Intelligent Fire-fighting Facility Detection Method and System Based on Internet of Things

Abstract

The present invention relates to the technical field of fire safety, and discloses an intelligent fire-fighting facility detection method and system based on the Internet of Things. The method includes obtaining smoke concentration, temperature and fire-fighting facility status data; inputting the smoke concentration data of the area to be detected into a smoke concentration prediction model to obtain a smoke concentration prediction value; inputting the temperature data of the area to be detected into a seasonal temperature prediction model to obtain a temperature prediction value; obtaining a fire risk assessment parameter prediction value of the area to be detected through a fire risk assessment parameter prediction model; calculating a fire-fighting facility performance assessment value of the area to be detected; and performing risk marking on the fire-fighting facilities in the area to be detected to complete the detection of the fire-fighting facilities in the area to be detected. The intelligent fire-fighting facility detection method based on the Internet of Things provided by the present invention effectively solves the problem of incomplete data collection and improves the accuracy of the detection and analysis results of fire-fighting facilities.

Description

Technical Field

[0001] The present invention relates to the technical field of fire safety, and in particular, to an intelligent fire-fighting facility detection method and system based on the Internet of Things. Background Art

[0002] At present, with the acceleration of the urbanization process, fire safety issues have become increasingly prominent. The Internet of Things refers to various devices and technologies such as various information sensors, radio frequency identification technologies, global positioning systems, infrared sensors, and laser scanners, which can collect real-time data of any object or process that needs to be monitored, connected, and interacted. Through various possible network accesses, the connection between things and things, and between things and people can be realized, and the intelligent perception, identification, and management of items and processes can be achieved. The development of the Internet of Things technology provides new possibilities for the intelligent management of fire-fighting facilities. By deploying various sensors and wireless communication technologies, real-time monitoring and early warning of fire hazards can be realized, and the fire safety level can be improved.

[0003] The existing fire-fighting facility detection technologies mainly include three steps: the placement, detection, and removal of fire-fighting facilities. These technologies usually rely on manual operations and traditional monitoring devices. For example, an operator installs a wiring socket at a water source and connects it to a fire-fighting facility detection device. However, in the existing methods, the real-time obtained smoke concentration and temperature data only reflect the current state and cannot provide information on future trends. In fire risk assessment, understanding future change trends is crucial for taking preventive measures in advance. In addition, fire risk assessment is usually in a complex dynamic environment, and real-time data may be affected by various factors, such as the accuracy of sensors and environmental interference.

[0004] In summary, the existing methods have limitations in the comprehensiveness of fire risk assessment data collection, which in turn leads to inaccurate analysis results of fire-fighting facility detection. Summary of the Invention

[0005] The present invention provides an intelligent fire-fighting facility detection method and system based on the Internet of Things to solve the problem of incomplete data collection.

[0006] In a first aspect, to solve the above technical problems, the present invention provides an intelligent fire-fighting facility detection method based on the Internet of Things, including:

[0007] Obtaining the current smoke concentration data, current temperature data, and current fire-fighting facility status data of the area to be detected;

[0008] Inputting the current smoke concentration data into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value;

[0009] Inputting the current temperature data into a pre-trained seasonal temperature prediction model to obtain a temperature prediction value;

[0010] Input the temperature prediction value and the smoke concentration prediction value into a pre-trained fire risk assessment parameter prediction model to obtain the predicted value of the fire risk assessment parameter for the area to be detected;

[0011] Calculate the performance evaluation value of the fire protection facilities corresponding to the area to be detected based on the current fire protection facilities status data and the predicted value of the fire risk assessment parameter;

[0012] Classify the performance evaluation value of the fire protection facilities according to a preset score threshold, and mark the fire protection facilities in the area to be detected according to the risk level classification result, thereby completing the detection of the fire protection facilities in the area to be detected;

[0013] Among them, the smoke concentration prediction model, the seasonal temperature prediction model, and the fire risk assessment parameter prediction model are trained based on historical fire data, and the historical fire data includes multiple fire event records, and each fire event record includes historical smoke concentration data, historical temperature data, historical fire protection facilities status data, and historical fire risk assessment parameters.

[0014] In an alternative embodiment, the training process of the smoke concentration prediction model includes:

[0015] Clean the historical smoke concentration data to obtain the first smoke concentration data;

[0016] Use a clustering algorithm to classify the first smoke concentration data to obtain the second smoke concentration data;

[0017] Among them, the second smoke concentration data is the smoke concentration data of multiple regions;

[0018] Statistically analyze the smoke concentration data in each region of the second smoke concentration data according to a set time period to obtain an average smoke concentration set; among them, the average smoke concentration set includes the average smoke concentration of each time period;

[0019] Train a decision tree model based on the average smoke concentration set, and when the number of training times reaches the maximum preset number of rounds, the training is completed to obtain a smoke concentration prediction model.

[0020] In an alternative embodiment, the step of using a clustering algorithm to classify the first smoke concentration data to obtain the second smoke concentration data includes:

[0021] Set a set of K values, and at each K value, use the K-means method to select the initial clustering center;

[0022] Assign each smoke concentration data point of the first smoke concentration data to the nearest cluster center to form K clusters, update the cluster center of each cluster, calculate the mean of all points within the cluster, and when the change in the cluster center is less than the set threshold, obtain the clustering result; wherein, the clustering result is the smoke concentration data of K regions.

[0023] Use the silhouette coefficient to evaluate the clustering result corresponding to each K value, and select the clustering result corresponding to the K value with the optimal clustering effect as the second smoke concentration data.

