occurred in that area, record the coordinates of the initial fire location, and trigger an alarm. The steps to obtain the initial fire determination threshold are as follows: First, collect historical fire risk index data, calculate its mean μ R and standard deviation σ R , then select an appropriate adjustment coefficient k3 (usually between 2.5 and 3.5), and apply the formula λ3 = μ R + k3σR Calculate the initial fire determination threshold λ3. The default value of λ3 is 0.8. Once the fire risk index of a certain area exceeds λ3, it indicates that an initial fire is likely to have occurred in that area. The system will record the coordinate position information of that area and trigger an alarm and take further fire extinguishing measures. The purpose of this step is to conduct a final initial fire determination for the detected high-risk areas and to give an alarm and respond in a timely manner to the initial fire accident.

[0135] The second aspect of the present invention provides a computer-readable storage medium, wherein program instructions are stored in the computer-readable storage medium, and when the program instructions run on a computer, they are used to execute the above-mentioned method for frequency conversion patrol inspection for fire prediction.

[0136] The third aspect of the present invention provides a system for frequency conversion patrol inspection for fire prediction, which includes the above-mentioned computer-readable storage medium.

[0137] Specifically, the principle of the present invention is: make full use of thermal imaging technology to obtain the temperature distribution information of the monitored area, and through complex mathematical analysis means, accurately model and evaluate the risks of these temperature change characteristics. Specifically, the method mainly includes the following key steps:

[0138] First, the thermal imager equipped on the integrated intelligent fire extinguisher will collect thermal imaging images of the monitored area in real time. These thermal imaging images contain rich temperature change information, which is an important data basis for subsequent identification of fire hazards.

[0139] Secondly, the frame difference method is used to detect moving targets in adjacent thermal imaging images, and the points with large temperature changes and high temperatures in the monitored area can be accurately located. These temperature change points and temperature abnormal points reflect potential fire hazards in the local environment.

[0140] Then, these temperature change points and temperature abnormal points are organized in a matrix form in the time series to obtain a temperature change point time series matrix and a temperature abnormal point time series matrix. These two matrices respectively record the trend characteristics of temperature changes and the distribution characteristics of high temperatures.

[0141] Next, the singular value decomposition is adopted for the temperature change point time series matrix, which can be decomposed into a uniform change component and a variable speed change component of the temperature change points; the principal component analysis is adopted for the temperature abnormal point time series matrix, which can be decomposed into a stable component and a change component of the positions of the temperature abnormal points. These decomposition results reveal the potential laws of temperature changes and the positions of abnormal points.

[0142] Finally, based on the temperature change characteristics extracted above, through the designed calculation formula of the fire risk matrix, the fire risk index of each area can be calculated. This formula comprehensively considers multiple factors such as the temperature change rate, temperature deviation degree, temperature change trend, and the second derivative of the temperature field, and can relatively comprehensively reflect the possibility of an initial fire occurring in a certain area.

[0143] Based on the calculated fire risk index matrix, this method can dynamically adjust the inspection strategy of the integrated intelligent fire extinguisher. Increase the inspection time for high-risk areas and reduce the inspection frequency for low-risk areas, so as to effectively concentrate monitoring resources on key parts. Once the risk index of a certain area exceeds the preset threshold, it can be determined that an initial fire has occurred and an alarm will be issued immediately.

[0144] To further better understand and implement the present invention, the following provides an embodiment 2 of a specific application scenario of the present invention in combination with a specific integrated intelligent fire extinguisher. The integrated intelligent fire extinguishing system in this embodiment 2 uses an integrated intelligent fire extinguisher as Figure 2 shown, including: a ceiling-mounted fire extinguishing agent tank; if there are sprinkler pipes / fire pipes, this fire extinguishing agent tank does not need to be configured; an inspection robot base; a 90° inspection camera; a built-in battery / pump / valve; an audible and visual alarm; a 360° inspection camera; a smoke sensor; various detection sensors / AI cameras; a fire extinguishing nozzle; the initial position is manually set to 0°, or 0 sensors can also be deployed. After working, according to the actual measurement of the stepping motor and the structure, record the starting positions of 360° and 90°. After powering on and working, conduct a 360° inspection. According to the set parameters, rotate within the set inspection range, up to 360° (can be set from 0 to 360°), and then return reciprocally. For the 90° inspection, the initial position is perpendicular to the ground and can rotate up to 90°. Rotate according to the set parameters, up to 90° (can be set from 0 to 90°).

[0145] Among them, the action logics of the 360° inspection, 90° inspection, and thermal imaging detection are specifically: taking the 360° inspection as the benchmark, every time it rotates one circle, the 90° changes by a set angle, and this angle is projected onto the inspection area to form a complete coverage, such as ceiling + wall, wall + ground, ground + depth ground. After setting the "jump angle", in each 360° inspection cycle, add 1 jump angle to the 90° jump angle. For example, if 3 jump angles are set, after all are completed, add 1 jump angle in the reverse direction. Thus, it goes round and round. After the sensor structure is locked, in each 360° inspection cycle, the sensor is stationary at the set angle, so it will not affect the thermal imaging response speed. When a fire point is captured, it can automatically track and control the rotation of the stepping motor, but the program should record to find the 0 point, such as Figure 3As shown. After detecting a fire point, the 360° stepper motor stops and enters the left-right rotation automatic tracking state. Of course, the number of steps advanced also needs to be recorded to return to point 0. During the inspection process, this integrated intelligent fire extinguisher considers adopting the solution of the present invention to achieve more efficient variable-frequency inspection; the specific description is as follows.

