Intelligent fire service management system

Abstract

The application relates to the technical field of fire control management, and discloses a smart fire control service management system, which comprises a data acquisition unit used for acquiring three basic parameters of environment data, working condition data and battery data of a fire control object in an office building; the system acquires environment data, working condition data and battery data of a fire extinguisher through the data acquisition unit; a fusion unit generates a dynamic composite abnormal threshold value; and an adjustment unit adjusts the threshold value, a battery health score and data deviation to execute a three-level sampling frequency adjustment mechanism, which means that when the state of the fire extinguisher is normal and the risk is low, the sampling frequency can be reduced to reduce battery energy consumption; when the risk increases or the battery health decreases, the sampling frequency is increased to ensure monitoring effect; the whole system realizes accurate management and regulation of the battery according to the actual working condition of the fire extinguisher, avoids waste of energy, prolongs the service life of the battery, reduces the cost of frequent replacement of the battery, and enhances the sustainability of smart fire control management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fire management, and particularly relates to a smart fire service management system. BACKGROUND

[0002] At present, in office buildings, multiple fire extinguishers are usually collected by relying on a platform to enable property personnel to remotely view the real-time state of the fire extinguishers, and in addition, personnel are regularly inspected, so that once the data of the fire extinguishers is abnormal, a real-time early warning can be performed, but in actual use, since the temperature, pressure sensor and RFID tag all need to be powered by a battery, in order to ensure real-time management.

[0003] At present, a continuous monitoring mode with a fixed sampling frequency is generally adopted, and the battery energy consumption gradually decreases with the monitoring time, which leads to the need to regularly replace the battery, and in the overall fire management, the battery cannot be effectively managed and controlled according to the actual working conditions of the fire equipment, so that the system has the problem of insufficient energy utilization, and the management ability of smart fire is reduced. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a smart fire service management system, which solves the above problems.

[0005] The above technical purpose of the present application is realized by the following technical scheme:

[0006] A smart fire service management system, comprising:

[0007] A data acquisition unit configured to acquire three basic parameters of environment data, working condition data and battery data of a fire object in an office building, wherein the fire object is a fire extinguisher;

[0008] A fusion unit configured to fuse the environment data, the working condition data and the battery data to generate a dynamic composite abnormal threshold of battery state perception;

[0009] An adjustment unit configured to compare the working condition data, the environment data and the battery data with the dynamic composite abnormal threshold to perform a three-level sampling frequency adjustment mechanism based on battery health;

[0010] A management unit configured to divide the office building into fire areas managed by master and slave nodes, and to perform a battery priority hierarchical wake-up strategy in combination with the distribution characteristics of the fire areas and the dynamic composite abnormal threshold;

[0011] A balancing unit configured to construct a three-dimensional evaluation matrix of battery remaining life, monitoring efficiency and energy consumption cost based on the battery data and the three-level sampling frequency adjustment mechanism, and to generate a fire management strategy based on the three-dimensional evaluation matrix.

[0012] Further, the environmental data, the working condition data and the battery data are fused to generate a dynamic composite abnormal threshold with battery state awareness, including:

[0013] The normalized environmental data, the working condition data and the battery data are fused and weighted to obtain fused data;

[0014] The fused data is analyzed to generate a dynamic composite abnormal threshold with battery state awareness, specifically including:

[0015] The average value of the fused data in the historical period is calculated to obtain a historical average value;

[0016] The standard deviation of the fused data in the historical period is calculated to obtain a historical standard deviation;

[0017] The product of the historical average value and the historical standard deviation is scaled, and the scaling ratio is controlled by a dynamic adjustment coefficient. Finally, the scaled result is superimposed on the historical average value to form a dynamic composite abnormal threshold;

[0018] The dynamic adjustment coefficient is composed of three parts, which respectively reflect the dynamic influence of the battery health state, the environmental fluctuation characteristics and the working condition stability on the threshold.

[0019] Further, the working condition data, the environmental data and the battery data are compared with the dynamic composite abnormal threshold to execute a three-level sampling frequency adjustment mechanism based on the battery health degree, including:

[0020] The battery data is calculated to obtain a battery health degree score;

[0021] The data deviation of the working condition data, the environmental data and the battery data from the dynamic composite abnormal threshold is calculated, specifically as follows:

[0022] The absolute difference between the working condition parameter and the dynamic composite abnormal threshold is calculated, and then divided by the dynamic composite abnormal threshold to obtain the relative deviation of the working condition parameter;

[0023] The absolute difference between the environmental parameter and the dynamic composite abnormal threshold is calculated, and then divided by the dynamic composite abnormal threshold to obtain the relative deviation of the environmental parameter;

[0024] The absolute difference between the battery parameter and the dynamic composite abnormal threshold is calculated, and then divided by the dynamic composite abnormal threshold to obtain the relative deviation of the battery parameter;

[0025] The weight of the relative deviation of the working condition parameter is in the range of 0.3-0.4, the weight of the relative deviation of the environmental parameter is in the range of 0.2-0.3, and the weight of the relative deviation of the battery parameter is in the range of 0.3-0.5. The sum of the three weights is 1;

[0026] The data deviation degree is obtained by adding the relative deviation degrees of the working condition parameters, the environmental parameters and the battery parameters according to respective weights.

[0027] According to the battery health degree score and the data deviation degree, the sampling frequency is divided into three levels, namely a first-level sampling frequency, a second-level sampling frequency and a third-level sampling frequency.

[0028] Further, the office building is divided into fire-fighting areas managed by master-slave nodes, including:

[0029] The office building is divided into a plurality of fire-fighting areas according to floors, and each floor is a fire-fighting area;

[0030] Each fire-fighting area contains all fire extinguishers on the floor, and each fire-fighting area is provided with one master node and a plurality of slave nodes under the master node;

[0031] The master node is used for managing a plurality of slave nodes on the floor;

[0032] The slave node is associated with a plurality of fire extinguishers, and collects environmental data, working condition data and battery data of the fire extinguishers in the area, and transmits the three basic parameters to the master node.

[0033] Further, in combination with the distribution characteristics of the fire-fighting area and the dynamic composite abnormal threshold, a battery priority classification wake-up strategy is executed, including:

[0034] According to the fire-fighting area divided according to the floor, a distribution characteristic parameter of each fire-fighting area is extracted, and the distribution characteristic parameter is composed of a fire extinguisher deployment density and a master-slave node distance;

[0035] The fire extinguisher deployment density is obtained by dividing the number of fire extinguishers in each floor fire-fighting area by the area of the floor fire-fighting area;

[0036] The master-slave node distance is obtained by calculating the straight-line distance from each fire extinguisher to the master node to which the fire extinguisher belongs using the Euclidean distance formula;

[0037] The dynamic composite abnormal threshold is associated with the area, and the regional average dynamic threshold is calculated by the master node collecting the dynamic composite abnormal thresholds reported by all slave nodes on the floor, including:

[0038] The dynamic composite abnormal thresholds reported by all slave nodes on the floor are collected by the master node, and the quartile range method is used to identify and eliminate outlier dynamic composite abnormal thresholds, and the effective dynamic composite abnormal thresholds are spatially weighted averaged according to the fire extinguisher deployment density and the distance weight of the area associated with each slave node, to finally generate a regional average dynamic threshold reflecting the overall state of the fire-fighting system on the floor.

[0039] Further, the battery priority hierarchical awakening strategy is executed in combination with the fire-fighting area distribution characteristics and the dynamic composite abnormal threshold, and further includes:

[0040] The area average dynamic threshold is combined with the distribution characteristic parameter to generate an area comprehensive risk score, specifically including: normalizing the fire extinguisher deployment density and the master-slave node distance, then establishing a multi-parameter coupling model, taking the area average dynamic threshold as the core risk input item, the deployment density as the reverse adjustment factor, and the master-slave node distance as the efficiency compensation item, and then determining the weight of each parameter by using the analytic hierarchy process, and performing nonlinear coupling of the area average dynamic threshold and the distribution characteristic parameter by using a weighted fusion algorithm to generate a quantitative risk score of 0-100 points;

[0041] When the area comprehensive risk score is between 0 and 40, the fire-fighting area is a low-risk area.

[0042] When the area comprehensive risk score is between 41 and 70, the fire-fighting area is a medium-risk area.

[0043] When the area comprehensive risk score is between 71 and 100, the fire-fighting area is a high-risk area.

[0044] The battery priority hierarchical awakening strategy is executed based on the area comprehensive risk score.

[0045] Further, the battery priority hierarchical awakening strategy is executed based on the area comprehensive risk score, including:

[0046] The area comprehensive risk score and the battery health score are analyzed to generate a wakeup priority index.