[0024] In an optional implementation manner, the training process of the seasonal temperature prediction model includes:

[0025] Divide the historical temperature data by season to obtain seasonal fire data;

[0026] Wherein, the seasonal fire data includes spring fire data, summer fire data, autumn fire data, and winter fire data;

[0027] According to the set time period, calculate the average temperature of the area included in the seasonal fire data in each time period to obtain a set of seasonal average temperatures;

[0028] Wherein, the set of seasonal average temperatures includes a set of spring average temperatures, a set of summer average temperatures, a set of autumn average temperatures, and a set of winter average temperatures;

[0029] Based on the set of seasonal average temperatures, train the LSTM neural network model, and when the number of training times reaches the maximum preset number of rounds, the training is completed to obtain the seasonal temperature prediction model;

[0030] Wherein, the seasonal temperature prediction model includes a spring temperature prediction model, a summer temperature prediction model, an autumn temperature prediction model, and a winter temperature prediction model.

[0031] In an optional implementation manner, the training process of the fire risk assessment parameter prediction model includes:

[0032] Based on the set of average smoke concentrations, the set of seasonal average temperatures, and historical fire risk assessment parameters, train the BP neural network model, and when the number of training times reaches the maximum preset number of rounds, the training is completed to obtain the fire risk assessment parameter prediction model;

[0033] Wherein, the historical fire risk assessment parameters include parameters indicating whether there is a fire source in the building and fire risk level parameters, and the fire risk level parameters represent the possibility of a fire occurring.

[0034] In an alternative embodiment, based on the current fire-fighting facility status data and the predicted values of the fire risk assessment parameters, a fire-fighting facility performance evaluation value corresponding to the area to be detected is calculated, including:

[0035] The fire-fighting facilities include a fire sprinkler system, a fire alarm system, a fire hydrant system, an emergency lighting system, an emergency broadcast system, and a smoke exhaust and supply system; the current fire-fighting facility status data includes the usage data, equipment temperature data, fault data, extinguishing agent flow rate data, and extinguishing agent pressure data of the fire-fighting facilities;

[0036] According to the usage data and fault data in the current fire-fighting facility status data, the fire extinguishing effectiveness and the failure rate are calculated; wherein, the usage data includes the usage time and the number of successful fire extinguishments of the fire-fighting facilities, and the fault data includes the usage time and the number of faults of the fire-fighting facilities;

[0037] According to a set of preset thresholds, the usage time, the equipment temperature data, the extinguishing agent flow rate data, the extinguishing agent pressure data, the failure rate, and the fire extinguishing effectiveness are respectively evaluated to obtain a usage time evaluation value, an equipment temperature evaluation value, an extinguishing agent flow rate evaluation value, an extinguishing agent pressure evaluation value, a fault evaluation value, and a fire extinguishing effectiveness evaluation value;

[0038] Input the predicted value of the smoke concentration and the predicted value of the temperature into the fire alarm system, and output an alarm response value;

[0039] The calculation formula of the fire-fighting facility performance evaluation value is as follows:

[0040] ;

[0041] Wherein, X is the fire-fighting facility performance evaluation value, are respectively the alarm response value, the usage time evaluation value, the equipment temperature evaluation value, the extinguishing agent flow rate evaluation value, the extinguishing agent pressure evaluation value, the fault evaluation value, and the fire extinguishing effectiveness evaluation value.

[0042] In an alternative embodiment, the calculation of the failure rate and the fire extinguishing effectiveness according to the temperature data and the fault data in the current fire-fighting facility status data includes:

[0043] The failure rate is the frequency of occurrence of faults in the fire-fighting facilities, and the fire extinguishing effectiveness is the success rate of fire extinguishment of the fire-fighting facilities. The calculation formula of the failure rate is:

[0044] ;

[0045] The calculation formula of the fire extinguishing effectiveness is:

[0046] ;

[0047] Among them, is the failure rate, T is the usage time, is the number of failures of the fire protection facilities, that is, the total number of failures of the fire protection facilities during the usage time; is the fire extinguishing effectiveness, is the number of successful fire extinguishments of the fire protection facilities, that is, the sum of the number of successful fire extinguishments of the fire protection facilities during the usage time.

[0048] In a second aspect, the present invention provides an intelligent fire protection facilities detection device based on the Internet of Things, including:

[0049] A data acquisition module, which acquires the current smoke concentration data, current temperature data, and current fire protection facilities status data of the area to be detected;

[0050] A smoke concentration prediction module, which is used to input the current smoke concentration data into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value;

[0051] A temperature prediction module, which is used to input the current temperature data into a pre-trained seasonal temperature prediction model to obtain a temperature prediction value;

[0052] A fire risk assessment parameter prediction module, which is used to input the temperature prediction value and the smoke concentration prediction value into a pre-trained fire risk assessment parameter prediction model to obtain a fire risk assessment parameter prediction value of the area to be detected;

[0053] A fire protection facilities performance evaluation value calculation module, which is used to calculate a fire protection facilities performance evaluation value corresponding to the area to be detected according to the current fire protection facilities status data and the fire risk assessment parameter prediction value;

[0054] A risk marking module, which is used to classify the fire protection facilities performance evaluation value into risk levels according to a preset score threshold, and mark the fire protection facilities in the area to be detected according to the risk level classification result, thereby completing the detection of the fire protection facilities in the area to be detected;

[0055] Among them, the smoke concentration prediction model, the seasonal temperature prediction model, and the fire risk assessment parameter prediction model are trained based on historical fire data, and the historical fire data includes multiple fire event records, and each fire event record includes historical smoke concentration data, historical temperature data, historical fire protection facilities status data, and historical fire risk assessment parameters.

[0056] In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method for detecting intelligent fire-fighting facilities based on the Internet of Things described in any one of the above is implemented.

