Aerosol fire extinguishing monitoring system based on digitization

Abstract

The invention discloses an aerosol fire extinguishing monitoring system based on digitization. The aerosol fire extinguishing monitoring system comprises a data acquisition module, a distance measurement definition module, a local factor design module, a clustering processing module, a parameter optimization module and an aerosol fire extinguishing monitoring module. The invention belongs to the field of data processing, and particularly relates to an aerosol fire extinguishing monitoring system based on digitization. According to the scheme, a positive definite matrix is introduced to define distance measurement, and correlation of all sensors is considered; euclidean distance attenuation and time weight are introduced to design local factors, and single-point noise and instantaneous anomaly of aerosol fire extinguishing monitoring are effectively inhibited; on the basis of a reward and punishment mechanism of secondary membership updating, rewards are given to core area data, outliers are suppressed, and identification of real anomaly monitoring is further enhanced; the accuracy of fire extinguishing monitoring is obviously improved; on the basis of an exploration type global updating mechanism and a utilization type local updating mechanism, the dual requirements for quick response and optimization precision are met; and the fire extinguishing monitoring effect is improved.

Description

Technical Field

[0001] The invention relates to the field of data processing, and in particular to an aerosol fire extinguishing monitoring system based on digitization. Background Art

[0002] The aerosol fire extinguishing monitoring system is a comprehensive system for real-time perception, analysis and feedback of the distribution and concentration of aerosol fire extinguishing agents in the protected area. However, the general aerosol fire extinguishing monitoring system has parameters with different correlations that are difficult to compare fairly, which is prone to false detection or missed detection, lacks the coordinated use of information between adjacent sensors, and does not effectively handle sudden instantaneous interference, which leads to poor accuracy of fire extinguishing monitoring; the general aerosol fire extinguishing monitoring system has improper hyperparameter settings, and the optimization process is difficult to balance rapid response and optimization accuracy, which leads to poor fire extinguishing monitoring effects. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a digital aerosol fire extinguishing monitoring system. In view of the fact that the parameters of different correlations in the general aerosol fire extinguishing monitoring system are difficult to compare fairly, it is easy to produce false detection or missed detection, lack of coordinated use of information between adjacent sensors, and no effective processing of sudden instantaneous interference, which leads to the problem of poor accuracy of fire extinguishing monitoring, this scheme introduces a positive definite matrix to define the distance metric, taking into account the correlation of each sensor; introduces Euclidean distance decay and time weight to design local factors, effectively suppressing single-point noise and instantaneous anomalies of aerosol fire extinguishing monitoring; based on the reward and punishment mechanism of secondary membership update, rewards are given to core area data, outliers are suppressed, and the identification of true abnormal monitoring is further strengthened; thereby significantly improving the accuracy of fire extinguishing monitoring; in view of the fact that the general aerosol fire extinguishing monitoring system has improper hyperparameter settings, the optimization process is difficult to take into account both rapid response and optimization accuracy, which leads to poor fire extinguishing monitoring effect, this scheme is based on an exploratory global update mechanism and an exploitative local update mechanism, comprehensively balancing global and local searches, meeting the dual requirements of rapid response and optimization accuracy; thereby improving the fire extinguishing monitoring effect.

[0004] The technical solution adopted by the present invention is as follows: the present invention provides a digital-based aerosol fire extinguishing monitoring system, comprising a data acquisition module, a distance metric definition module, a local factor design module, a clustering processing module, a parameter optimization module and an aerosol fire extinguishing monitoring module;

[0005] The data acquisition module collects historical aerosol fire extinguishing monitoring data and monitoring status;

[0006] The distance metric definition module introduces a positive definite matrix to define the distance metric;

[0007] The local factor design module introduces time weight to design local factors;

[0008] The cluster processing module iteratively updates the membership, cluster center and positive definite matrix based on the defined objective function to achieve clustering of monitoring data;

[0009] The parameter optimization module optimizes the hyperparameters of the clustering processing model;

[0010] The aerosol fire extinguishing monitoring module performs aerosol fire extinguishing monitoring on the real-time collected data based on the clustering result.