[0047] The battery priority hierarchical awakening strategy is executed through the wakeup priority index and the area comprehensive risk score, specifically including:

[0048] The battery priority hierarchical awakening strategy includes a first-level awakening, a second-level awakening, and a third-level awakening.

[0049] Further, a battery remaining life-monitoring efficiency-energy consumption cost three-dimensional evaluation matrix is constructed according to the battery data and the third-level sampling frequency adjustment mechanism:

[0050] Based on the battery data and the third-level sampling frequency adjustment mechanism, normalized battery remaining life indicators, monitoring efficiency indicators, and energy consumption cost indicators are obtained, and a battery remaining life-monitoring efficiency-energy consumption cost three-dimensional evaluation matrix is constructed based on the three indicators.

[0051] The monitoring efficiency and the data deviation are dynamically evaluated to generate a joint evaluation value of each node.

[0052] According to the joint evaluation value of each node in the fire-fighting area, a monitoring priority of the fire-fighting area node is generated, specifically including:

[0053] When the joint evaluation value is greater than or equal to 0.85, it is determined as a high-priority node, and real-time monitoring is started; when 0.5 is less than the joint evaluation value and is less than 0.85, it is determined as a medium-priority node, and normal monitoring period is performed; when the joint evaluation value is less than 0.5, it is determined as a low-priority node, and enters a standby monitoring mode;

[0054] According to the risk level of the fire-fighting area, the weight of the three-dimensional evaluation matrix is dynamically adjusted.

[0055] Further, according to the risk level of the fire-fighting area, the weight of the three-dimensional evaluation matrix is dynamically adjusted, including:

[0056] When the fire-fighting area is a high-risk area, the monitoring efficiency weight is increased, and the energy consumption cost weight is reduced;

[0057] When the fire-fighting area is a medium-risk area, the default weight is maintained;

[0058] When the fire-fighting area is a low-risk area, the energy consumption cost weight is increased, and the monitoring efficiency weight is reduced.

[0059] Further, based on the three-dimensional evaluation matrix, a fire management strategy is generated, including:

[0060] The three-dimensional evaluation matrix is analyzed to obtain a comprehensive score of the fire-fighting area node;

[0061] Based on the comprehensive score, a fire management strategy is generated, and the fire management strategy includes a battery health management strategy and a battery dynamic power consumption regulation strategy;

[0062] The battery health management strategy is specifically as follows:

[0063] When the node is a high-priority node and the comprehensive score is greater than or equal to 0.85, the sampling frequency is increased to 1 minute / time, and the battery is marked for replacement within 30 days;

[0064] When the node is a medium-priority node and 0.5 is less than the comprehensive score and is less than 0.85, the sampling is maintained at 10 minutes / time;

[0065] When the node is a low-priority node and the comprehensive score is less than 0.5, the frequency is reduced to 6 hours / time, and only the battery SOC basic monitoring is retained;

[0066] The battery dynamic power consumption regulation strategy is specifically as follows:

[0067] For a high-risk fire-fighting area, the master node is always active, and the slave node is awakened once every 30 minutes;

[0068] For the medium-risk fire-fighting area, the master node works intermittently (wakes up once every 10 minutes), and the slave node dynamically adjusts the sampling according to the battery health score;

[0069] For the low-risk fire-fighting area, the master node is deeply dormant (activated twice a day), and the slave node only wakes up in an emergency when the temperature in the fire-fighting area is greater than 60 DEG C.

[0070] In summary, the present application mainly has the following beneficial effects:

[0071] Through multi-dimensional data fusion and dynamic threshold adjustment mechanism, the precise scheduling of battery energy is realized, and the traditional fixed sampling mode cannot perceive the environment, working condition and battery state difference, resulting in a large amount of energy waste, the present application innovatively fuses and weights the environmental temperature and humidity, fire extinguisher pressure parameters and battery health, generates a dynamic composite abnormal threshold, and combines a three-level sampling frequency adjustment mechanism, so that the system can dynamically adjust the monitoring frequency according to the battery health score and the deviation degree of real-time data, when the data deviation degree is low, the sampling frequency is automatically reduced to 6 hours / time, and in the high-risk scene, it is increased to 1 minute / time, effectively balancing the monitoring accuracy and energy cost, in addition, by constructing a three-dimensional evaluation matrix of battery remaining life-monitoring efficiency-energy consumption cost, the system can dynamically adjust the weight distribution of different risk areas, for example, in the high-risk area, the monitoring efficiency is given priority to, and in the low-risk area, the energy consumption is optimized, so as to realize the gradient management of the batteries of the fire-fighting equipment of the whole building, and the labor and material cost of replacing the batteries of the property is significantly reduced.

[0072] Through the master-slave node architecture and hierarchical wake-up strategy, the problem of resource allocation in traditional fire-fighting management is solved, based on the fire-fighting area divided by floors, combined with the spatial characteristic parameters such as the deployment density of fire extinguishers and the distance between master and slave nodes, the system generates a comprehensive risk score of the area (0-100 points), and executes a priority hierarchical wake-up strategy accordingly, in the high-risk area (71-100 points), the master node is active all the time, and the slave node wakes up once every 30 minutes, ensuring real-time response to abnormal events, in the medium-risk area (41-70 points), the master node works intermittently, and the slave node dynamically adjusts the sampling period according to the battery health, and in the low-risk area (0-40 points), it is deeply dormant, only retaining the basic monitoring function, through differentiated management, the overall system energy consumption is reduced. At the same time, the response speed of the key area is improved.

[0073] By constructing a three-dimensional evaluation matrix, the mode change from passive replacement to active maintenance is realized, the three-dimensional evaluation matrix is used for quantitative analysis on the battery residual life, monitoring efficiency and energy consumption cost, the system can automatically generate a node comprehensive score (0-1 score), and a hierarchical management strategy is executed according to the score: the high-priority node (≥0.85 score) is marked for battery replacement within 30 days, the medium-priority node is maintained regularly, and the low-priority node (<0.5 score) enters standby mode. This mechanism can avoid the risk of sudden power failure, and the dynamic power consumption regulation strategy concentrates the high-risk area from node energy consumption in the key monitoring period, combined with the emergency wake-up mechanism, the annual wake-up times of the low-risk area equipment are reduced on the premise of ensuring the safety bottom line, and the management effect of the intelligent fire service of the office building is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0074] Figure 1 is a block diagram of the intelligent fire service management system of the present application. DETAILED DESCRIPTION

[0075] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0076] REFERENCE Figure 1 An intelligent fire service management system, comprising:

[0077] A data acquisition unit is configured to acquire three basic parameters of environment data, working condition data and battery data of a fire object in an office building, wherein the fire object is a fire extinguisher.

[0078] A fusion unit is configured to fuse the environment data, the working condition data and the battery data to generate a dynamic composite abnormal threshold of battery state perception.

[0079] An adjustment unit is configured to compare the working condition data, the environment data and the battery data with the dynamic composite abnormal threshold to execute a three-level sampling frequency adjustment mechanism based on the battery health.

[0080] A management unit is configured to divide the office building into fire areas managed by master and slave nodes, and execute a battery priority hierarchical wake-up strategy in combination with the distribution characteristics of the fire areas and the dynamic composite abnormal threshold.

[0081] A balancing unit is configured to construct a three-dimensional evaluation matrix of battery residual life, monitoring efficiency and energy consumption cost based on the battery data and the three-level sampling frequency adjustment mechanism, and generate a fire management strategy based on the three-dimensional evaluation matrix.

[0082] Through the coordinated operation of multiple units, a three-dimensional fire-fighting equipment monitoring and management system is constructed. The data acquisition unit realizes full-dimensional real-time acquisition of the fire extinguisher environment, working condition and battery data, laying a data foundation for accurate monitoring. The fusion unit dynamically generates a composite abnormal threshold based on multi-source data, breaking through the limitations of traditional fixed threshold monitoring, intelligently adapting to changes in environmental conditions, and significantly improving the accuracy and timeliness of battery state perception. The adjustment unit constructs a three-level sampling frequency adjustment mechanism that can dynamically optimize data acquisition density according to battery health, ensuring monitoring efficiency while reducing redundant energy consumption, achieving intelligent balance between monitoring accuracy and energy efficiency. The management unit implements differentiated management based on regional distribution characteristics through master-slave node fire-fighting area division and priority hierarchical wake-up strategy, ensuring key monitoring of high-risk areas while reducing unnecessary energy consumption through wake-up strategy, improving overall system response efficiency. The balancing unit constructs a three-dimensional evaluation matrix of battery remaining life, monitoring efficiency and energy consumption cost, providing quantitative decision-making basis for fire management strategy generation, promoting the transformation of fire management from experience-driven to data-driven, and achieving organic integration of equipment life cycle health management, optimal allocation of monitoring resources and fine control of operating costs. Through deep synergy of data fusion, dynamic adjustment, intelligent management and multi-dimensional evaluation, the intelligent level of office building fire-fighting equipment monitoring is effectively improved, and intelligent fire-fighting service management of office buildings is realized.

