Intelligent fire safety auxiliary decision-making method

Abstract

This invention discloses a smart fire safety auxiliary decision-making method. The method includes constructing a three-dimensional map model using three-dimensional functions; displaying the distribution of water sources and fire-fighting equipment around the monitoring area on the three-dimensional map and performing aggregate calculations using a distribution statistical model; when a fire occurs, acquiring data from detection sensors, using intelligent and precise address matching and GPS location positioning, and locating the fire site on the three-dimensional map using an automatic positioning model; automatically analyzing various fire-fighting data resources around the fire site and displaying them on the three-dimensional map, calculating the shortest rescue path via road network and displaying it on the three-dimensional map, and transmitting the rescue route map to the mobile devices of rescue personnel via wireless network for easy viewing; and employing artificial intelligence algorithms to automatically calculate the fire hazard data of various types of buildings and predict the approximate fire loss for each fire, providing crucial decision-making support for commanders.

Description

Technical Field

[0001] This invention relates to the field of fire safety, and in particular to a smart fire safety auxiliary decision-making method. Background Technology

[0002] With the rapid development of society and the economy, fire safety has become an increasingly important issue, serving as a crucial prerequisite for ensuring the safety of people's lives and property. As my country's market economy continues to develop, the uncertainties affecting fire safety are increasing, and fire risks are becoming more prominent. Therefore, the scientific management and evaluation of fire safety has become a consensus and a common need across all sectors of society. However, traditional fire safety evaluation methods primarily involve reviewing the legality of fire protection facilities, fire safety management systems, fire safety operating procedures, and fire safety inspection records of social units, as well as conducting on-site inspections and qualitative evaluations of the integrity of fire protection facilities. These evaluations only reflect the integrity of fire protection facilities at the time of on-site inspection. After the supervisors or fire evaluation personnel leave, there is still a lack of effective monitoring and evaluation methods to determine whether the facilities are still in good working order. In other words, fire safety evaluation that only focuses on the supervision of the facilities themselves often fails to achieve the desired effect. Furthermore, the lack of on-site management is also one of the main causes of fire safety accidents.

[0003] Patent publication number CN202383739U discloses a fire safety management system, including a fire safety data server, a fire safety management terminal, and a fire safety query terminal. The fire safety management terminal and the fire safety query terminal are connected to the server via a network. The fire safety management terminal includes independent terminals for safety training management, safety accident management, accident investigation management, accident reward and punishment management, work experience management, and safety history management. This utility model fire safety management system adopts digital management, sets up a fire safety data server, and configures fire safety management terminals in relevant business and personnel departments. The fire safety management terminals can read and write data stored on the fire safety data server, enabling real-time data generation and data resource sharing. Each fire safety query terminal can query data stored on the fire safety server at any time, improving work efficiency, facilitating scientific management, and realizing digital management for fire safety prevention and handling.

[0004] Patent CN105976116B discloses a method and system for dynamic fire safety evaluation based on the Internet of Things. The method includes real-time acquisition of fire safety data, transmission of the acquired fire safety data via network, and analysis of the data to ultimately obtain the fire safety evaluation result. This invention can monitor the fire personnel system and its implementation, as well as fire-fighting facilities in real time, and use the monitoring results as dynamic fire safety evaluation indicators. This can effectively improve the allocation capacity of fire-fighting resources and the efficiency of fire safety supervision in social units, thereby preventing and reducing fire accidents and ultimately protecting life and property. In use, this invention can periodically generate dynamic fire safety evaluation reports for social units within the jurisdiction of fire supervision departments, and can also periodically generate health status evaluation reports for fire-fighting facilities, enabling the maintenance and management of fire-fighting facilities and ensuring their integrity and effectiveness. Summary of the Invention

[0005] In order to overcome the shortcomings and deficiencies of existing technologies, this invention provides a smart fire safety auxiliary decision-making method.

[0006] The technical solution adopted in this invention is that the method includes the following steps:

[0007] Step S1: Construct a 3D map model using 3D functions;

[0008] Step S2: Display the distribution of water sources and fire-fighting equipment around the monitoring area on the 3D map and perform ensemble calculations using a distribution statistical model;

[0009] Step S3: When a fire occurs, acquire data from the detection sensors, use intelligent and accurate address matching and GPS location positioning, and use an automatic positioning model to locate the fire location on a 3D map;

[0010] Step S4: Automatically analyze various fire protection data resources around the fire location and display them on a 3D map, including:

[0011] Step A1: Establish a multi-source information set function to calculate the distribution of water sources around the fire, water source information and distance from the fire point, distribution of key units in the surrounding area, distribution of major hazard sources, and detailed information on the distribution of social linkage units and combat support points;

[0012] Step A2: Use meteorological functions to display on-site meteorological information, including weather conditions, wind direction, wind force, temperature, and humidity.