[0011] Furthermore, the data acquisition module uses the monitoring status as a data label and selects and uses it only as a cluster label; performs feature engineering processing on the collected data to obtain a fire extinguishing monitoring data set.

[0012] Furthermore, the distance metric definition module defines a distance metric value, which is expressed as: ;in, is the i-th data vector; is the kth cluster center vector; is the positive definite matrix used in the kth region; T is the matrix transpose; is a custom distance metric.

[0013] Furthermore, the local factor design module utilizes neighborhood information by designing local factors; introducing additional time weight factors ; The local factor is expressed as: ; ;in, is a local factor; g and i are both data indices; is the Euclidean distance between the i-th data and the g-th data; is the membership degree of the g-th data to the k-th cluster; is the updated membership degree; is the g-th data vector; is the neighbor set of the i-th data; and is the sampling time of the data point; is the time scale parameter.

[0014] Furthermore, the cluster processing module clusters the fire extinguishing monitoring data set, specifically including the following contents:

[0015] The objective function definition unit is expressed as: ; Where J is the objective function; c is the number of clusters; n is the number of data points; m is the fuzzy index; is the balance parameter; initialize the cluster center and membership; is the membership degree of the i-th data to the k-th cluster; It is updated ;

[0016] Iterate the optimization unit; update the membership, and use the weighted distance between the current data and the cluster center and the local factor to update the membership; expressed as: ; Update the cluster center by weighted average; expressed as: ;

[0017] Positive definite matrix update unit; construct covariance matrix, covariance matrix It is expressed as: ; Positive definite matrix Updated to: ;in; is the silhouette coefficient of the kth cluster; is the proportionality constant; M is the dimension of the data vector; det(·) is the determinant;

[0018] The secondary update mechanism sets the unit; when the monitoring data is obviously inclined to the core area, the reward mechanism is adopted; the outlier data is suppressed; and the secondary update of the membership degree is realized; after dividing each cluster area, when , it is determined to fall in the core area, ; Otherwise, it is judged to fall in the outlier area. ;in, is the membership of the i-th data point to the k-th cluster; is the membership degree after the second update; The inhibition rate is determined by local information; the inhibition rate is determined by local information, which is expressed as: ; ;in, is the local membership; Is whether the jth data point belongs to the kth cluster in the last iteration. If so, then ,otherwise ; is the Euclidean distance between the i-th data point and the j-th data point; and are the weighted distance measure and weighted local factor value between the data point and the cluster center in the kth cluster respectively; and are the weighted distance measure and weighted local factor value in the neighborhood of the i-th data point, respectively;

[0019] Iteration judgment unit; if the objective function converges, the iteration ends and the clustering result is obtained; if the maximum number of iterations is reached, parameter optimization is performed based on the parameter optimization module; otherwise, the cluster center continues to be updated and data points are allocated.

[0020] Furthermore, the parameter optimization module optimizes the hyperparameters in the clustering process, specifically including the following contents:

[0021] Initialize the unit; establish the optimization space based on the hyperparameters in the clustering process and initialize the optimization population;

[0022] Fitness function definition unit; fitness function It is expressed as: ;in, and are different cluster centers, p and q are cluster center indexes;

[0023] Exploratory global update unit; perform large step search in the global range, expressed as: ; ;in, is the optimized individual position after the initial update; is the optimized individual position before updating; W is the dynamic weight; RB is the search range; S is the decay rate; t is the current optimization number; is the maximum number of optimizations; RS is the minimum search range; is a random number between 0 and 1; is the initial movement threshold; yes Flight Operator;

[0024] Utilize the local update unit; perform a refined search based on the current optimal solution, expressed as:

[0025] ;in, It is the position after the second update; is the behavior weight; rand is a random number between 0 and 1; is a random number between 0 and 1, independent of r1; is the secondary moving threshold; bf is the profit factor; is the location of the optimal solution;

[0026] Optimization judgment unit; setting a fitness threshold. If the maximum number of optimization times is reached or the fitness value of the optimal solution is higher than the fitness threshold, the optimization ends, and the clustering parameters are set based on the position of the optimal solution to obtain the clustering results.