[0083] In one case of the embodiment, the three basic parameters of environmental data, working condition data and battery data of the fire-fighting object in the office building are acquired, including:

[0084] The environmental data is: temperature, humidity, smoke concentration;

[0085] The working condition data is: pressure, position and temperature and humidity (representing only the temperature and humidity of the fire extinguisher);

[0086] The battery data is: battery SOC and battery health status.

[0087] In one case of the embodiment, the environmental data, working condition data and battery data are fused to generate a dynamic composite abnormal threshold for battery state perception, including:

[0088] The normalized environmental data, working condition data and battery data are fused and weighted to obtain fusion data, and the specific calculation formula is as follows:

[0089]

[0090] In the formula, F represents the fusion data, E represents the environmental data, E min and E max represent the minimum and maximum values of the environmental data respectively, R represents the working condition data, R min and R maxrespectively represent the minimum and maximum of the operating condition data, B represents the battery data, B min and B max respectively represent the minimum and maximum of the battery data, and α, β and γ respectively represent the weights of the corresponding environment data E, operating condition data R and battery data B, wherein the value ranges of α, β and γ are both between 0.3 and 0.4, and α+β+γ=1;

[0091] The fusion data is analyzed to generate a dynamic composite abnormal threshold of battery state awareness, and the specific calculation formula is as follows:

[0092] Y = μ + δσ·F;

[0093] In the formula, Y represents the dynamic composite abnormal threshold, μ represents the historical mean of the fusion data F (the historical mean can be obtained by adding all the fusion data in the past and dividing by the number of fusion data), σ represents the historical standard deviation of the fusion data F (the historical standard deviation can be obtained by calculating the difference between each fusion data and the historical mean, squaring the differences, adding them, dividing by the number of fusion data minus one, and then taking the square root), and δ represents a dynamic adjustment coefficient;

[0094] The dynamic adjustment coefficient δ is calculated, and the calculation formula is as follows:

[0095]

[0096] In the formula, δ0 represents an initial dynamic adjustment coefficient, k1 and k2 are respectively the influence coefficients of the battery health degree and the comprehensive fluctuation factor, which are both positive numbers, wherein the comprehensive fluctuation factor mainly refers to the fluctuation characteristics and stability characteristics of the environment data and the operating condition data, e represents a natural constant, HF represents the battery health degree score, and the value range is [0, 1], the closer HF is to 1, the closer the performance of the battery is to the brand-new state, and the closer HF is to 0, the more serious the aging of the battery is, and the worse the performance is, γ1 represents an exponential parameter of the influence of the battery health degree, V represents the change rate of the fusion data F, λ1 represents an adjustment parameter of the change rate V of the fusion data, ΔE represents the change amount of the environment data, represents the historical average of the environment data, ΔR represents the change amount of the operating condition data, represents the historical average of the operating condition data, and S represents the operating condition stability index, and λ2 represents an adjustment parameter of the operating condition stability;

[0097] By means of normalized fusion weighting, the data of the environment, the working condition and the battery are comprehensively considered, so that the actual running state of the battery under different working conditions and environments can be comprehensively reflected, the misjudgment caused by a single data factor can be avoided, the subsequent evaluation of the battery state is more accurate, the dynamic composite abnormal threshold is calculated based on the fusion data, the threshold can change with the data change in the battery running process, the dynamic characteristics of the battery state can be timely reflected, the sensitivity and detection effect of the abnormal state of the battery are effectively improved, potential battery problems can be found in time, the safe operation of the battery is ensured, the calculation of the dynamic adjustment coefficient comprehensively considers the influence of various factors on the battery, including the battery health, the fluctuation characteristics and stability of the environment data and the working condition data, the dynamic composite abnormal threshold can be more accurately adjusted, so that it is more suitable for the actual health status and performance of the battery under different conditions, the accuracy and reliability of the battery state perception are further improved, and a strong basis is provided for the maintenance and management of the battery.

[0098] In one case of the embodiment, the working condition data, the environment data and the battery data are compared with the dynamic composite abnormal threshold, a three-level sampling frequency adjustment mechanism based on the battery health is performed, including:

[0099] The battery data is calculated to obtain a battery health score, and the specific calculation formula is as follows:

[0100] HF=w SOC ·SOC+w HS ·HS;

[0101] In the formula, SOC represents the state of charge of the battery, the value range is [0, 1], HS represents the health state of the battery, the value range is [0, 1], w SOC and w HS are weights corresponding to SOC and HS respectively, wherein the value range of w SOC is 0.2-0.4, the value range of w HS is 0.6-0.8, and w SOC +w HS =1.

[0102] The data deviation of the working condition data, the environment data and the battery data from the dynamic composite abnormal threshold is calculated, and the specific calculation formula is as follows:

[0103]

[0104] In the formula, D represents the data deviation, represents the relative deviation of the working condition data from the dynamic composite abnormal threshold, represents the relative deviation of the environment data from the dynamic composite abnormal threshold, w represents the relative deviation degree of the battery data from the dynamic composite anomaly threshold R E B w and represent the weights corresponding to R w E w B w R w E w B = 1.

[0105] According to the battery health score and the data deviation degree, the sampling frequency is divided into three levels, as follows:

[0106] The battery health score threshold is set to HF th , and the data deviation degree threshold is set to D th .

[0107] The first level sampling frequency: when HF≥HF th and D≤D th , the sampling frequency is the lowest, and the sampling frequency is once every 30 minutes.

[0108] The second level sampling frequency: when HF<HF th and D≤D th or HF≥HF th and D>D th , the sampling frequency is moderate, and the sampling frequency is once every 10 minutes.

[0109] The third level sampling frequency: when HF<HF th and D>D th , the sampling frequency is the highest, and the sampling frequency is once every 1 minute.

[0110] Through the weighted calculation based on the state of charge and the state of health, combined with the differentiated weight allocation, the core influence of the battery health state is highlighted, and the dynamic characteristics of the real-time power level are also considered. The actual performance of the battery can be more comprehensively reflected, and the three-level sampling frequency system constructed on this basis can intelligently match the monitoring density according to the battery health: when the health is good, low-frequency sampling is adopted to effectively reduce the data acquisition power consumption and storage pressure; when the health decreases, the sampling frequency is automatically increased to ensure high-frequency monitoring at the early stage of battery performance degradation, providing data support for battery life prediction and preventive maintenance, and avoiding resource waste caused by excessive sampling or monitoring blind area caused by insufficient sampling.

[0111] ​​Through multi-dimensional deviation analysis of fusion conditions, environment and battery data, a dynamic abnormality identification mechanism is constructed. The weight setting of battery data highlights the dominant role of core monitoring indicators, while taking into account the synergistic effect of working conditions and environmental factors, so that the system can accurately capture abnormal fluctuations in external operating conditions and internal state parameters. The three-level adjustment strategy further enhances the adaptability of the monitoring mechanism: when the data deviation is low, maintain the basic sampling frequency to balance the monitoring efficiency and resource consumption; when a single dimension (health or deviation) is abnormal, start medium frequency to focus on local risk tracking; when double abnormalities are superimposed, trigger high-frequency sampling to ensure real-time capture of key data when battery performance declines or operating environment changes dramatically, providing high-density data support for battery safety warning and fault diagnosis, effectively improving the reliability and response speed of the battery management system.

[0112] In one case of the embodiment, the office building is divided into fire-fighting areas managed by master and slave nodes, including:

[0113] The office building is divided into multiple fire-fighting areas according to floors, with each floor being a fire-fighting area;

[0114] Each fire-fighting area contains all fire extinguishers on the floor, and each fire-fighting area is provided with 1 master node, and multiple slave nodes are provided under each master node;

[0115] The master node is deployed in areas such as machine rooms and power distribution rooms, and is used to manage multiple slave nodes on the floor;

[0116] The slave node is deployed in areas such as corridors and office areas, and is associated with multiple fire extinguishers, and collects fire extinguisher environmental data, working condition data and battery data in the area, and transmits the three basic parameters to the master node;

[0117] The office building is divided into fire-fighting areas managed by master and slave nodes according to floors, and the intelligent hierarchical architecture realizes the precision and efficiency of fire-fighting management. First, the independent fire-fighting area division based on floors, combined with the centralized control of master nodes (machine rooms / power distribution rooms) to slave nodes (corridors / office areas), effectively realizes the purpose of fire-fighting management, and the slave node collects real-time environmental data (temperature and humidity, smoke concentration), working condition data (pressure, validity period) and battery data (remaining power, abnormal state) of the fire extinguisher, and analyzes the data through the master node, constructing a dynamic monitoring network covering the whole floor, so that the management personnel can identify potential problems such as equipment aging and battery failure in advance, improve the ability of fire-fighting management, and reduce the system complexity through hierarchical management. The master node is responsible for strategy issuance and data integration, and the slave node focuses on local data collection, which not only ensures the stability of communication, but also reduces the influence range of single point failure, realizes the whole life cycle management of fire-fighting equipment, and achieves the fire safety management of high-rise buildings.