[0057] In a fourth aspect, the present invention further provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. When the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the method for detecting intelligent fire-fighting facilities based on the Internet of Things described in any one of the above.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The present invention provides a method for detecting intelligent fire-fighting facilities based on the Internet of Things, including: obtaining historical fire data; wherein the historical fire data includes multiple fire event records, and each fire event record includes historical smoke concentration data, historical temperature data, historical fire-fighting facility status data, and historical fire risk assessment parameters; obtaining the current smoke concentration data, current temperature data, and current fire-fighting facility status data of the area to be detected; inputting the current smoke concentration data into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value; inputting the current temperature data into a pre-trained seasonal temperature prediction model to obtain a temperature prediction value; inputting the temperature prediction value and the smoke concentration prediction value into a pre-trained fire risk assessment parameter prediction model to obtain a fire risk assessment parameter prediction value for the area to be detected; calculating a fire-fighting facility performance evaluation value corresponding to the area to be detected according to the current fire-fighting facility status data and the fire risk assessment parameter prediction value; classifying the risk level of the fire-fighting facility performance evaluation value according to a preset score threshold, and performing a risk mark on the fire-fighting facilities in the area to be detected according to the risk level classification result, thereby completing the detection of the fire-fighting facilities in the area to be detected.

[0060] The present invention provides an intelligent fire-fighting facility detection method based on the Internet of Things. First, a data acquisition module collects historical fire data, as well as smoke concentration data, temperature data, fire-fighting facility status data, and fire risk assessment parameters of the area to be detected. Then, the smoke concentration prediction module inputs the smoke concentration data of the area to be detected into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value. Similarly, the temperature prediction module inputs the temperature data into a seasonal temperature prediction model to obtain a temperature prediction value. Subsequently, the fire risk assessment parameter prediction module inputs the predicted temperature data and smoke concentration data of the area to be detected into a fire risk assessment parameter prediction model, thereby obtaining a fire risk assessment parameter prediction value of the area to be detected. Using these data, the fire-fighting facility performance evaluation value calculation module calculates a fire-fighting facility performance evaluation value based on the fire-fighting facility status data and fire risk assessment parameters of the area to be detected. Finally, the risk marking module classifies the fire-fighting facility performance evaluation value according to a preset score threshold, and marks the fire-fighting facilities in the area to be detected according to the risk level classification result, completing the detection work of the fire-fighting facilities.

[0061] The present invention provides an intelligent fire-fighting facility detection method and system based on the Internet of Things to solve the problems of limited comprehensiveness of data collection and accuracy of analysis results. Through the prediction model, the changing trends of smoke concentration and temperature can be estimated in advance, so as to more accurately evaluate the fire risk. At the same time, the prediction model can perform comprehensive analysis by combining data from multiple dimensions (such as season, time, historical events, etc.). Compared with real-time data that can only reflect the state at a single moment, this multi-dimensional analysis can more comprehensively evaluate the fire risk. For example, even if the current smoke concentration and temperature are within the normal range, but if the prediction model shows that they may rise rapidly in the future, then measures need to be taken in advance to avoid the occurrence of a fire. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 is a schematic flowchart of an intelligent fire-fighting facility detection method based on the Internet of Things provided by the first embodiment of the present invention;

[0063] Figure 2 is a schematic structural diagram of an intelligent fire-fighting facility detection system based on the Internet of Things provided by the second embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0065] Reference Figure 1 , the first embodiment of the present invention provides an intelligent fire-fighting facility detection method based on the Internet of Things, including the following steps:

[0066] S11, obtain the current smoke concentration data, current temperature data and current fire-fighting facility status data of the area to be detected;

[0067] S12, input the current smoke concentration data into the pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value;

[0068] S13, input the current temperature data into the pre-trained seasonal temperature prediction model to obtain a temperature prediction value;

[0069] S14, input the temperature prediction value and the smoke concentration prediction value into the pre-trained fire risk assessment parameter prediction model to obtain the fire risk assessment parameter prediction value of the area to be detected;

[0070] S15, calculate the fire-fighting facility performance evaluation value corresponding to the area to be detected according to the current fire-fighting facility status data and the fire risk assessment parameter prediction value;

[0071] S16, classify the fire-fighting facility performance evaluation value according to a preset score threshold, and mark the fire-fighting facilities in the area to be detected according to the risk level classification result, and complete the detection of the fire-fighting facilities in the area to be detected.

[0072] Among them, the smoke concentration prediction model, the seasonal temperature prediction model and the fire risk assessment parameter prediction model are trained based on historical fire data, and the historical fire data includes multiple fire event records, and each fire event record includes historical smoke concentration data, historical temperature data, historical fire-fighting facility status data and historical fire risk assessment parameters.

[0073] Among them, the historical fire data is obtained from past fire events and obtained from fire archive records, and these data are used to train the smoke concentration prediction model, the seasonal temperature prediction model and the fire risk assessment parameter prediction model.

[0074] Specifically, each fire event record includes historical smoke concentration data, historical temperature data, historical fire-fighting facility status data, and historical fire risk assessment parameters. The smoke concentration data records the concentration level of smoke in the air during a fire. The smoke concentration data is collected by an MQ-2 sensor, which is a device specifically designed to detect smoke particles in the air and can convert the detected smoke concentration into a corresponding analog voltage signal. This voltage signal is directly proportional to the actual smoke concentration, that is, the higher the smoke concentration, the greater the output voltage value. Since the signal output by the sensor is very weak, a signal amplification circuit is required to perform gain processing on it during the data collection process. The amplified signal is then digitized by an analog-to-digital converter (ADC), converting the continuous analog signal into discrete digital values. The temperature data refers to the temperature at the fire origin and the surrounding environment. Multiple sensors are used to collect the smoke concentration data and the temperature data, so both the smoke concentration data and the temperature data cover different regions and different time periods. The fire-fighting facility status data includes the usage data of fire-fighting facilities, equipment temperature data, fault data, fire extinguishing agent flow rate data, and fire extinguishing agent pressure data. The fire risk assessment parameters include the presence of a fire source parameter in the building and a fire risk level parameter, and the fire risk level parameter represents the likelihood of a fire occurring.