[0013] Step A3: Remote command personnel analyze and make decisions to formulate a rescue plan and calculate the feasibility of the rescue plan;

[0014] Step S5: Calculate the shortest rescue route on the road network and display it on a 3D map. The rescue route map can be sent to the mobile devices of rescuers via wireless network for easy viewing.

[0015] Step S6: Using artificial intelligence algorithms, by inputting fire type, burned area, and combustible material information, the system automatically calculates fire hazard data, fire spread status, and one-click dispatching schemes for various types of buildings. It can also combine data analysis models to calculate the approximate fire loss prediction for each fire, providing important decision-making support for command personnel.

[0016] The three-dimensional function is expressed as follows:

[0017]

[0018] Among them, A b Let represent the coordinate value of any coordinate axis in three-dimensional space, n represent any point on the coordinate axis, B represent the total number of points on the coordinate axis, d(n) represent the scaling factor of the coordinates, e represent the natural constant, and H(f) represent the coordinate values ​​of any coordinate axis in three-dimensional space. n H(f) represents the true value of the coordinates. m ) represents the coordinate error value, k represents a constant, and H(m) represents the coordinate measurement error correction function.

[0019] The distribution statistical model is expressed as follows:

[0020]

[0021] in, This represents a statistical function for water sources and fire-fighting equipment. This represents the collection of existing water sources and fire-fighting equipment, where q1 represents the rate of change in the quantity of water, t1 represents the time it takes for the quantity of water to change, and z... x Represents the water source distribution function. q2 represents the increase in the quantity of water resources, t2 represents the rate of change in the quantity of fire-fighting equipment, and z represents the time it takes for the quantity of fire-fighting equipment to change. w Represents the distribution function of fire protection equipment. This indicates an increase in the quantity of fire-fighting equipment.

[0022] The automatic positioning model is expressed as follows:

[0023]

[0024] Where ΔN represents the fire location matrix, R ψ N represents the number of fire locations. δ R represents the location of a single fire site. λ N represents the number of false fire locations. εp1 represents the location of the false fire, p2 represents the probability of a false fire, and p1 represents the probability of a real fire.

[0025] The multi-source information set function is expressed as follows:

[0026] Y d =R j -ζ·Q

[0027] Among them, Y d R represents a multi-source information matrix. j Let ζ represent the true value matrix of multi-source information, ζ represent the weight of the information, and Q represent the address location matrix of multi-source information.

[0028] The meteorological function is expressed as follows:

[0029] E d+1 =E bji -I·[P·R fkd -E d ]

[0030] Among them, E d+1 E represents the set of meteorological data at the current moment. bji R represents the set of meteorological data from the previous moment. fkd The matrix represents the impact range of different fire levels, where I represents the type matrix of meteorological data, P represents the weight of different meteorological data on the impact of fire, and E represents the impact range of different fire levels. d Indicates the predicted value of the fire's impact;

[0031] The feasibility of the rescue plan is expressed as:

[0032] K a+1 =J vsj ×i gf ×sin(ξu)+K a

[0033] Among them, K a+1 J represents the feasibility of the rescue plan at the current moment. vsj This represents the coefficient matrix affecting the rescue plan, i gf Let ξ represent the error factor of the rescue plan, ξ represent the number of times different rescue plans were used, u represent the proportion of human factors in the rescue plan, and K represent the error factor of the rescue plan. a This indicates the feasibility of the rescue plan at the previous moment.

[0034] The expression for calculating the shortest rescue path in the road network is:

[0035]

[0036] Where F(c) represents the shortest path function, and U represents the shortest path distance. V(c) represents the accessibility of the shortest path, O(c) represents the estimated travel time of the shortest path, m(c) represents the estimated travel speed of the shortest path, and m(c) represents the calculation error of the shortest path.

[0037] The approximate fire loss prediction for each fire is expressed as follows:

[0038]

[0039] Where D(x) represents the fire loss prediction function, x o Indicates the start time of the fire, x s Indicates the end time of the fire, u r (x) represents the probability of economic loss for different objects, W represents the degree of damage to the object, u(x) represents the economic conversion factor for the object, and p r (x) represents the probability of personal injury, G represents the degree of personal injury, p(x) represents the personal economic conversion factor, and dx represents the integral operation.