[0118] In one case of the embodiment, in combination with the fire-fighting area distribution characteristics and the dynamic composite abnormal threshold, a battery priority classification wake-up strategy is executed, including:

[0119] According to the fire-fighting area divided by the floor, the distribution characteristic parameters of each fire-fighting area are extracted, specifically including:

[0120] The distribution characteristic parameters are composed of the fire extinguisher deployment density and the master-slave node distance;

[0121] Wherein, the fire extinguisher deployment density can be obtained by dividing the number of fire extinguishers in each floor fire-fighting area by the area of the floor fire-fighting area;

[0122] The straight-line distance of each fire extinguisher to the master node to which it belongs is calculated using the Euclidean distance formula, and the master-slave node distance is obtained;

[0123] The dynamic composite abnormal threshold is associated by region, and the regional average dynamic threshold is calculated by the master node collecting the dynamic composite abnormal threshold reported by all slave nodes on the floor, specifically including: collecting the T value reported by all slave nodes on the floor through the master node, identifying and removing outlier T values using the interquartile range method, and performing spatial weighted average on the effective T values according to the fire extinguisher deployment density and distance weight of each slave node associated region, wherein the data weight of the fire extinguisher with higher deployment density and closer distance to the master node is higher, and finally the regional average dynamic threshold reflecting the overall state of the fire-fighting system on the floor is generated;

[0124] After obtaining all T values, enter the outlier identification and removal phase, and use the interquartile range method to ensure data reliability, the specific steps are as follows: first, arrange all collected T values in ascending order, then calculate the quartiles, wherein the first quartile is the value at the 25th position of the sorted data, the third quartile is the value at the 75th position, and the interquartile range is the difference between the third quartile and the first quartile. According to the interquartile range method, the criterion for identifying outliers is less than the first quartile minus 1.5 times the interquartile range, or greater than the third quartile plus 1.5 times the interquartile range. These outliers will be removed, and the remaining ones are the effective T values. This process can exclude abnormal data interference caused by equipment failure, data transmission anomaly, etc.;

[0125] According to the fire extinguisher deployment density and distance weight of each slave node associated region, the spatial weighted average of the effective T values is performed, and the specific process is as follows: multiply the effective T value of each slave node by the corresponding comprehensive weight, then add these products, and divide by the sum of all comprehensive weights to obtain the regional average dynamic threshold;

[0126] The quartile range method is used to identify and eliminate outliers T values, effectively excluding abnormal data interference caused by factors such as equipment failure and data transmission anomalies, ensuring that the T values used for calculation are reliable, laying a solid foundation for subsequent analysis. In terms of regional state reflection, the weight is determined by combining the fire extinguisher deployment density and the master-slave node distance, and the spatial weighted average of the effective T value is performed, so that the data of the fire extinguisher with higher deployment density and closer distance to the master node has higher weight, which can more accurately reflect the fire fighting state of the key area. The generated regional average dynamic threshold can truly reflect the overall state of the fire fighting system on the floor. In terms of resource utilization, based on the floor fire fighting area distribution characteristics and the dynamic composite abnormal threshold, the battery priority hierarchical wake-up strategy is executed, which can reasonably allocate battery energy and preferentially wake up key area equipment, thereby ensuring monitoring effect, prolonging device endurance, and improving system operation efficiency and stability.

[0127] In one case of the embodiment, the battery priority hierarchical wake-up strategy is executed in combination with the fire fighting area distribution characteristics and the dynamic composite abnormal threshold, and further includes:

[0128] The regional average dynamic threshold is combined with the distribution characteristic parameters to generate a regional comprehensive risk score, specifically including: normalizing the fire extinguisher deployment density and the master-slave node distance to eliminate dimensional differences, taking the regional average dynamic threshold as the core risk input item, the deployment density as the reverse adjustment factor, and the master-slave node distance as the efficiency compensation item, then using the analytic hierarchy process to determine the weight of each parameter, and using the weighted fusion algorithm to nonlinearly couple the regional average dynamic threshold and the distribution characteristic parameters to generate a quantitative risk score of 0-100 points;

[0129] The processing procedure of the normalized fire extinguisher deployment density is as follows: determining the maximum value of the fire extinguisher deployment density in all fire-fighting areas of all floors, taking the maximum value as a normalized reference value, the reference value represents the most dense area of the fire extinguisher deployment in the whole office building, for each fire-fighting area of each floor, calculating the actual fire extinguisher deployment density (i.e. the number of fire extinguishers on the floor divided by the floor area), and then comparing the actual value with the reference value to obtain a proportion value, the proportion value is the normalized fire extinguisher deployment density, and the value range of the proportion value is between 0 and 1, for example, an office building has three floors, each floor has an area of 1000 square meters, 20 fire extinguishers are deployed on the first floor, the deployment density is "20 / 1000 square meters = 0.02 / square meter", 25 fire extinguishers are deployed on the second floor, the deployment density is "25 / 1000 square meters = 0.025 / square meter", and 30 fire extinguishers are deployed on the third floor, the deployment density is "30 / 1000 square meters = 0.03 / square meter", at this time, the maximum deployment density of the third floor is 0.03 / square meter, and the maximum deployment density is taken as the reference value, the normalized deployment density of the first floor is "0.02 / 0.03 = 0.67", the normalized deployment density of the second floor is "0.025 / 0.03 = 0.83", and the normalized deployment density of the third floor is "0.03 / 0.03 = 1", through the normalization, the fire extinguisher deployment densities of the three floors are converted to the range of 0 to 1, the influence of the area difference of different floors is eliminated, and the fire extinguisher deployment densities can be compared on a unified scale.

[0130] The processing procedure of the normalized master-slave node distance is as follows: determining the maximum value of the distance from all fire extinguishers to the master node, taking the maximum value as a normalized reference value, the reference value represents the farthest distance between the fire extinguisher and the master node, for each fire extinguisher, calculating the actual distance from the fire extinguisher to the master node, and then comparing the actual value with the reference value to obtain a proportion value, for example, a floor has three fire extinguishers, the distances from the fire extinguishers to the master node are 10 meters, 15 meters and 20 meters respectively, taking the maximum distance 20 meters as the reference value, then the normalized distance of the first fire extinguisher is "10 meters / 20 meters = 0.5", the normalized distance of the second fire extinguisher is "15 meters / 20 meters = 0.75", and the normalized distance of the third fire extinguisher is "20 meters / 20 meters = 1", through the method, the distance from the fire extinguisher to the master node is converted to the range of 0 to 1, the influence of the layout difference of fire extinguishers in different floors is eliminated, and the master-slave node distance can be compared on a unified scale.

[0131] When the area comprehensive risk score is 0-40, the fire-fighting area is a low-risk area.

[0132] When the regional comprehensive risk score is 41-70 points, the fire-fighting area is a medium-risk area;

[0133] When the regional comprehensive risk score is 71-100 points, the fire-fighting area is a high-risk area;

[0134] The battery priority hierarchical awakening strategy is executed based on the regional comprehensive risk score;

[0135] By means of the maximum value benchmark normalization method, the dimensional influence such as area difference and layout difference is effectively eliminated, the basic data of different fire-fighting areas are horizontally comparable, for example, the fire extinguisher deployment density is converted into a proportional value in the interval of 0-1, the relative difference between areas is retained, and the influence of the area base on the evaluation result is avoided, the objectivity of data preprocessing is ensured, on the basis, the regional average dynamic threshold is taken as the core risk input, the weight is determined by the analytic hierarchy process, the multi-parameter is organically integrated by nonlinear coupling, and the quantitative score in the 0-100 point system is generated, this evaluation mode combining dynamic risk and static distribution characteristics breaks the one-sidedness of a single index, can comprehensively reflect the comprehensive risk state of the fire-fighting area, provides a precise decision basis for subsequent hierarchical strategy, and makes the risk level division more scientific and reliable;

[0136] The battery priority hierarchical awakening strategy based on the quantitative risk score realizes dynamic optimization of the fire-fighting system resources, by dividing the risk level into three levels of low, medium and high, the system can intelligently adjust the awakening mechanism according to the risk degree of different areas: the low-risk area can reduce the battery awakening frequency because of high deployment density and high response efficiency, while ensuring basic monitoring and reducing energy consumption, the high-risk area can ensure real-time monitoring and improve the timeliness of abnormal response by high-frequency awakening because of problems such as insufficient deployment and response lag, this differentiated strategy avoids resource waste and solves the monitoring blind area problem of high-risk areas, realizes the balance between safety and economy, the mechanism can be continuously optimized with dynamic changes of regional parameters, adapts to complex environments such as personnel flow and equipment adjustment in office buildings, promotes the transformation of fire monitoring from passive response to active prevention, and effectively improves the overall emergency management efficiency.