[0075] In step S11, the current smoke concentration data, current temperature data, and current fire-fighting facility status data of the area to be detected are obtained.

[0076] It should be noted that the current smoke concentration data, current temperature data, and current fire-fighting facility status data of the area to be detected are obtained in real time. The smoke concentration data records the concentration level of smoke in the air during a fire and is collected by an MQ-2 sensor. The temperature data refers to the ambient temperature and is collected by a thermocouple temperature sensor. The fire-fighting facility status data includes the usage data of fire-fighting facilities, equipment temperature data, fault data, fire extinguishing agent flow rate data, and fire extinguishing agent pressure data. Among them, the usage data includes the usage time of fire-fighting facilities and the number of successful fire extinguishments, and the fault data includes the usage time of fire-fighting facilities and the number of faults of fire-fighting facilities. The equipment temperature data refers to the temperature inside and outside the equipment measured by a thermocouple sensor installed on the fire-fighting equipment. The fire extinguishing agent flow rate and pressure are detected by a flow meter and a pressure sensor respectively.

[0077] In step S12, the current smoke concentration data is input into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value.

[0078] It should be noted that the training process of the smoke concentration prediction model includes: cleaning the historical smoke concentration data, that is, removing outliers, filling in missing values, and smoothing noise to obtain the first smoke concentration data. Using a clustering algorithm to classify the first smoke concentration data to obtain the second smoke concentration data;

[0079] Among them, the second smoke concentration data is the smoke concentration data of multiple regions. Specifically, using the clustering algorithm to classify the first smoke concentration data to obtain the second smoke concentration data includes: setting the K value set to 1-10, and at each K value, using the K-means method to select the initial clustering center; Assigning each smoke concentration data point of the first smoke concentration data to the nearest clustering center to form K clusters, updating the clustering center of each cluster, calculating the mean value of all points within the cluster, and when the change in the clustering center is less than the set threshold of 0.00001, obtaining the clustering result; Among them, the clustering result is the smoke concentration data of K regions; Using the silhouette coefficient to evaluate the clustering results corresponding to each K value, and selecting the clustering result corresponding to the K value with the best clustering effect as the second smoke concentration data. Specifically, the silhouette coefficient method is an index for evaluating the clustering effect, which comprehensively considers the compactness of the data points within the cluster and the separation of the data points between the clusters. The value range of the silhouette coefficient is [-1, 1], and the closer the value is to 1, the better the clustering effect. The process of evaluating using the silhouette coefficient is: calculating the silhouette coefficients of all data points, and then taking the average value, and selecting the K value with the largest average silhouette coefficient as the optimal number of clusters. For each data point i, the calculation formula of the silhouette coefficient is as follows:

[0080] ;

[0081] Among them, is the silhouette coefficient of the i-th data point, is the average distance within the cluster, that is, the average distance between the i-th data point and all other data points within the same cluster, is the average distance between clusters, that is, the average distance between the i-th data point and all points in its nearest cluster;

[0082] Furthermore, according to the set time period, statistical analysis is performed on the smoke concentration data within each region of the second smoke concentration data to obtain the average smoke concentration set; among them, the set time period refers to taking one hour as an interval, and the average smoke concentration set includes the average smoke concentration of each time period; The calculation formula of the average smoke concentration of each time period is as follows:

[0083] ;

[0084] Among them, is the average smoke concentration within the k-th time period, is the smoke concentration in the i-th time period, and n is the number of set time periods;

[0085] Furthermore, based on the set of average smoke concentrations, the decision tree model is trained. When the number of training times reaches the maximum preset number of rounds, the training is completed, and a smoke concentration prediction model is obtained. The maximum preset number of rounds is set to 100 rounds. The smoke concentration data of the area to be detected is input into the smoke concentration prediction model to obtain a smoke concentration prediction value.

[0086] In step S13, the current temperature data is input into a pre-trained seasonal temperature prediction model to obtain a temperature prediction value.

[0087] It should be noted that the training process of the seasonal temperature prediction model includes: dividing the historical temperature data by season to obtain seasonal fire data; among them, the seasonal fire data includes spring fire data, summer fire data, autumn fire data, and winter fire data; according to the set time period, that is, taking each hour as an interval, calculate the average temperature of the area included in the seasonal fire data at each time period to obtain a set of seasonal average temperatures; among them, the set of seasonal average temperatures includes a set of spring average temperatures, a set of summer average temperatures, a set of autumn average temperatures, and a set of winter average temperatures. Based on the set of seasonal average temperatures, the LSTM neural network model is trained. When the number of training times reaches the maximum preset number of rounds, the training is completed, and a seasonal temperature prediction model is obtained; among them, the maximum preset number of rounds is set to 100 rounds, and the seasonal temperature prediction model includes a spring temperature prediction model, a summer temperature prediction model, an autumn temperature prediction model, and a winter temperature prediction model. Obtain the temperature data of the area to be detected, and input the temperature data into the temperature prediction model corresponding to the current season according to the current season to obtain a temperature prediction value.