[0040] Beneficial effects:

[0041] This invention proposes a smart fire safety auxiliary decision-making method. This method monitors fires in real time using real-time 3D map data, enabling timely and accurate detection of fire points. It also uses the fusion of multiple algorithms and models to guide rescue efforts, providing highly operable rescue plans and accurate rescue routes for rescue personnel. The proposed algorithms and models are based on existing theories and foundations, are easy to understand, and have high application value, thus ensuring the safe and effective conduct of firefighting operations. Attached Figure Description

[0042] Figure 1 This is a first flowchart of the method of the present invention;

[0043] Figure 2 This is the second flowchart of the method of the present invention. Detailed Implementation

[0044] It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other. The following describes the application in further detail with reference to the accompanying drawings and specific embodiments.

[0045] like Figure 1 As shown, a smart fire safety auxiliary decision-making method includes the following steps:

[0046] Step S1: Construct a 3D map model using 3D functions;

[0047] The three-dimensional function is related to the coordinate values ​​of any coordinate axis in three-dimensional space, any point on the coordinate axis, the total number of points on the coordinate axis, the scaling factor of the coordinate, the natural constant, the true value of the coordinate, the error value of the coordinate, the constant k, and the error correction function of the coordinate measurement.

[0048] Step S2: Display the distribution of water sources and fire-fighting equipment around the monitoring area on the 3D map and perform ensemble calculations using a distribution statistical model;

[0049] The distribution statistical model is related to the statistical functions of water sources and fire-fighting equipment, the set of existing water sources and fire-fighting equipment, the rate of change of the quantity of water sources, the time of change of the quantity of water sources, the water source distribution function, the increment of the quantity of water sources, the rate of change of the quantity of fire-fighting equipment, the time of change of the quantity of fire-fighting equipment, the fire-fighting equipment distribution function, and the increment of the quantity of fire-fighting equipment.

[0050] Step S3: When a fire occurs, acquire data from the detection sensors, use intelligent and accurate address matching and GPS location positioning, and use an automatic positioning model to locate the fire location on a 3D map;

[0051] The automatic location model is related to the fire location matrix, the number of fire locations, the location of a single fire location, the number of false fire locations, the location of false fire locations, the probability of false fires, and the probability of actual fires.

[0052] like Figure 2 As shown, step S4: Automatically analyze various fire protection data resources around the fire location and display them on a 3D map, including:

[0053] Step A1: Establish a multi-source information set function to calculate the distribution of water sources around the fire, water source information and distance from the fire point, distribution of key units in the surrounding area, distribution of major hazard sources, and detailed information on the distribution of social linkage units and combat support points;

[0054] The multi-source information set function is related to the multi-source information matrix, the true value matrix of the multi-source information, the weight of the information, and the address location matrix of the multi-source information.

[0055] Step A2: Use meteorological functions to display on-site meteorological information, including weather conditions, wind direction, wind force, temperature, and humidity.

[0056] The meteorological function is related to the current meteorological data set, the previous meteorological data set, the meteorological data type matrix, the weight of different meteorological data on the fire impact, the impact range of different fire levels, and the predicted value of the fire impact.

[0057] Step A3: Remote command personnel analyze and make decisions to formulate a rescue plan and calculate the feasibility of the rescue plan;

[0058] The feasibility of a rescue plan is related to the feasibility of the rescue plan at the current moment, the coefficient matrix affecting the rescue plan, the error factor of the rescue plan, the number of times different rescue plans are used, the proportion of human factors in the rescue plan, and the feasibility of the rescue plan at the previous moment.

[0059] Step S5: Calculate the shortest rescue route on the road network and display it on a 3D map. The rescue route map can be sent to the mobile devices of rescuers via wireless network for easy viewing.

[0060] The calculation of the shortest rescue route on the road network is related to the shortest path function, the shortest path distance, the shortest path accessibility, the shortest path estimated travel time, the shortest path estimated travel speed, and the calculation error of the shortest path.

[0061] Step S6: Using artificial intelligence algorithms, by inputting fire type, burned area, and combustible material information, the system automatically calculates fire hazard data, fire spread status, and one-click dispatch plans for various types of buildings, including personnel type and quantity, vehicle type and quantity, fire extinguishing equipment, and fire extinguishing methods. It can also combine data analysis models to calculate the approximate fire loss prediction for each fire, providing important decision-making support for command personnel.