[0027] Furthermore, the aerosol fire extinguishing monitoring module is based on the clustering result, and uses the label of the cluster center as the cluster label; the aerosol fire extinguishing monitoring data is collected in real time, and is distributed based on the clustering processing module, and the cluster label corresponding to the aerosol fire extinguishing monitoring data is used as the monitoring result.

[0028] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0029] (1) In view of the fact that the parameters of general aerosol fire extinguishing monitoring systems have different correlations, it is difficult to compare them fairly, which is prone to false detection or missed detection. There is a lack of coordinated use of information between adjacent sensors and no effective processing of sudden instantaneous interference, which leads to poor accuracy of fire extinguishing monitoring. This scheme introduces a positive definite matrix to define the distance metric, taking into account the correlation of each sensor; introduces Euclidean distance decay and time weight to design local factors, effectively suppressing single-point noise and instantaneous anomalies in aerosol fire extinguishing monitoring; based on the reward and punishment mechanism of secondary membership update, rewards are given to core area data, outliers are suppressed, and the identification of truly abnormal monitoring is further strengthened; thereby significantly improving the accuracy of fire extinguishing monitoring.

[0030] (2) In view of the problem that the general aerosol fire extinguishing monitoring system has improper hyperparameter settings, the optimization process is difficult to take into account both rapid response and optimization accuracy, which leads to poor fire extinguishing monitoring effect. This scheme is based on an exploratory global update mechanism and an exploitative local update mechanism, which comprehensively balances global and local searches to meet the dual requirements of rapid response and optimization accuracy, thereby improving the fire extinguishing monitoring effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of a digital aerosol fire extinguishing monitoring system provided by the present invention;

[0032] Figure 2 Schematic diagram of the clustering processing module.

[0033] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0035] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0036] Example 1, see Figure 1 , the present invention provides a digital-based aerosol fire extinguishing monitoring system, including a data acquisition module, a distance metric definition module, a local factor design module, a clustering processing module, a parameter optimization module and an aerosol fire extinguishing monitoring module;

[0037] The data acquisition module collects historical aerosol fire extinguishing monitoring data and monitoring status;

[0038] The distance metric definition module introduces a positive definite matrix to define the distance metric;

[0039] The local factor design module introduces time weight to design local factors;

[0040] The cluster processing module iteratively updates the membership, cluster center and positive definite matrix based on the defined objective function to achieve clustering of monitoring data;

[0041] The parameter optimization module optimizes the hyperparameters of the clustering processing model;

[0042] The aerosol fire extinguishing monitoring module performs aerosol fire extinguishing monitoring on the real-time collected data based on the clustering result.

[0043] Example 2, see Figure 1 This embodiment is based on the above embodiment. The data acquisition module uses the monitoring status as a data label and selects it only as a cluster label for use; feature engineering is performed on the collected data to obtain a fire extinguishing monitoring data set; the historical aerosol fire extinguishing monitoring data includes basic environmental parameters, aerosol-related data, optical parameter data, sampling time and auxiliary data; the basic environmental parameters include temperature, humidity and atmospheric pressure; the aerosol-related data include aerosol concentration and particle diameter distribution; the optical parameter data includes the density, distribution and thermal radiation of smoke; the auxiliary data includes wind speed, wind direction and other pollutant concentrations; the monitoring status includes normal, slightly abnormal, moderately abnormal and severely abnormal.

[0044] Example 3, see Figure 1 This embodiment is based on the above embodiment. The distance metric definition module is used in aerosol fire extinguishing monitoring. The monitoring data of different sensors have cross-influence. In order to effectively reflect the real difference between the data, the distance metric value is defined, which is expressed as: ;in, is the i-th data vector; is the kth cluster center vector; is the positive definite matrix used in the kth region; T is the matrix transpose; is a custom distance metric; using the positive definite matrix Incorporating prior information into the covariance structure can more accurately characterize the correlation and scale differences among the monitoring data, and help to accurately detect abnormal aerosol distribution.