[0088] It should be noted that due to the limitations of real-time data, the smoke concentration and temperature data obtained in real time only reflect the current state, but cannot provide information on future trends. In fire risk assessment, understanding future change trends is crucial for taking preventive measures in advance. Therefore, in this embodiment, through the prediction model, the change trends of smoke concentration and temperature can be estimated in advance, so as to more accurately assess the fire risk. For example, even if the current smoke concentration and temperature are within the normal range, but if the prediction model shows that they may rise rapidly in the future, then measures need to be taken in advance to avoid the occurrence of a fire. At the same time, the advantage of the prediction model lies in the utilization of historical data. The prediction model is trained based on historical fire data, which contains records of multiple fire events, including historical smoke concentration, temperature, fire-fighting facility status and other information. Through machine learning algorithms (such as decision trees, LSTM neural networks, etc.), the model can learn the characteristics and laws before the occurrence of a fire, so as to make a more accurate judgment on future trends. The prediction model can identify potential fire risks in advance, rather than relying solely on current real-time data. This early warning function is of great significance for fire prevention and emergency response.

[0089] In addition, due to the complexity of the application scenario, fire risk assessment is usually in a complex dynamic environment, and real-time data may be affected by various factors, such as the accuracy of sensors, environmental interference, etc. The prediction model can filter out these interference factors through learning historical data and provide a more stable trend judgment. The prediction model can also conduct comprehensive analysis by combining data from multiple dimensions (such as season, time, historical events, etc.), while real-time data can only reflect the state at a single moment. This multi-dimensional analysis can more comprehensively assess the fire risk.

[0090] In step S14, the temperature prediction value and the smoke concentration prediction value are input into a pre-trained fire risk assessment parameter prediction model to obtain the fire risk assessment parameter prediction value of the area to be detected.

[0091] It should be noted that the training process of the fire risk assessment parameter prediction model includes: training a BP neural network model based on the average smoke concentration set, the seasonal average temperature set and historical fire risk assessment parameters, and completing the training when the number of training times reaches the maximum preset number of rounds, to obtain the fire risk assessment parameter prediction model; wherein, the maximum preset number of rounds is set to 100 rounds, and the historical fire risk assessment parameters include whether there is a fire source parameter in the building and the fire risk level parameter.

[0092] Specifically, the fire risk assessment parameter prediction model includes an input layer, a hidden layer, and an output layer. The number of neurons in the input layer is set to 2, with 1 neuron for receiving smoke concentration data and 1 neuron for receiving temperature data; the number of neurons in the output layer is set to 2, with 1 neuron for outputting the parameter indicating whether there is a fire source in the building and 1 neuron for outputting the fire risk level parameter. A corresponding relationship is established between the neurons in the hidden layer and the neurons in the output layer using the sigmoid function as the activation function, and the connection weights between the neurons are initialized with random values. When the input layer is activated by the smoke concentration data value and the temperature data value, the hidden layer outputs:

[0093] ;

[0094] Among them, represents the output result of the hidden layer, is the smoke concentration data value, is the temperature data value, represents the weight corresponding to when the smoke concentration data value is activated, represents the weight corresponding to when the temperature data value is activated, is the hidden layer bias.

[0095] The output layer outputs:

[0096] t ;

[0097] Among them, t represents the output result of the output layer, represents the connection weight between the hidden layer and the output layer, h is the output of the hidden layer, represents the output layer bias. The output of the output layer is further processed using the normalization method, and the formula used for normalization is:

[0098] ;

[0099] Among them, is the value after normalization, t is the output result of the output layer, is the minimum value of t, is the maximum value of t.

[0100] Input the temperature prediction value and the smoke concentration prediction value into the pre-trained fire risk assessment parameter prediction model to obtain the fire risk assessment parameter prediction value of the area to be detected, that is, to obtain whether there is a fire source in the area to be detected and its risk fire level.

[0101] Specifically, a fire source parameter value of 1 indicates the presence of a fire source, while a value of 0 indicates the absence of a fire source. The fire risk level parameter represents the likelihood of a fire occurring and takes on ten hierarchical numerical values from 0 to 9. Among them, a fire risk level parameter value of 0 indicates that the likelihood of a fire occurring is basically non-existent, and values from 1 to 9 indicate that the likelihood of a fire occurring is possible, with the fire risk gradually increasing.

[0102] In step S15, based on the current fire protection facility status data and the predicted values of the fire risk assessment parameters, a fire protection facility performance evaluation value corresponding to the area to be detected is calculated.

[0103] Among them, the fire protection facilities include a fire sprinkler system, a fire alarm system, a fire hydrant system, an emergency lighting system, an emergency broadcast system, and a smoke control and exhaust system; the fire sprinkler system is an automatic fire extinguishing system usually installed on the ceiling of a building. When the ambient temperature reaches a certain threshold, the sprinkler head will automatically rupture and release water to extinguish the fire; the fire alarm system includes fire detectors and alarms, which are used to detect the smoke concentration, temperature, or flame at the initial stage of a fire and issue an alarm; the fire hydrant system is a fixed fire extinguishing facility that includes indoor and outdoor fire hydrants. The fire hydrant system provides high-pressure water sources for firefighters to connect hoses to extinguish fires; the emergency lighting system can provide necessary lighting when the normal power supply fails; the emergency broadcast system is a system used to transmit information to the people inside the building in case of an emergency; the smoke control and exhaust system includes natural ventilation and mechanical smoke exhaust systems, as well as passive fire protection measures such as fire doors and firewalls, aiming to control the smoke and heat inside the building to improve visibility and air quality during a fire. The fire protection facility status data includes the usage data, equipment temperature data, fault data, fire extinguishing agent flow data, and fire extinguishing agent pressure data of the fire protection facilities.