[0062] The approximate fire loss prediction for each fire is related to the fire loss prediction function, the fire start time, the fire end time, the probability of economic loss for different objects, the degree of damage to objects, the economic conversion factor for objects, the probability of personal injury, the degree of personal injury, and the economic conversion factor for personal injury.

[0063] A three-dimensional function, expressed as:

[0064]

[0065] Among them, A b Let represent the coordinate value of any coordinate axis in three-dimensional space, n represent any point on the coordinate axis, B represent the total number of points on the coordinate axis, d(n) represent the scaling factor of the coordinates, e represent the natural constant, and H(f) represent the coordinate values ​​of any coordinate axis in three-dimensional space. n H(f) represents the true value of the coordinates. m ) represents the coordinate error value, k represents a constant, and H(m) represents the coordinate measurement error correction function.

[0066] The distribution statistical model is expressed as follows:

[0067]

[0068] in, This represents a statistical function for water sources and fire-fighting equipment. This represents the collection of existing water sources and fire-fighting equipment, where q1 represents the rate of change in the quantity of water, t1 represents the time it takes for the quantity of water to change, and z... x Represents the water source distribution function. q2 represents the increase in the quantity of water resources, t2 represents the rate of change in the quantity of fire-fighting equipment, and z represents the time it takes for the quantity of fire-fighting equipment to change. w Represents the distribution function of fire protection equipment. This indicates an increase in the quantity of fire-fighting equipment.

[0069] The automatic localization model is expressed as follows:

[0070]

[0071] Where ΔN represents the fire location matrix, R ψ N represents the number of fire locations. δ R represents the location of a single fire site. λ N represents the number of false fire locations. ε p1 represents the location of the false fire, p2 represents the probability of a false fire, and p1 represents the probability of a real fire.

[0072] The function for collecting multi-source information is expressed as follows:

[0073] Y d =R j -ζ·Q

[0074] Among them, Y d R represents a multi-source information matrix. j Let ζ represent the true value matrix of multi-source information, ζ represent the weight of information, and Q represent the address location matrix of multi-source information;

[0075] The meteorological function is expressed as follows:

[0076] E d+1 =E bji -I·[P·R fkd -E d ]

[0077] Among them, E d+1 E represents the set of meteorological data at the current moment. bji R represents the set of meteorological data from the previous moment. fkd The matrix represents the impact range of different fire levels, where I represents the type matrix of meteorological data, P represents the weight of different meteorological data on the impact of fire, and E represents the impact range of different fire levels. d Indicates the predicted value of the fire's impact;

[0078] The feasibility of the rescue plan is expressed as:

[0079] K a+1 =Jvsj ×i gf ×sin(ξu)+K a

[0080] Among them, K a+1 J represents the feasibility of the rescue plan at the current moment. vsj This represents the coefficient matrix affecting the rescue plan, i gf Let ξ represent the error factor of the rescue plan, ξ represent the number of times different rescue plans were used, u represent the proportion of human factors in the rescue plan, and K represent the error factor of the rescue plan. a This indicates the feasibility of the rescue plan at the previous moment.

[0081] The shortest rescue path for the road network is calculated using the following expression:

[0082]

[0083] Where F(c) represents the shortest path function, and U represents the shortest path distance. V(c) represents the accessibility of the shortest path, O(c) represents the estimated travel time of the shortest path, m(c) represents the estimated travel speed of the shortest path, and m(c) represents the calculation error of the shortest path.

[0084] The approximate fire loss prediction for each fire is expressed as follows:

[0085]

[0086] Where D(x) represents the fire loss prediction function, x o Indicates the start time of the fire, x s Indicates the end time of the fire, u r (x) represents the probability of economic loss for different objects, W represents the degree of damage to the object, u(x) represents the economic conversion factor for the object, and p r (x) represents the probability of personal injury, G represents the degree of personal injury, p(x) represents the personal economic conversion factor, and dx represents the integral operation.

[0087] This invention proposes a smart fire safety auxiliary decision-making method. This method monitors fires in real time using real-time 3D map data, enabling timely and accurate detection of fire points. It also uses the fusion of multiple algorithms and models to guide rescue efforts, providing highly operable rescue plans and accurate rescue routes for rescue personnel. The proposed algorithms and models are based on existing theories and foundations, are easy to understand, and have high application value, thus ensuring the safe and effective conduct of firefighting operations.