[0045] Example 4, see Figure 1 ,This embodiment is based on the above embodiment. The local factor design module is in the monitoring network. In the regional sensor network, the neighboring monitoring data usually has a high correlation; by designing local factors, the neighborhood information is used to weaken the influence of individual noise; an additional time weight factor is introduced , reducing the local disturbance caused by transient anomalies; the local factor is expressed as: ; ;in, is a local factor; g and i are both data indices; is the Euclidean distance between the i-th data and the g-th data; is the membership degree of the g-th data to the k-th cluster; is the updated membership degree; is the g-th data vector; is the neighbor set of the i-th data; and is the sampling time of the data point; is the time scale parameter.

[0046] Example 5, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. The clustering processing module clusters the fire extinguishing monitoring data set, which specifically includes the following contents:

[0047] The objective function definition unit is expressed as: ; Where J is the objective function; c is the number of clusters; n is the number of data points; m is the fuzzy index; is the balance parameter; initialize the cluster center and membership; is the membership degree of the i-th data to the k-th cluster; It is updated ;

[0048] Iterative optimization unit; for each cluster area, the monitoring data is grouped and anomaly detected through iterative update; the membership is updated, and the weighted distance between the current data and the cluster center and the local factor are used to update the monitoring data membership, reflecting the degree of dependence of the data point on each cluster; it is expressed as: ; Update the cluster center by weighted average, combining the influence of a single data point and its neighborhood data, so that the cluster center is more in line with the overall characteristics of the actual area; expressed as: ;

[0049] Positive definite matrix update unit; construct a covariance matrix to capture the distribution characteristics of each monitoring data, and then use its inverse matrix to construct a positive definite matrix; covariance matrix It is expressed as: ; Positive definite matrix Updated to: ;in; is the silhouette coefficient of the kth cluster; is the proportionality constant; M is the dimension of the data vector; det(·) is the determinant;

[0050] Secondary update mechanism setting unit; Aerosol fire extinguishing monitoring often has external environmental interference and noise data, and abnormal data can be effectively weakened by suppressing competitive learning; When the monitoring data obviously tends to the core area of ​​the fire, a reward mechanism is adopted; Conversely, suppression is adopted for outlier data; Then, the secondary update of membership is realized; After dividing each cluster area, different update strategies are adopted according to whether the sample falls in the core area or the outlier area. , it is determined to fall in the core area, ; otherwise, it is judged to fall in the outlier area. ;in, is the membership of the i-th data point to the k-th cluster; is the membership degree after the second update; The inhibition rate is determined by local information; the inhibition rate is determined by local information, which is expressed as: ; ;in, is the local membership; Is whether the jth data point belongs to the kth cluster in the last iteration. If so, then ,otherwise ; is the Euclidean distance between the i-th data point and the j-th data point; and are the weighted distance measure and weighted local factor value between the data point and the cluster center in the kth cluster respectively; and are the weighted distance measure and weighted local factor value in the neighborhood of the i-th data point, respectively;

[0051] Iteration judgment unit; if the objective function converges, the iteration ends and the clustering result is obtained; if the maximum number of iterations is reached, parameter optimization is performed based on the parameter optimization module; otherwise, the cluster center continues to be updated and data points are allocated.

[0052] By performing the above operations, the parameters of the general aerosol fire extinguishing monitoring system with different correlations are difficult to compare fairly, which is prone to false detection or missed detection, lacks the coordinated use of information between adjacent sensors, and does not effectively handle sudden instantaneous interference, which leads to the problem of poor accuracy of fire extinguishing monitoring. This scheme introduces a positive definite matrix to define the distance metric, taking into account the correlation of each sensor; introduces Euclidean distance decay and time weight to design local factors, effectively suppressing single-point noise and instantaneous anomalies in aerosol fire extinguishing monitoring; based on the reward and punishment mechanism of secondary membership update, rewards are given to core area data, outliers are suppressed, and the identification of truly abnormal monitoring is further strengthened; thereby significantly improving the accuracy of fire extinguishing monitoring.