[0146] Before officially enabling this intelligent monitoring system, the operation and maintenance personnel calibrated and tested the key parameters of the system. First, by collecting the historical temperature change data of the warehouse, the mean and standard deviation of the temperature change amount were calculated, thereby determining the first threshold λ1. Specifically, the mean μ of the temperature change amount ΔT is 3.2 degrees Celsius, and the standard deviation σ ΔT is 1.0 degree Celsius. Selecting the adjustment coefficient k1 as 2, the calculation result of the first threshold λ1 is 5.2 degrees Celsius.

[0147] Similarly, after analyzing the historical temperature data of the warehouse, the highest temperature T max is determined to be 35 degrees Celsius, and the average temperature T avg is 20 degrees Celsius. Selecting the adjustment coefficient k2 as 0.2, the calculation result of the second threshold λ2 is 3 degrees Celsius.

[0148] In addition, the operation and maintenance personnel also calculated the mean and standard deviation of the historical fire risk index by collecting the past fire accident data of the warehouse, thereby determining the initial fire judgment threshold λ3. After statistics, the mean μ of the historical fire risk index R is 0.6, and the standard deviation σ R is 0.1. Selecting the adjustment coefficient k3 as 3, the calculation result of the initial fire judgment threshold λ3 is 0.9.

[0149] The above three key thresholds λ1, λ2, and λ3 are set as the default parameters of the system and do not need to be frequently adjusted during the actual operation process without special needs.

[0150] After the installation and debugging work is completed, this integrated intelligent fire extinguishing system is officially put into use. The daily routine inspection process is as follows:

[0151] 1. The thermal imager collects the thermal imaging images inside the warehouse in real time to obtain the real-time temperature distribution information.

[0152] 2. Use the frame difference method to analyze adjacent thermal imaging images to identify the temperature change points and temperature abnormal points. According to the foregoing judgment formula:

[0153] ΔT(x,y,t) = |T(x,y,t) - T(x,y,t - 1)| > λ1;

[0154] T(x,y,t) - (T avg (t) + λ2) > 0;

[0155] For the pixel points that meet the above conditions, they are determined as temperature change points and temperature anomaly points.

[0156] 3. Organize all temperature change points and temperature anomaly points into two matrices in the time series: the time series matrix M of temperature change points change and the time series matrix M of temperature anomaly points abnormal .

[0157] Time series matrix of temperature change points:

[0158]

[0159] Time series matrix of temperature anomaly points:

[0160]

[0161] 4. Perform singular value decomposition on the time series matrix M of temperature change points change to obtain the uniform change component and variable speed change component of temperature change points:

[0162]

[0163] 5. Perform principal component analysis on the time series matrix M of temperature anomaly points abnormal to obtain the stable component and change component of the position of temperature anomaly points:

[0164]

[0165] 6. According to the above-extracted temperature change characteristics, calculate the fire risk index of each area through the fire risk matrix calculation formula:

[0166]

[0167] Among them, the weight coefficients obtained by training through machine learning methods are: α = 0.4, β = 0.3, γ = 0.2, δ = 0.1.

[0168] 7. Dynamically adjust the inspection strategy of the integrated intelligent fire extinguisher according to the calculated fire risk index matrix. For the areas where the fire risk index is higher than the average value, increase the inspection duration; for the areas where the fire risk index is lower than the average value, reduce the inspection duration. The specific calculation method is as follows:

[0169] Let the basic pause duration t base = 2 seconds. During a certain inspection process, the calculated parameters are: R avg = 0.5, R max = 0.8, R min = 0.2. Then the actual pause duration of each area is calculated as follows:

[0170] For high-risk areas (R(x, y, t) > 0.5): t pause (x, y) = 2(1 + ) = 2(1 + 2);

[0171] For low-risk areas (R(x, y, t) ≤ 0.5):

[0172]

[0173] The upper limit of the pause duration is set to 5 seconds, and the lower limit is set to 0.5 seconds.

[0174] 8. When the fire risk index R(x, y, t) of a certain area exceeds the initial fire determination threshold λ3 = 0.9, immediately determine that an initial fire has occurred in this area, record the coordinate position where the initial fire occurred, and trigger an alarm.

[0175] Next, the operation of the system in the warehouse environment is visually demonstrated through some charts.

[0176] First, the change in the internal temperature distribution of the warehouse during a certain inspection tour is plotted. Figure 4 The thermal imaging images at three preset time points (t1, t2, t3) are shown, and it can be clearly seen that there are significant differences in the temperature distribution inside the warehouse.