[0088] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart fire safety auxiliary decision-making method, characterized in that... The method includes the following steps: Step S1: Construct a 3D map model using 3D functions; Step S2: Display the distribution of water sources and fire-fighting equipment around the monitoring area on the 3D map and perform ensemble calculations using a distribution statistical model; Step S3: When a fire occurs, acquire data from the detection sensors, use intelligent and accurate address matching and GPS location positioning, and use an automatic positioning model to locate the fire location on a 3D map; Step S4: Automatically analyze various fire protection data resources around the fire location and display them on a 3D map, including: Step A1: Establish a multi-source information set function to calculate the distribution of water sources around the fire, water source information and distance from the fire point, distribution of key units in the surrounding area, distribution of major hazard sources, and detailed information on the distribution of social linkage units and combat support points; Step A2: Use meteorological functions to display on-site meteorological information, including weather conditions, wind direction, wind force, temperature, and humidity. Step A3: Remote command personnel analyze and make decisions to formulate a rescue plan and calculate the feasibility of the rescue plan; Step S5: Calculate the shortest rescue route on the road network and display it on a 3D map. The rescue route map can be sent to the mobile devices of rescuers via wireless network for easy viewing. Step S6: Using artificial intelligence algorithms, by inputting fire type, burned area, and combustible material information, the system automatically calculates fire hazard data, fire spread status, and one-click dispatch schemes for various types of buildings. It can also combine data analysis models to calculate the predicted loss for each fire, providing important decision-making support for command personnel. The multi-source information set function is expressed as follows: in, Represents a multi-source information matrix. This represents the true value matrix of multi-source information. The weights of the information are represented by Q, which represents the address location matrix of the multi-source information. The meteorological function is expressed as follows: in, This represents the set of meteorological data at the current moment. This represents the set of meteorological data from the previous moment. Indicates the impact range of different fire levels. I A matrix representing the types of meteorological data. P This indicates the weight of different meteorological data on the impact of fire. Indicates the predicted value of the fire's impact; The feasibility of the rescue plan is expressed as: in, Indicates the feasibility of the rescue plan at the current moment. This represents the coefficient matrix that influences the rescue plan. This represents the error factor of the rescue plan. Indicates the number of times different rescue plans were used. This indicates the proportion of human factors in the rescue plan. This indicates the feasibility of the rescue plan at the previous moment.

2. The intelligent fire safety auxiliary decision-making method as described in claim 1, characterized in that, The three-dimensional function is expressed as follows: in, Let n represent the coordinate value of any point on the coordinate axis in three-dimensional space, and B represent the total number of points on the coordinate axis. This indicates the scaling factor of the coordinates, and e represents the natural constant. Represents the true value of the coordinates. This represents the error value of the coordinates, and k represents a constant. This represents the error correction function for coordinate measurement.

3. The intelligent fire safety auxiliary decision-making method as described in claim 1, characterized in that, The distribution statistical model is expressed as follows: in, This represents a statistical function for water sources and fire-fighting equipment. This indicates the collection of existing water sources and fire-fighting equipment. Indicates the rate of change in the quantity of water resources. Indicates the time period during which the quantity of water resources changes. Represents the water source distribution function. This indicates an increase in the quantity of water resources. This indicates the rate of change in the number of fire-fighting equipment. Indicates the time period during which the quantity of fire-fighting equipment changed. Represents the distribution function of fire protection equipment. This indicates an increase in the quantity of fire-fighting equipment.

4. The intelligent fire safety auxiliary decision-making method as described in claim 1, characterized in that, The automatic positioning model is expressed as follows: in, A matrix representing the locations of fires. Indicates the number of fire locations. Indicates the location of a single fire site. Indicates the number of false fire locations. Indicates the location of the falsely reported fire. Indicates the probability of a false fire alarm. This represents the actual probability of a fire.

5. The intelligent fire safety auxiliary decision-making method as described in claim 1, characterized in that, The expression for calculating the shortest rescue path in the road network is: in, Represents the shortest path function. U Indicates the shortest path distance. Indicates the accessibility of the shortest path. This represents the estimated travel time of the shortest path. This represents the estimated speed of the shortest path. This represents the error in calculating the shortest path.

6. The intelligent fire safety auxiliary decision-making method as described in claim 1, characterized in that, The expression for each fire loss prediction is: in, This represents the fire loss prediction function. Indicates the time the fire started. Indicates the end time of the fire. Represents the probability of economic loss for different objects. Indicates the degree of damage to an object. This represents the economic conversion factor for the object. Indicates the probability of personal injury. Indicates the degree of personal injury. This represents the personal economic conversion factor. This indicates integration.

Images