[0137] In one case of the embodiment, the battery priority hierarchical awakening strategy is executed based on the regional comprehensive risk score, including:

[0138] The regional comprehensive risk score and the battery health degree score HF are analyzed to generate an awakening priority index P, specifically including:

[0139]

[0140] In the formula, FD represents the regional comprehensive risk score, FD minand FD max respectively, wa1 and wa2 are weight coefficients respectively, and wa1 + wa2 = 1, the value range of wa1 is between 0.5-0.6, the value range of wa2 is between 0.4-0.5, αa represents the exponential adjustment parameter of the regional comprehensive risk score, and βa represents the exponential adjustment parameter of the battery health score;

[0141] The battery priority hierarchical awakening strategy is executed through the awakening priority index and the regional comprehensive risk score;

[0142] The maximum threshold of the awakening priority index is set as P max , and the minimum threshold of the awakening priority index is set as P min ;

[0143] The battery priority hierarchical awakening strategy is as follows:

[0144] Primary awakening: when P≥P max and the fire-fighting area is a high-risk area, the slave node of the fire-fighting area is awakened every one hour, the slave node collects the extinguisher environment data, working condition data and battery data as three basic parameters and uploads them to the master node;

[0145] Secondary awakening: when P min <P<P max and the fire-fighting area is a medium-risk area, the slave node of the fire-fighting area is awakened every 3 hours, and the slave node only collects the extinguisher environment data and working condition data;

[0146] Tertiary awakening: when P≤P min and the fire-fighting area is a low-risk area, the slave node of the fire-fighting area is awakened every 6 hours, and the slave node only collects the battery data;

[0147] The overall and scientific evaluation of the battery wake-up demand is realized by combining the regional comprehensive risk score FD with the battery health score HF to generate a wake-up priority index P. The FD reflects the regional fire risk situation, and the HF reflects the state of the battery itself. The combination of the two avoids the one-sidedness of a single indicator, making the wake-up decision more in line with the actual risk situation. In terms of resource allocation, the hierarchical wake-up strategy realizes the precise use of resources. The first-level wake-up collects comprehensive data at a high frequency in high-risk areas to ensure timely capture of abnormal changes in fire extinguisher environments, working conditions, and batteries, providing strong support for rapid emergency response. The second-level wake-up balances the monitoring intensity and energy consumption in medium-risk areas and only collects key environmental and working condition data to reduce data processing pressure. The third-level wake-up focuses on battery data in low-risk areas to minimize wake-up frequency, save system energy consumption and communication resources, and improve overall operating efficiency. By setting a clear wake-up priority index threshold, a standardized and differentiated wake-up mechanism is established, which can ensure the safety monitoring accuracy of high-risk areas and avoid resource waste in low-risk areas, significantly improving the flexibility of battery monitoring in fire management.

[0148] In one case of the present embodiment, a battery remaining life-monitoring efficiency-energy consumption cost three-dimensional evaluation matrix is constructed according to the battery data and the three-level sampling frequency adjustment mechanism:

[0149] Based on the battery data and the three-level sampling frequency adjustment mechanism, the normalized battery remaining life index, monitoring efficiency index, and energy consumption cost index are obtained. A battery remaining life-monitoring efficiency-energy consumption cost three-dimensional evaluation matrix is constructed based on the three indexes. Specifically, the battery remaining life index normalization process is as follows: the historical remaining life data of the fire extinguisher battery is obtained, the time unit is set to hours, the maximum remaining life value and the minimum remaining life value in the historical data are determined, for the current battery remaining life value, the minimum value is subtracted and then divided by the difference between the maximum value and the minimum value to obtain the normalized battery remaining life index, so that the result falls within the [0, 1] interval. For example, the maximum remaining life is 1000 hours, the minimum is 200 hours, and the current battery remaining life is 600 hours. The normalized value of the battery remaining life index is "(600-200) / (1000-200) = 0.5";

[0150] The normalization process of the monitoring efficiency index is as follows: the number of successful monitoring of the fire abnormal event at the three sampling frequencies is counted, the maximum number of successful monitoring and the minimum number of successful monitoring in the historical monitoring period are determined, the number of successful monitoring in the current monitoring period is subtracted from the minimum value, and then divided by the difference between the maximum value and the minimum value, to obtain the normalized monitoring efficiency index, so that it falls within the interval [0, 1], for example, the maximum number of successful monitoring is 100 times, the minimum is 10 times, and the current number of successful monitoring is 60 times, then the normalized value of the monitoring efficiency index is "(60-10) / (100-10)≈0.5556";

[0151] The normalization process of the energy consumption cost index is as follows: the node energy consumption data at different sampling frequencies is aggregated, the maximum energy consumption value and the minimum energy consumption value in the historical operation period are determined, the energy consumption value in the current period is subtracted from the minimum value, and then divided by the difference between the maximum value and the minimum value, to obtain the normalized energy consumption cost index, so that it falls within the interval [0, 1], for example, the maximum energy consumption is 1000 joules, the minimum is 100 joules, and the current energy consumption is 500 joules, then the normalized value of the energy consumption cost index is "(500-100) / (1000-100)≈0.4444";

[0152] The dimension differences of the three indexes are eliminated by normalizing the battery remaining life index, the monitoring efficiency index and the energy consumption cost index;

[0153] The time series integration algorithm is used to process the data of the battery remaining life index, the monitoring efficiency index and the energy consumption cost index in the time series, the recent monitoring data of each index is integrated, and the value reflecting the overall state in a period of time is converted, and then the integral results of the three indexes are used as coordinate axes to construct a three-dimensional evaluation space;

[0154] According to the monitoring time sequence, the integral values of the three indexes in each period are combined to form data points, which are input into the fuzzy clustering algorithm. Based on the position relationship of the data points in the three-dimensional space, the algorithm considers the continuous change in time and the similarity in space, divides the data points into different categories, identifies the correlation mode of each index with time and space, generates a clustering result, and constructs a three-dimensional evaluation matrix according to the clustering result. The horizontal and vertical axes of the matrix correspond to the three indexes respectively, and each element in the matrix reflects the comprehensive evaluation value of the three indexes under specific spatio-temporal conditions, so as to comprehensively quantify and evaluate the battery-related performance;

[0155] The monitoring effectiveness and data deviation degree are dynamically evaluated to generate the joint evaluation value of each node, specifically including: the dynamic weighted coupling algorithm is used to jointly evaluate the monitoring effectiveness and data deviation degree, the historical monitoring data distribution characteristics are analyzed by the entropy weight method, the weight value of the monitoring effectiveness index is dynamically calculated, the remaining weight is automatically allocated to the reverse index of the data deviation degree, the real-time weight combination is formed, the monitoring effectiveness is normalized, the ability of the system to detect fire abnormalities is quantified, the data deviation degree is calculated to reflect the difference between the current data and the dynamic composite abnormal threshold, and finally the reverse values of the monitoring effectiveness and the data deviation degree are fused according to the dynamic weight to generate the joint evaluation value of each node;

[0156] According to the joint evaluation value of each node of the fire-fighting area, the monitoring priority of the fire-fighting area node is generated, specifically including:

[0157] The joint evaluation values of each node of the fire-fighting area are sorted in descending order to generate a monitoring priority queue, when the joint evaluation value is greater than or equal to 0.85, it is determined as a high-priority node, real-time monitoring is started, when 0.5 is less than or equal to the joint evaluation value and less than 0.85, it is determined as a medium-priority node, normal monitoring period is executed, and when the joint evaluation value is less than 0.5, it is determined as a low-priority node, and enters standby monitoring mode;

[0158] The weight of the three-dimensional evaluation matrix is dynamically adjusted according to the risk level of the fire-fighting area;