[0053] Example 6, see Figure 1 This embodiment is based on the above embodiment. The parameter optimization module optimizes the hyperparameters in the clustering process, which specifically includes the following contents:

[0054] Initialize the unit; establish the optimization space based on the hyperparameters in the clustering process and initialize the optimization population;

[0055] Fitness function definition unit; fitness function It is expressed as: ;in, and are different cluster centers, p and q are cluster center indexes;

[0056] Exploratory global update unit; perform large step search in the global range, expressed as: ; ;in, is the optimized individual position after the initial update; is the optimized individual position before updating; W is the dynamic weight; RB is the search range; S is the decay rate; t is the current optimization number; is the maximum number of optimizations; RS is the minimum search range; is a random number between 0 and 1; is the initial movement threshold; yes Flight Operator;

[0057] Utilize the local update unit; perform a refined search based on the current optimal solution, expressed as:

[0058] ;in, It is the position after the second update; is the behavior weight; rand is a random number between 0 and 1; is a random number between 0 and 1, independent of r1; is the secondary moving threshold; bf is the profit factor; is the location of the optimal solution;

[0059] Optimization judgment unit; setting a fitness threshold. If the maximum number of optimization times is reached or the fitness value of the optimal solution is higher than the fitness threshold, the optimization ends, and the clustering parameters are set based on the position of the optimal solution to obtain the clustering results.

[0060] By performing the above operations, the general aerosol fire extinguishing monitoring system has improper hyperparameter settings, and the optimization process is difficult to take into account both rapid response and optimization accuracy, which leads to poor fire extinguishing monitoring effects. This scheme is based on an exploratory global update mechanism and an exploitative local update mechanism, which comprehensively balances global and local searches to meet the dual needs of rapid response and optimization accuracy, thereby improving the fire extinguishing monitoring effect.

[0061] Embodiment 7, see Figure 1 This embodiment is based on the above embodiment. The aerosol fire extinguishing monitoring module is based on the clustering result, and the label of the cluster center is used as the cluster label; the aerosol fire extinguishing monitoring data is collected in real time, and is distributed based on the clustering processing module, and the cluster label corresponding to the aerosol fire extinguishing monitoring data is used as the monitoring result; if the monitoring result is moderately abnormal, the sampling frequency is increased; if it is a serious abnormality, an early warning process is performed.

[0062] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0063] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0064] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A digital aerosol fire extinguishing monitoring system, characterized by: The system includes a data acquisition module, a distance metric definition module, a local factor design module, a cluster processing module, a parameter optimization module and an aerosol fire extinguishing monitoring module; The data acquisition module collects historical aerosol fire extinguishing monitoring data and monitoring status; The distance metric definition module introduces a positive definite matrix to define the distance metric; The local factor design module introduces time weight to design local factors; The cluster processing module iteratively updates the membership, cluster center and positive definite matrix based on the defined objective function to achieve clustering of monitoring data; The parameter optimization module optimizes the hyperparameters of the clustering processing model; The aerosol fire extinguishing monitoring module performs aerosol fire extinguishing monitoring on the real-time collected data based on the clustering result.

2. A digital aerosol fire extinguishing monitoring system according to claim 1, characterized in that: The distance metric definition module defines the distance metric value, which is expressed as: ;in, is the i-th data vector; is the kth cluster center vector; is the positive definite matrix used in the kth region; T is the matrix transpose; is a custom distance metric.

3. A digital aerosol fire extinguishing monitoring system according to claim 2, characterized in that: The local factor design module utilizes neighborhood information by designing local factors; introducing additional time weight factors ; The local factor is expressed as: ; ;in, is a local factor; g and i are both data indices; is the Euclidean distance between the i-th data and the g-th data; is the membership degree of the g-th data to the k-th cluster; is the updated membership degree; is the g-th data vector; is the neighbor set of the i-th data; and is the sampling time of the data point; is the time scale parameter.