[0104] It should be noted that based on the usage data and fault data in the current fire protection facility status data, the fire extinguishing effectiveness and failure rate are calculated. Among them, the usage data includes the usage time and the number of successful fire extinguishments of the fire protection facilities, and the fault data includes the usage time and the number of faults of the fire protection facilities. Specifically, the failure rate is the frequency of fire protection facility failures, and the fire extinguishing effectiveness is the success rate of fire protection facilities in extinguishing fires. The calculation formula for the failure rate is:

[0105] ;

[0106] The calculation formula for the fire extinguishing effectiveness is:

[0107] ;

[0108] Among them, is the failure rate, T is the usage time, is the number of failures of the fire protection facilities, that is, the total number of failures of the fire protection facilities during the usage time; is the fire extinguishing effectiveness, is the number of successful fire extinguishments of the fire protection facilities, that is, the sum of the number of successful fire extinguishments of the fire protection facilities during the usage time.

[0109] Furthermore, a threshold set is set, specifically: usage time: 1000 hours, equipment temperature data: 60 °C, fire extinguishing agent flow rate data: 10 L / min, fire extinguishing agent pressure data: 5 bar, failure rate: 0.01, fire extinguishing effectiveness: 95%. If the usage time is less than 1000 hours, the usage time evaluation value is 1, otherwise it is -1; if the equipment temperature data is less than 60 °C, the equipment temperature evaluation value is 1, otherwise it is -1; if the fire extinguishing agent flow rate data is greater than 10 L / min, the fire extinguishing agent flow rate evaluation value is 1, otherwise it is -1; if the fire extinguishing agent pressure data is greater than 5 bar, the fire extinguishing agent pressure evaluation value is 1, otherwise it is -1; if the failure rate is less than 0.01, the failure evaluation value is 1, otherwise it is -1; if the fire extinguishing effectiveness is greater than 95%, the fire extinguishing effectiveness evaluation value is 1, otherwise it is -1. Input the smoke concentration prediction value and the temperature prediction value into the fire alarm system, and output an alarm response value. Specifically, set the response time threshold to 2 s. If the fire alarm system does not respond, the alarm response value is -1; if it responds within the set response time threshold, the alarm response value is 1; if it responds after exceeding the set response time threshold, the alarm response value is 0. The calculation formula for the performance evaluation value of the fire protection facilities is as follows:

[0110] ;

[0111] where X is the performance evaluation value of the fire protection facilities, are the alarm response value, usage time evaluation value, equipment temperature evaluation value, fire extinguishing agent flow rate evaluation value, fire extinguishing agent pressure evaluation value, failure evaluation value, and fire extinguishing effectiveness evaluation value in sequence.

[0112] In step S16, classify the performance evaluation value of the fire protection facilities according to a preset score threshold, and mark the fire protection facilities in the area to be detected according to the risk level classification result, completing the detection of the fire protection facilities in the area to be detected.

[0113] It should be noted that when performing the risk level classification, the risk level is classified into five levels: excellent, good, general, passing, and failing, and each level corresponds to a different range of performance evaluation values of the fire protection facilities.

[0114] Exemplarily, the preset score threshold can be set to , 2, 4, 6, etc. The specific correspondence is that when the performance evaluation value of the fire protection facilities is reached, the risk is marked as excellent; when , the risk is marked as good; when , the risk is marked as average; when , the risk is marked as passing; when , the risk is marked as failing.

[0115] In summary, the present invention provides an intelligent fire protection facilities detection method based on the Internet of Things, including:

[0116] Obtaining historical fire data; wherein, the historical fire data includes multiple fire event records, and each fire event record includes historical smoke concentration data, historical temperature data, historical fire protection facilities status data, and historical fire risk assessment parameters; obtaining the current smoke concentration data, current temperature data, and current fire protection facilities status data of the area to be detected; inputting the current smoke concentration data into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value; inputting the current temperature data into a pre-trained seasonal temperature prediction model to obtain a temperature prediction value; inputting the temperature prediction value and the smoke concentration prediction value into a pre-trained fire risk assessment parameter prediction model to obtain a fire risk assessment parameter prediction value for the area to be detected; calculating a performance evaluation value of the fire protection facilities corresponding to the area to be detected according to the current fire protection facilities status data and the fire risk assessment parameter prediction value; classifying the risk level of the performance evaluation value of the fire protection facilities according to a preset score threshold, and performing a risk mark on the fire protection facilities in the area to be detected according to the risk level classification result, thereby completing the detection of the fire protection facilities in the area to be detected.

[0117] The present invention provides an intelligent fire-fighting facility detection method based on the Internet of Things. First, a data acquisition module collects historical fire data, as well as smoke concentration data, temperature data, fire-fighting facility status data, and fire risk assessment parameters of the area to be detected. Then, the smoke concentration prediction module inputs the smoke concentration data of the area to be detected into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value. Similarly, the temperature prediction module inputs the temperature data into a seasonal temperature prediction model to obtain a temperature prediction value. Subsequently, the fire risk assessment parameter prediction module inputs the predicted temperature data and smoke concentration data of the area to be detected into a fire risk assessment parameter prediction model, thereby obtaining a fire risk assessment parameter prediction value corresponding to the area to be detected. Using these data, the fire-fighting facility performance evaluation value calculation module calculates a fire-fighting facility performance evaluation value according to the fire-fighting facility status data and fire risk assessment parameters of the area to be detected. Finally, the risk marking module classifies the fire-fighting facility performance evaluation value according to a preset score threshold, and marks the fire-fighting facilities in the area to be detected according to the risk level classification result, completing the detection work of the fire-fighting facilities.

[0118] The present invention provides an intelligent fire-fighting facility detection method and system based on the Internet of Things to solve the problems of limited comprehensiveness of data collection and accuracy of analysis results.