[0159] By integrating the battery remaining life, monitoring effectiveness and energy consumption cost, a three-dimensional evaluation matrix is formed to realize comprehensive quantification of battery-related performance. Through the normalization processing of the three indexes, the dimensional difference is eliminated, so that data of different natures can be compared and analyzed comprehensively on the same scale. Next, the time series integral processing further integrates the dynamic changes of each index in the time dimension into a value reflecting the overall state, providing a more stable and representative data basis for subsequent clustering analysis. The fuzzy clustering algorithm can identify the correlation pattern of each index with time and space based on the spatiotemporal position relationship of these data points in three-dimensional space, and the generated clustering result accurately reflects the comprehensive state of the battery under different conditions, which can accurately manage the battery in fire-fighting services;

[0160] The dynamic weighting coupling algorithm is used for joint evaluation of the monitoring effectiveness and data deviation degree, the weight combination can be dynamically adjusted in real time, the weight is dynamically calculated according to the historical monitoring data distribution characteristics by using the entropy weight method, the objectivity and adaptability of the evaluation process are ensured, the fusion of the monitoring effectiveness and the data deviation degree is more scientific and reasonable, and the joint evaluation value accurately reflects the monitoring ability and data quality of each node, the monitoring priority queue of the fire-fighting area node is generated according to the joint evaluation value, the reasonable allocation of the monitoring resources is realized, the high-priority node starts real-time monitoring, the fire-fighting hidden danger can be found in time, the medium-priority node performs normal monitoring period, the conventional monitoring demand is ensured, the low-priority node enters the standby monitoring mode, resources are saved, meanwhile, the weight of the three-dimensional evaluation matrix is dynamically adjusted according to the risk level of the fire-fighting area, so that the evaluation system can flexibly adapt to different risk environments, the fire-fighting management strategy is further optimized, and the safety of the fire-fighting area is effectively ensured.

[0161] In a case of the embodiment, the weight of the three-dimensional evaluation matrix is dynamically adjusted according to the risk level of the fire-fighting area, including:

[0162] When the fire-fighting area is a high-risk area, the monitoring effectiveness weight is increased, and the energy consumption cost weight is reduced.

[0163] When the fire-fighting area is a medium-risk area, the default weight is maintained.

[0164] When the fire-fighting area is a low-risk area, the energy consumption cost weight is increased, and the monitoring effectiveness weight is reduced.

[0165] In a high-risk fire-fighting area:

[0166] 1. In the high-risk area, the fire extinguisher may accelerate the battery aging due to high environmental temperature, and needs to be frequently triggered in an emergency (such as uploading data to the master node in real time), and the battery performance directly determines whether the fire extinguisher can remain stable in multiple uses or long-time work, therefore, the battery data weight (γ) can be 0.4, and the environmental parameters (such as temperature and humidity) of the high-risk area affect the battery performance, but such area is usually equipped with constant temperature and humidity equipment (such as precision air conditioner), the environmental fluctuation range is small, and the environmental risk has been controlled by physical measures (such as fireproof material and ventilation system) in the early stage of construction, therefore, the importance of real-time monitoring of the environmental data is relatively lower than that of the battery real-time state, and therefore the environmental data weight (α) is appropriately reduced, the environmental data weight (α) can be 0.3, and the pressure index in the working condition data is a direct basis for whether the fire extinguisher can spray extinguishing agent (such as insufficient pressure and unable to work), even if the battery state is good, the working condition is abnormal, and the fire extinguishing is still failed, therefore, the basic monitoring weight needs to be maintained, and therefore the working condition data weight (β) can be 0.3, that is, the basic monitoring of the working state of the fire extinguisher can be maintained.

[0167] 2. In high-risk scenarios, whether the battery can trigger multiple times is crucial. The battery's health state (HS) reflects the battery's long-term aging degree (such as internal resistance, capacity decay). Even if the battery SOC is sufficient (such as 0.8), if the battery's health state (HS) < 0.5 (severe aging), the battery may fail due to high internal resistance during the first large-current discharge. Therefore, w HS The value can be 0.8, ensuring the reliability of the battery in extreme working conditions. SOC The value can be 0.2.

[0168] 3. The working condition data (pressure) directly determines whether the fire extinguishing can be successful (such as insufficient pressure, the injection fails), and the battery data (SOC / HS) determines whether it can continue to feed back the state. Therefore, w B The value can be 0.5, for example, when the battery is abnormal (such as SOC < 0.2), even if the environment and working conditions are normal, it needs to be awakened immediately and the sampling frequency is increased to avoid "device available but sampling interruption". E The value can be 0.2, because the environment of the high-risk area has been controlled by physical measures, and the abnormality is mostly short-term and sudden (such as sudden increase in smoke density), which can be quickly responded by the dynamic adjustment factor δ in the dynamic composite abnormal threshold, without over-weighting in the deviation calculation. R The value can be 0.3.

[0169] 4. The awakening strategy of high-risk fire-fighting areas needs to respond to the overall risk of the area and the health of individual batteries, for example, the comprehensive risk score of a certain computer room area = 85 (high risk), but the health score of a certain fire extinguisher battery = 0.9 (healthy), at this time the awakening priority is dominated by the comprehensive risk score of the area, ensuring that all devices in the area enter high-frequency monitoring. If the comprehensive risk score of the area = 80 and the health score of the battery = 0.2 (severe aging), the health score of the battery is increased in weight, and the device with abnormal battery is awakened first. Therefore, wa1 can be 0.5 and wa2 can be 0.5, to avoid excessive awakening or missing awakening caused by a single factor (such as high area risk but healthy battery).

[0170] In the medium-risk fire-fighting area:

[0171] 1、In the medium-risk area, the office environment risk (such as human smoking, equipment heating) and the working condition risk (such as the fire extinguisher being moved, the pressure naturally decaying) need to be monitored synchronously, for example, the increase in humidity may cause the rust of the metal parts of the fire extinguisher (affecting the working condition) and accelerate the corrosion of the battery electrode (affecting the battery data), both of which have relevance, and the balanced weight can avoid the single factor missing detection, therefore the environment data weight (a) can be valued at 0.35, the working condition data weight (b) can be valued at 0.35, while the fire extinguisher in the medium-risk area has low usage frequency, the battery is in a long standby state, the instant availability of the battery SOC (current power) has less influence (even if the power is 50%, it can also meet the single triggering demand), and the slow decline of the battery health state HS can be captured through regular sampling monitoring (such as the secondary sampling frequency), so it does not need to rely on the battery data too much, therefore the battery data weight (g) can be valued at 0.3;

[0172] 2、In the medium-risk fire-fighting area, the office fire extinguisher needs to balance the battery SOC (current power) and the battery health state HS, battery SOC < 0.2 may cause the sensor to fail to sample on time, affecting data integrity, and battery health state HS < 0.6 means that the remaining life of the battery is < 1 year, which needs to be replaced in advance, therefore w HS can be valued at 0.7, w SOC can be valued at 0.3;

[0173] 3、In the medium-risk fire-fighting area, the office environment (such as smoking causing the increase in smoke concentration), working condition (such as the fire extinguisher being moved causing the position offset), and battery (such as long standby causing the decline of the battery health state HS) risks are evenly distributed, therefore, w R can be valued at 0.3 to ensure that the pressure anomaly is captured in time, w E can be valued at 0.3, while the progressive influence of temperature and humidity fluctuations on the battery and working condition needs to be concerned (such as every 10% increase in humidity, the battery self-discharge rate increases by 15%), w B can be valued at 0.4 to balance the battery health and instant power and avoid the missing judgment of “working condition / environment is normal but the battery is about to fail”;

[0174] 4、The overall risk of the medium-risk area mainly reflects the comprehensive influence of the fire extinguisher deployment density and the master-slave node distance, therefore wa1 is slightly higher than wa2, because the management goal of the medium-risk area is efficiency optimization-prioritize waking up the fire-fighting equipment with “high regional risk but medium battery health” (such as the regional comprehensive risk score = 60, the battery health score HF = 0.6), to avoid the energy waste caused by excessive attention to individual battery health (such as the frequent awakening of the high-health battery in the low-risk area), and then wa1 can be valued at 0.55 and wa2 can be valued at 0.45;

[0175] In the low-risk fire-fighting area:

[0176] 1、Although the environmental parameters seem to be relatively stable in low-risk areas, long-term high humidity (such as humidity > 80% in storage rooms due to poor ventilation) or extreme temperature (such as stairwell temperature < 0°C in winter) can slowly damage the battery and working condition performance, for example, the battery resistance increases in low temperature environment, resulting in insufficient sensor start-up current (even if the battery SOC = 0.5, it may not wake up), high humidity can cause the internal circuit board of the fire extinguisher to be short-circuited (abnormal working condition), therefore the system needs to capture environmental parameters by increasing the α weight, therefore the environmental data weight (α) can be taken as 0.4, and the fire extinguisher in the low-risk area moves or triggers rarely, the natural fluctuation range of the working condition data (pressure, position) is small (such as the pressure decreases by 0.05 MPa per year), and the health state (HS) of the battery declines at a lower rate than in high-risk and medium-risk areas, therefore, the β and γ weights are set to medium, which ensures the monitoring of the working condition basic state and the remaining life of the battery, and avoids wasting resources due to excessive attention to stable parameters, therefore the working condition data weight (β) can be taken as 0.3, and the battery data weight (γ) can be taken as 0.3;

[0177] 2、The battery in the low-risk fire-fighting area is in a low-power standby state for a long time, and the battery SOC fluctuates little (0.3-0.7), but the health state (HS) of the battery declines in a hidden manner (such as a decrease of 0.05 per year), which may fail due to a sudden decrease in capacity at the first trigger, therefore w HS can be taken as 0.6, and w SOC can be taken as 0.4, and the sensitivity to "long-term aging" is improved by the health state (HS) weight of the battery, avoiding the hidden failure of "enough power but the battery has failed";

[0178] 3、In the low-risk fire-fighting area, the hidden erosion in the long-term stable environment is the main risk (such as battery corrosion caused by long-term humidity > 85% in storage rooms), therefore w E can be taken as 0.5, the working condition data weight is the lowest, w R can be taken as 0.2, because the fire extinguisher in the low-risk area is fixed in position and the natural decay of pressure is slow, it does not need to be monitored frequently, w B can be taken as 0.3;

[0179] 4、The regional comprehensive risk score of the low-risk area is usually < 40 points, indicating high deployment density, short node distance, and stable overall environment, at this time the wake-up priority depends more on the regional distribution characteristics, therefore wa1 can be taken as 0.6, emphasizing "regional stability priority", and wa2 can be taken as 0.4;

[0180] By differentiating the weight configuration according to the risk level, the pertinence and reliability of the fire monitoring are significantly improved. In the high-risk area, the instant state and the core indicators of the working condition of the battery are focused on, the stable operation of the fire-fighting equipment in the extreme scene is preferentially ensured, and the fire extinguishing failure caused by battery aging or pressure abnormality is avoided. In the medium-risk area, the weights of the environment, working condition and battery data are balanced, and the associated risks (such as the progressive influence of humidity on the equipment components) are synchronously captured to prevent the single factor from being missed. In the low-risk area, the long-term erosion monitoring of the environment is strengthened to early warn the implicit failure (such as the dampening of the circuit board caused by high humidity) and make up for the potential risk blind area in the stable environment. This grading strategy accurately matches the monitoring resources with the risk characteristics, avoids the monitoring blind area in the high-risk scene, and prevents the waste of resources in the low-risk scene.

[0181] By dynamically adjusting the weight, the monitoring efficiency and energy consumption cost are effectively balanced, the system management efficiency is improved, the battery health state weight and the regional risk dominant mechanism in the wake-up strategy are improved in the high-risk area to ensure the timeliness and comprehensiveness of the emergency response, the wake-up priority is reasonably allocated under the efficiency optimization target in the medium-risk area to avoid the energy waste caused by excessive wake-up, and the working condition and battery instant data weight are reduced in the low-risk area to significantly reduce the energy consumption while ensuring the basic monitoring. The low-value high-frequency wake-up is reduced through the wake-up strategy, and the collaborative optimization of the fire management system in management is realized.

[0182] In one case of the embodiment, based on the three-dimensional evaluation matrix, a fire management strategy is generated, including:

[0183] The three-dimensional evaluation matrix is analyzed to obtain a comprehensive score of the fire area node, specifically including: the battery remaining life indicator, the monitoring efficiency indicator and the energy consumption cost indicator are weighted and fused to obtain the comprehensive score of the fire area node, and the comprehensive score is valued in the range of [0, 1];

[0184] Based on the comprehensive score, a fire management strategy is generated, and the fire management strategy includes: a battery health management strategy and a battery dynamic power consumption regulation strategy;

[0185] The battery health management strategy is specifically as follows:

[0186] When the node is a high priority and the comprehensive score is greater than or equal to 0.85, the sampling frequency is increased to 1 minute / time, and the battery is marked for replacement within 30 days;

[0187] When the node is a medium priority and 0.5 is less than or equal to the comprehensive score and less than 0.85, the sampling is maintained at 10 minutes / time;

[0188] When the node is a low priority and the comprehensive score is less than 0.5, the frequency is reduced to 6 hours / time, and only the battery SOC basic monitoring is retained;

[0189] The battery dynamic power consumption regulation strategy is as follows:

[0190] For high-risk fire-fighting areas, the master node is always active, and the slave node wakes up every 30 minutes;

[0191] For medium-risk fire-fighting areas, the master node works intermittently (wakes up every 10 minutes), and the slave node dynamically adjusts the sampling according to the battery health score, as follows:

[0192] When the battery health score HF is greater than or equal to 0.7 (battery health), the slave node collects data at a secondary sampling frequency, and only uploads working condition data (pressure, position) and environmental data (temperature, humidity), and battery data (SOC / HS) is collected at a tertiary sampling frequency (once every 30 minutes);

[0193] When the battery health score HF is less than 0.7 (battery health is declining), the slave node collects all three types of data (environment, working condition, battery) at a secondary sampling frequency, and uploads the battery health state abnormal signal (such as SOC<0.3 or HS<0.6) when the master node is activated;

[0194] For low-risk fire-fighting areas, the master node is deeply hibernated (activated twice a day), and the slave node only wakes up in an emergency when the temperature in the fire-fighting area is greater than 60°C;

[0195] Through a three-dimensional evaluation matrix, the nodes in the fire-fighting area are comprehensively scored, achieving precision and scientific management of fire-fighting, and the core indicators such as battery remaining life, monitoring efficiency, and energy consumption cost are weighted and integrated, changing the one-sidedness of single indicator evaluation, and can fully reflect the actual state of the node. Based on the comprehensive score, the battery health management strategy is developed, and different management measures are taken for high, medium and low priority nodes: high priority nodes increase the sampling frequency and are marked for replacement, ensuring real-time monitoring and timely maintenance of key nodes, medium priority nodes maintain regular monitoring to avoid excessive intervention, and low priority nodes reduce the sampling frequency to save energy, which not only ensures the fire-fighting efficiency of key areas, but also avoids resource waste, achieving a dynamic balance between monitoring accuracy and management cost, and improving the overall reliability of the fire-fighting system;

[0196] By implementing hierarchical management according to the risk level of the fire-fighting area, the matching degree of system energy consumption and monitoring efficiency is effectively optimized, the master node in the high-risk area is active all the time, the slave node is periodically woken up, the real-time response to abnormal conditions is ensured, the fire-fighting safety is maximally guaranteed, the sampling frequency and data uploading strategy of the slave node in the medium-risk area are dynamically adjusted according to the battery health degree, the unnecessary energy consumption is reduced through differential sampling while ensuring the timely transmission of key data (such as battery abnormal signal), the master node in the low-risk area is deeply hibernated, and the slave node is only woken up at high temperature, thereby significantly reducing the system power consumption and prolonging the equipment endurance. This hierarchical regulation mechanism not only meets the monitoring requirements of different risk areas, but also reduces the overall energy consumption through intelligent hibernation and wake-up strategies, realizes the benign interaction between the fire-fighting monitoring system and the energy saving and consumption reduction, and provides technical support for long-term stable operation.

[0197] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and changes can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A smart fire service management system characterized in that, The method comprises the following steps: a data acquisition unit is used to acquire three basic parameters of environment data, working condition data and battery data of a fire-fighting object in an office building, wherein the fire-fighting object is a fire extinguisher; a fusion unit is used to fuse the environment data, working condition data and battery data to generate a dynamic composite abnormal threshold value with battery state awareness, comprising: fusing and weighting the normalized environment data, working condition data and battery data to obtain fused data; analyzing the fused data to generate a dynamic composite abnormal threshold value with battery state awareness, specifically comprising: calculating the average value of the fused data in a historical period to obtain a historical average value; calculating the standard deviation of the fused data in the historical period to obtain a historical standard deviation; scaling the product of the historical average value and the historical standard deviation, and the scaling ratio is controlled by a dynamic adjustment coefficient, and finally the scaled result is superimposed on the historical average value to form a dynamic composite abnormal threshold value; the dynamic adjustment coefficient is composed of three parts, which respectively reflect the dynamic influence of the battery health state, the environment fluctuation characteristics and the working condition stability on the threshold value; an adjustment unit is used to compare the working condition data, environment data and battery data with the dynamic composite abnormal threshold value, and execute a three-level sampling frequency adjustment mechanism based on the battery health degree; a management unit is used to divide the office building into fire-fighting areas managed by master and slave nodes, and execute a battery priority classification wake-up strategy based on the distribution characteristics of the fire-fighting areas and the dynamic composite abnormal threshold value; a balancing unit is used to construct a three-dimensional evaluation matrix of battery remaining life-monitoring efficiency-energy consumption cost according to the battery data and the three-level sampling frequency adjustment mechanism, and generate a fire-fighting management strategy based on the three-dimensional evaluation matrix.