4. A digital aerosol fire extinguishing monitoring system according to claim 3, characterized in that: The clustering processing module clusters the fire extinguishing monitoring data set, which specifically includes the following contents: The objective function definition unit is expressed as: ; Where J is the objective function; c is the number of clusters; n is the number of data points; m is the fuzzy index; is the balance parameter; initialize the cluster center and membership; is the membership degree of the i-th data to the k-th cluster; It is updated ; Iterate the optimization unit; update the membership, and use the weighted distance between the current data and the cluster center and the local factor to update the membership; expressed as: ; Update the cluster center by weighted average; expressed as: ; Positive definite matrix update unit; construct covariance matrix, covariance matrix It is expressed as: ; Positive definite matrix Updated to: ;in; is the silhouette coefficient of the kth cluster; is the proportionality constant; M is the dimension of the data vector; det(·) is the determinant; Secondary update mechanism setting unit; Iteration judgment unit; if the objective function converges, the iteration ends and the clustering result is obtained; if the maximum number of iterations is reached, parameter optimization is performed based on the parameter optimization module; otherwise, the cluster center continues to be updated and data points are allocated.

5. A digital aerosol fire extinguishing monitoring system according to claim 4, characterized in that: The secondary update mechanism setting unit adopts a reward mechanism when the monitoring data obviously tends to the core area; suppresses the outlier data; and then realizes the secondary update of the membership degree; after dividing each cluster area, when , it is determined to fall in the core area, ; Otherwise, it is judged to fall in the outlier area. ;in, is the membership of the i-th data point to the k-th cluster; is the membership degree after the second update; The inhibition rate is determined by local information; the inhibition rate is determined by local information, which is expressed as: ; ;in, is the local membership; Is whether the jth data point belongs to the kth cluster in the last iteration. If so, then ,otherwise ; is the Euclidean distance between the i-th data point and the j-th data point; and are the weighted distance measure and weighted local factor value between the data point and the cluster center in the kth cluster respectively; and are the weighted distance measure and weighted local factor value in the neighborhood of the i-th data point, respectively.

6. A digital aerosol fire extinguishing monitoring system according to claim 5, characterized in that: The parameter optimization module optimizes the hyperparameters in the clustering process, specifically including the following contents: Initialize the unit; establish the optimization space based on the hyperparameters in the clustering process and initialize the optimization population; Fitness function definition unit; fitness function It is expressed as: ;in, and are different cluster centers, p and q are cluster center indexes; Exploratory global update unit; perform large step search in the global range, expressed as: ; ;in, is the optimized individual position after the initial update; is the optimized individual position before updating; W is the dynamic weight; RB is the search range; S is the decay rate; t is the current optimization number; is the maximum number of optimizations; RS is the minimum search range; is a random number between 0 and 1; is the initial movement threshold; yes Flight Operator; Utilize the local update unit; perform a refined search based on the current optimal solution, expressed as: ;in, It is the position after the second update; is the behavior weight; rand is a random number between 0 and 1; is a random number between 0 and 1, independent of r1; is the secondary moving threshold; bf is the profit factor; is the location of the optimal solution; Optimization judgment unit; setting a fitness threshold. If the maximum number of optimization times is reached or the fitness value of the optimal solution is higher than the fitness threshold, the optimization ends, and the clustering parameters are set based on the position of the optimal solution to obtain the clustering results.

7. A digital aerosol fire extinguishing monitoring system according to claim 6, characterized in that: The data acquisition module uses the monitoring status as a data label and selects and uses it only as a cluster label; performs feature engineering processing on the collected data to obtain a fire extinguishing monitoring data set.

8. The digital aerosol fire extinguishing monitoring system according to claim 7 is characterized in that: The aerosol fire extinguishing monitoring module is based on the clustering results, and the label of the cluster center is used as the cluster label; The aerosol fire extinguishing monitoring data is collected in real time, allocated based on the clustering processing module, and the cluster labels corresponding to the aerosol fire extinguishing monitoring data are used as monitoring results.

Images