[0177] Figure 5 The distribution of temperature change points and temperature anomaly points during a certain inspection tour is shown. It can be seen from the figure that the temperature change points are mainly concentrated in some local areas of the warehouse, while the temperature anomaly points are more dispersed.

[0178] Figure 6 The distribution of the fire risk index in each area during a certain inspection tour is shown. It can be seen from the figure that there are relatively high fire risks in the northwest corner and the southeast corner of the warehouse, while the risk in the central area is relatively low.

[0179] Finally, Figure 7 The change in the inspection path and pause duration of the integrated intelligent fire extinguisher after adopting the dynamic inspection strategy is shown. It can be seen from the figure that the system concentrates more inspection time on high-risk areas, while reducing the inspection duration for low-risk areas accordingly.

[0180] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A method for predicting fire and performing frequency conversion patrol inspection, characterized in that, Including the following steps: S10. Obtain in real time the thermal imaging images collected during the rotation of the integrated intelligent fire extinguisher; the integrated intelligent fire extinguisher is equipped with a pan-tilt, and a thermal imager is arranged on the pan-tilt for collecting thermal imaging images; S20. Use the frame difference method to perform moving target detection on adjacent thermal imaging images, and identify the temperature change points and temperature anomaly points in the thermal imaging images; the temperature change points refer to the points where the temperature change between adjacent frames exceeds a preset first threshold; the temperature anomaly points refer to the points where the temperature is higher than the sum of the ambient average temperature and a preset second threshold; S30. Combine the temperature change points and temperature anomaly points corresponding to all adjacent thermal imaging images into a temperature change point time series matrix and a temperature anomaly point time series matrix respectively; S40. Decompose the temperature change point time series matrix by using the singular value decomposition method to obtain a temperature change point uniform change matrix and a temperature change point variable speed change matrix; S50. Decompose the temperature anomaly point time series matrix by using the principal component analysis method to obtain a temperature anomaly point position stable matrix and a temperature anomaly point position change matrix; S60. According to the temperature change point variable speed change matrix and the temperature anomaly point position change matrix, calculate the fire risk index matrix by using a preset fire risk matrix calculation equation; Each element in the fire risk index matrix is a vector, including coordinates and a fire risk index. The higher the fire risk index, the greater the possibility of an incipient fire occurring in the area corresponding to the coordinates; S70. Dynamically adjust the inspection strategy of the pan-tilt according to the calculated fire risk index matrix: for areas with a high fire risk index, increase the pause duration corresponding to the rotation process of the integrated intelligent fire extinguisher; for areas with a low fire risk index, reduce the pause duration corresponding to the rotation process of the integrated intelligent fire extinguisher; S80. When the fire risk index of a certain area exceeds a preset incipient fire determination threshold, determine that an incipient fire has occurred in this area, record the coordinates of the incipient fire location, and trigger an alarm; Among them, the fire risk matrix calculation equation is specifically expressed as follows: ; In the formula, is the coordinate at time of the fire risk index; is the coordinate at time of the temperature value; is the time of the average ambient temperature; is the phase angle of the temperature change, obtained by calculating the phase of the temperature change through Fourier transform; is the weight coefficient; is the imaginary unit; is obtained by calculating the second-order derivative of the temperature field through the finite difference method.

2. The fire-starting prediction variable-frequency patrol inspection method according to claim 1, wherein, The determination formula for temperature change points is expressed as follows: ; The determination formula for temperature anomaly points: ; In the formula, is the temperature change amount; is the first threshold; is the second threshold.

3. The fire-starting prediction frequency conversion inspection method according to claim 2, wherein The temperature change point time series matrix is expressed as follows: ； The temperature anomaly point time series matrix is expressed as follows: 。 4. The method for fire prediction and variable-frequency patrol inspection according to claim 3, characterized in that The singular value decomposition is specifically expressed as follows: ; In the formula, is the uniform change matrix of the temperature change point; is the variable-speed change matrix of the temperature change point, where is matrix, is orthogonal matrix, is diagonal matrix, is orthogonal matrix.

5. A method for predicting fire and performing variable-frequency patrol inspection according to claim 4, characterized in that, The steps for obtaining the first threshold specifically include: Collect historical temperature change data and calculate the mean of the temperature change amounts and the standard deviation ; Select an appropriate adjustment coefficient ; Apply the formula to calculate the first threshold value.

6. The fire-starting prediction frequency conversion inspection method according to claim 5, characterized in that, The steps for obtaining the second threshold specifically include: Analyze historical temperature data to determine the maximum temperature and the average temperature ; Select an appropriate adjustment coefficient ; Apply the formula to calculate the second threshold value.

7. A method for predicting fire and frequency conversion patrol inspection according to claim 6, characterized in that, The steps for obtaining the incipient fire determination threshold specifically include: Collect historical fire risk index data and calculate its mean value and standard deviation ; Select an appropriate adjustment coefficient ; Apply the formula to calculate the initial fire determination threshold value.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program instructions, and when the program instructions run on a computer, they are used to execute a fire prediction variable frequency inspection method according to any one of claims 1-7.

9. A fire prediction variable-frequency patrol inspection system, characterized in that, Including the computer-readable storage medium according to claim 8.

Images