2. The intelligent fire service management system as claimed in claim 1, wherein, comparing the working condition data, environment data and battery data with the dynamic composite abnormal threshold value, and executing a three-level sampling frequency adjustment mechanism based on the battery health degree, comprising: calculating the battery data to obtain a battery health degree score; calculating the data deviation of the working condition data, environment data and battery data from the dynamic composite abnormal threshold value, specifically as follows: calculating the absolute difference between the working condition parameter and the dynamic composite abnormal threshold value, and then dividing by the dynamic composite abnormal threshold value to obtain the relative deviation of the working condition parameter; calculating the absolute difference between the environment parameter and the dynamic composite abnormal threshold value, and then dividing by the dynamic composite abnormal threshold value to obtain the relative deviation of the environment parameter; calculating the absolute difference between the battery parameter and the dynamic composite abnormal threshold value, and then dividing by the dynamic composite abnormal threshold value to obtain the relative deviation of the battery parameter; wherein the weight value range of the relative deviation of the working condition parameter is between 0.3 and 0.4, the weight value range of the relative deviation of the environment parameter is between 0.2 and 0.3, and the weight value range of the relative deviation of the battery parameter is between 0.3 and 0.5, and the sum of the three weights is equal to 1; adding the relative deviation of the working condition parameter, the relative deviation of the environment parameter and the relative deviation of the battery parameter according to their respective weights to obtain the data deviation; dividing the sampling frequency into three levels according to the battery health degree score and the data deviation, the three levels being a first-level sampling frequency, a second-level sampling frequency and a third-level sampling frequency.

3. The intelligent fire service management system as claimed in claim 1, wherein, dividing the office building into fire-fighting areas managed by master and slave nodes, comprising: The office building is divided into multiple fire-fighting areas according to floors, and each floor is a fire-fighting area; Each fire-fighting area contains all fire extinguishers on the floor, and each fire-fighting area is provided with one master node, and multiple slave nodes are arranged under each master node; The master node is used to manage multiple slave nodes on the floor; The slave node is associated with multiple fire extinguishers, and collects fire extinguisher environmental data, working condition data and battery data in the area, and transmits the three basic parameters to the master node.

4. The intelligent fire service management system as claimed in claim 3, wherein, Combined with the distribution characteristics of the fire-fighting area and the dynamic composite abnormal threshold, a battery priority hierarchical awakening strategy is executed, including: According to the fire-fighting area divided by the floor, the distribution characteristic parameters of each fire-fighting area are extracted, and the distribution characteristic parameters are composed of the fire extinguisher deployment density and the master-slave node distance; Among them, the fire extinguisher deployment density can be obtained by dividing the number of fire extinguishers in each floor fire-fighting area by the area of the floor fire-fighting area; The master-slave node distance can be obtained by calculating the straight-line distance from each fire extinguisher to the master node using the Euclidean distance formula; The dynamic composite abnormal threshold is associated by area, and the regional average dynamic threshold is calculated by the master node collecting the dynamic composite abnormal threshold reported by all slave nodes on the floor, including: The master node collects the dynamic composite abnormal threshold reported by all slave nodes on the floor, and the quartile range method is used to identify and eliminate outlier dynamic composite abnormal thresholds. According to the fire extinguisher deployment density and distance weight of each slave node associated area, the effective dynamic composite abnormal threshold is spatially weighted and averaged, and finally the regional average dynamic threshold reflecting the overall state of the fire-fighting system on the floor is generated.

5. The intelligent fire service management system as claimed in claim 4, wherein, Combined with the distribution characteristics of the fire-fighting area and the dynamic composite abnormal threshold, the battery priority hierarchical awakening strategy is executed, and also includes: The regional average dynamic threshold is combined with the distribution characteristic parameters to generate a regional comprehensive risk score, including: normalizing the fire extinguisher deployment density and the master-slave node distance, then establishing a multi-parameter coupling model, taking the regional average dynamic threshold as the core risk input item, the deployment density as the reverse adjustment factor, and the master-slave node distance as the efficiency compensation item, and then using the analytic hierarchy process to determine the weight of each parameter. The regional average dynamic threshold and the distribution characteristic parameters are nonlinearly coupled by a weighted fusion algorithm to generate a quantitative risk score of 0-100 points; When the regional comprehensive risk score is between 0-40, the fire-fighting area is a low-risk area; When the regional comprehensive risk score is between 41-70, the fire-fighting area is a medium-risk area; When the regional comprehensive risk score is between 71-100, the fire-fighting area is a high-risk area; Based on the regional comprehensive risk score, the battery priority hierarchical awakening strategy is executed.

6. The intelligent fire service management system as claimed in claim 5, wherein, Based on the regional comprehensive risk score, the battery priority hierarchical awakening strategy is executed, including: The regional comprehensive risk score and the battery health score are analyzed to generate an awakening priority index; The battery priority hierarchical awakening strategy is executed through the awakening priority index and the regional comprehensive risk score, including: The battery priority hierarchical awakening strategy includes primary awakening, secondary awakening and tertiary awakening.

7. The intelligent fire service management system as claimed in claim 5, wherein, According to the battery data and the three-level sampling frequency adjustment mechanism, a three-dimensional evaluation matrix of battery residual life-monitoring efficiency-energy consumption cost is constructed: Based on the battery data and the three-level sampling frequency adjustment mechanism, three indexes of normalized battery residual life index, monitoring efficiency index and energy consumption cost index are obtained, and a three-dimensional evaluation matrix of battery residual life-monitoring efficiency-energy consumption cost is constructed based on the three indexes; The monitoring efficiency and data deviation are dynamically evaluated to generate the joint evaluation value of each node; According to the joint evaluation value of each node in the fire-fighting area, the monitoring priority of the fire-fighting area node is generated, which specifically includes: When the joint evaluation value is greater than or equal to 0.85, it is determined as a high-priority node, and real-time monitoring is started; when 0.5 is less than the joint evaluation value and less than 0.85, it is determined as a medium-priority node, and normal monitoring period is executed; when the joint evaluation value is less than 0.5, it is determined as a low-priority node, and enters standby monitoring mode; The weight of the three-dimensional evaluation matrix is dynamically adjusted according to the risk level of the fire-fighting area.

8. The intelligent fire service management system as claimed in claim 7, wherein, The weight of the three-dimensional evaluation matrix is dynamically adjusted according to the risk level of the fire-fighting area, including: When the fire-fighting area is a high-risk area, the monitoring efficiency weight is increased and the energy consumption cost weight is reduced; When the fire-fighting area is a medium-risk area, the default weight is maintained; When the fire-fighting area is a low-risk area, the energy consumption cost weight is increased and the monitoring efficiency weight is reduced.

9. The intelligent fire service management system as claimed in claim 7, wherein, Based on the three-dimensional evaluation matrix, the fire management strategy is generated, including: The three-dimensional evaluation matrix is analyzed to obtain the comprehensive score of the fire-fighting area node; Based on the comprehensive score, the fire management strategy is generated, including battery health management strategy and battery dynamic power consumption regulation strategy; The battery health management strategy is as follows: When the node is high-priority and the comprehensive score is greater than or equal to 0.85, the sampling frequency is increased to 1 minute / time, and the battery is marked for replacement within 30 days; When the node is medium-priority and 0.5 is less than the comprehensive score and less than 0.85, the sampling frequency is maintained at 10 minutes / time; When the node is low-priority and the comprehensive score is less than 0.5, the frequency is reduced to 6 hours / time, and only the battery SOC basic monitoring is retained; The battery dynamic power consumption regulation strategy is as follows: For high-risk fire-fighting areas, the master node is always active, and the slave node is awakened every 30 minutes; For medium-risk fire-fighting areas, the master node works intermittently, and the slave node dynamically adjusts the sampling according to the battery health score; For low-risk fire-fighting areas, the master node is deeply asleep, and the slave node is only awakened in emergency when the temperature in the fire-fighting area is greater than 60℃.

Images