[0119] Referring to Figure 2 , the second embodiment of the present invention provides an intelligent fire-fighting facility detection system based on the Internet of Things, including:

[0120] A data acquisition module 100, which acquires the current smoke concentration data, current temperature data, and current fire-fighting facility status data of the area to be detected;

[0121] A smoke concentration prediction module 101, which is used to input the current smoke concentration data into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value;

[0122] A temperature prediction module 102, which is used to input the current temperature data into a pre-trained seasonal temperature prediction model to obtain a temperature prediction value;

[0123] A fire risk assessment parameter prediction module 103, which is used to input the temperature prediction value and the smoke concentration prediction value into a pre-trained fire risk assessment parameter prediction model to obtain a fire risk assessment parameter prediction value of the area to be detected;

[0124] A fire-fighting facility performance evaluation value calculation module 104, which is used to calculate a fire-fighting facility performance evaluation value corresponding to the area to be detected according to the current fire-fighting facility status data and the fire risk assessment parameter prediction value;

[0125] A risk marking module 105 is configured to classify the risk levels of the performance evaluation values of the fire-fighting facilities according to a preset score threshold, and mark the fire-fighting facilities in the area to be detected according to the risk level classification result, thereby completing the detection of the fire-fighting facilities in the area to be detected.

[0126] Among them, the smoke concentration prediction model, the seasonal temperature prediction model, and the fire risk assessment parameter prediction model are trained based on historical fire data. The historical fire data includes multiple fire event records, and each fire event record includes historical smoke concentration data, historical temperature data, historical fire-fighting facility status data, and historical fire risk assessment parameters.

[0127] It should be noted that the intelligent fire-fighting facility detection system based on the Internet of Things provided in the embodiments of the present invention is used to execute all the process steps of the method for detecting intelligent fire-fighting facilities based on the Internet of Things in the above embodiments. The working principles and beneficial effects of the two correspond one by one, so they will not be elaborated here.

[0128] The embodiments of the present invention also provide an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above embodiments of the method for detecting intelligent fire-fighting facilities based on the Internet of Things are implemented, such as Figure 1 the step S11 shown. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiments are implemented, such as the temperature prediction module.

[0129] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device.

[0130] The electronic device can be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device, and do not constitute a limitation to the electronic device. It may include more or fewer components than the above, or combine certain components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0131] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects all parts of the entire electronic device through various interfaces and circuits.

[0132] The memory can be used to store the computer programs and / or modules. The processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and by calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0133] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0134] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative work.

[0135] The specific embodiments described above have further elaborated on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting intelligent fire-fighting facilities based on the Internet of Things, characterized in that: include: Obtain the current smoke concentration data, current temperature data and current fire-fighting facility status data of the area to be detected; Inputting the current smoke concentration data into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value; Inputting the current temperature data into a pre-trained seasonal temperature prediction model to obtain a temperature prediction value; Inputting the temperature prediction value and the smoke concentration prediction value into a pre-trained fire risk assessment parameter prediction model to obtain the fire risk assessment parameter prediction value of the area to be detected; Calculate the fire protection facility performance evaluation value corresponding to the area to be detected based on the current fire protection facility status data and the fire risk assessment parameter prediction value; The fire protection facility performance evaluation value is classified into risk levels according to a preset score threshold, and the fire protection facilities in the area to be inspected are risk marked according to the risk level classification result, so as to complete the inspection of the fire protection facilities in the area to be inspected; The smoke concentration prediction model, the seasonal temperature prediction model and the fire risk assessment parameter prediction model are obtained by training based on historical fire data, wherein the historical fire data includes multiple fire event records, each of which includes historical smoke concentration data, historical temperature data, historical firefighting facility status data and historical fire risk assessment parameters; The training process of the smoke concentration prediction model includes: Performing data cleaning on the historical smoke concentration data to obtain first smoke concentration data; Set a set of K values, and use the K-means method to select the initial cluster center at each K value; Assigning each smoke density data point of the first smoke density data to the nearest cluster center to form K clusters, updating the cluster center of each cluster, calculating the mean of all points in the cluster, and obtaining a clustering result when the change of the cluster center is less than a set threshold; wherein the clustering result is the smoke density data of K regions; The clustering result corresponding to each K value is evaluated using the silhouette coefficient, and the clustering result corresponding to the K value with the best clustering effect is selected as the second smoke density data; wherein the second smoke density data is the smoke density data of multiple regions; The process of using the silhouette coefficient for evaluation is as follows: calculate the silhouette coefficients of all data points, then take the average, and select the K value with the largest average silhouette coefficient as the optimal number of clusters; for each data point i, the calculation formula of the silhouette coefficient is as follows: ； in, is the silhouette coefficient of the ith data point, is the average distance within the cluster, that is, the average distance between the i-th data point and all other data points in the same cluster, is the average distance between clusters, that is, the average distance between the i-th data point and all the points in its nearest cluster; The training process of the seasonal temperature prediction model includes: Dividing the historical temperature data by season to obtain seasonal fire data; The seasonal fire data include spring fire data, summer fire data, autumn fire data and winter fire data; According to the set time period, the average temperature of the area included in the seasonal fire data in each time period is calculated to obtain a seasonal average temperature set; The seasonal average temperature set includes a spring average temperature set, a summer average temperature set, an autumn average temperature set and a winter average temperature set; Based on the seasonal average temperature set, the LSTM neural network model is trained, and when the number of training rounds reaches a maximum preset number, the training is completed to obtain a seasonal temperature prediction model; The seasonal temperature prediction model includes a spring temperature prediction model, a summer temperature prediction model, an autumn temperature prediction model and a winter temperature prediction model; Among them, the fire risk assessment parameter prediction model includes an input layer, a hidden layer and an output layer. The number of neurons in the input layer is set to 2, 1 neuron is used to receive smoke concentration data, and 1 neuron is used to receive temperature data; the number of neurons in the output layer is set to 2, 1 neuron is used to output whether there is a fire source parameter in the building, and 1 neuron is used to output the fire risk level parameter; the neurons in the hidden layer and the neurons in the output layer are respectively established with the activation function sigmoid function, and the connection weights between the neurons are initialized with random values.

2. The method for detecting intelligent fire-fighting facilities based on the Internet of Things according to claim 1 is characterized in that: After the first smoke density data is classified by using a clustering algorithm to obtain the second smoke density data, the method includes: Performing statistical analysis on the smoke concentration data in each area of ​​the second smoke concentration data according to a set time period to obtain an average smoke concentration set; wherein the average smoke concentration set includes the average smoke concentration in each time period; Based on the average smoke concentration set, the decision tree model is trained. When the number of training rounds reaches a maximum preset number of rounds, the training is completed to obtain a smoke concentration prediction model.

3. The method for detecting intelligent fire-fighting facilities based on the Internet of Things according to claim 2 is characterized in that: The training process of the fire risk assessment parameter prediction model includes: Based on the average smoke concentration set, the seasonal average temperature set and the historical fire risk assessment parameters, the BP neural network model is trained, and the training is completed when the number of training rounds reaches a maximum preset number of rounds, thereby obtaining a fire risk assessment parameter prediction model; The historical fire risk assessment parameters include a parameter of whether there is a fire source in the building and a fire risk level parameter, and the fire risk level parameter is expressed as the possibility of fire occurrence.

4. The method for detecting intelligent fire-fighting facilities based on the Internet of Things according to claim 1 is characterized in that: The calculating, based on the current fire protection facility status data and the fire risk assessment parameter prediction value, a fire protection facility performance assessment value corresponding to the area to be detected includes: The fire-fighting facilities include a fire sprinkler system, a fire alarm system, a fire hydrant system, an emergency lighting system, an emergency broadcast system, and a smoke exhaust system; the current fire-fighting facility status data includes usage data, equipment temperature data, fault data, fire-extinguishing agent flow data, and fire-extinguishing agent pressure data of the fire-fighting facilities; Calculate the fire extinguishing effectiveness and failure rate according to the usage data and failure data in the current fire-fighting facility status data; wherein the usage data includes the usage time and the number of successful fire-fighting of the fire-fighting facility, and the failure data includes the usage time and the number of failures of the fire-fighting facility; According to the set threshold value set, the use time, the equipment temperature data, the fire extinguishing agent flow data, the fire extinguishing agent pressure data, the failure rate and the fire extinguishing effectiveness are evaluated respectively to obtain a use time evaluation value, an equipment temperature evaluation value, a fire extinguishing agent flow evaluation value, a fire extinguishing agent pressure evaluation value, a failure evaluation value and a fire extinguishing effectiveness evaluation value; Inputting the predicted smoke concentration value and the predicted temperature value into the fire alarm system, and outputting an alarm response value; The calculation formula of the fire protection facility performance evaluation value is as follows: ； Among them, X is the performance evaluation value of fire protection facilities, They are alarm response value, usage time evaluation value, equipment temperature evaluation value, fire extinguishing agent flow evaluation value, fire extinguishing agent pressure evaluation value, fault evaluation value and fire extinguishing effectiveness evaluation value.

5. The method for detecting intelligent fire-fighting facilities based on the Internet of Things according to claim 4 is characterized in that: The calculating of fire extinguishing effectiveness and failure rate according to the usage data and failure data in the current fire-fighting facility status data includes: The failure rate is the frequency of fire-fighting facility failures, and the fire-fighting effectiveness is the fire-fighting success rate of the fire-fighting facilities. The calculation formula of the failure rate is: ； The calculation formula for the fire extinguishing effectiveness is: ； in, is the failure rate, For usage time, is the number of fire-fighting facility failures, that is, the total number of fire-fighting facility failures during the use time; is the effectiveness of fire extinguishing, It is the number of successful fire extinguishing times of fire-fighting facilities, that is, the sum of the successful fire extinguishing times of fire-fighting facilities during the use time.

6. An intelligent fire-fighting facility detection system based on the Internet of Things, characterized in that: The method for detecting intelligent fire-fighting facilities based on the Internet of Things according to any one of claims 1 to 5 comprises: The data acquisition module acquires the current smoke concentration data, current temperature data and current fire-fighting facility status data of the area to be detected; A smoke concentration prediction module, used for inputting the current smoke concentration data into a pre-trained smoke concentration prediction model to obtain a smoke concentration prediction value; A temperature prediction module is used to input the current temperature data into a pre-trained seasonal temperature prediction model to obtain a temperature prediction value; A fire risk assessment parameter prediction module, used for inputting the temperature prediction value and the smoke concentration prediction value into a pre-trained fire risk assessment parameter prediction model to obtain the fire risk assessment parameter prediction value of the area to be detected; A fire protection facility performance evaluation value calculation module, used to calculate the fire protection facility performance evaluation value corresponding to the area to be detected according to the current fire protection facility status data and the fire risk assessment parameter prediction value; A risk marking module is used to classify the fire protection facility performance evaluation value into risk levels according to a preset score threshold, and to mark the fire protection facilities in the area to be inspected according to the risk level classification result, so as to complete the inspection of the fire protection facilities in the area to be inspected; Among them, the smoke concentration prediction model, the seasonal temperature prediction model and the fire risk assessment parameter prediction model are trained based on historical fire data, and the historical fire data contains multiple fire event records, each fire event record includes historical smoke concentration data, historical temperature data, historical fire protection facility status data and historical fire risk assessment parameters.

7. An electronic device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the intelligent fire protection facility detection method based on the Internet of Things as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the intelligent fire-fighting facility detection method based on the Internet of Things as described in any one of claims 1 to 5.

Images