Search

CN-115408941-B - Fire intelligent early warning system based on multisource data

CN115408941BCN 115408941 BCN115408941 BCN 115408941BCN-115408941-B

Abstract

The invention discloses a fire intelligent early warning system based on multi-source data, relates to the technical field of fire early warning, and solves the technical problems that in the prior art, in the prediction of fire spreading, the accuracy of the fire spreading cannot be ensured and the fire intelligent early warning system cannot be applied to various fire early warning scenes due to single considered influencing factors; according to the invention, in the process of acquiring the fire spreading speed through the speed prediction model, the target area is divided into a plurality of subareas with different inflammable degrees according to the area condition data, the fire spreading speed is predicted by taking the subareas as a basic unit, the accuracy of the fire spreading speed is ensured, and the accuracy of the fire spreading prediction is improved.

Inventors

  • XIANG YU
  • LI YUN

Assignees

  • 李云

Dates

Publication Date
20260508
Application Date
20220826

Claims (6)

  1. 1. The utility model provides a fire condition intelligent early warning system based on multisource data, includes central analysis module to and data display module and a plurality of edge analysis module that are connected with it, and edge analysis module is connected its characterized in that with data acquisition equipment: The edge analysis module is used for collecting basic data through a data collecting device connected with the edge analysis module when a fire occurs, wherein the basic data comprises environment data and area condition data, and Performing data processing on the basic data to obtain original data, and sending the original data to the central analysis module, wherein the data processing comprises data screening and data integration; the central analysis module is used for identifying a target area according to the area condition data and dividing the target area into a plurality of subareas according to the identification result, wherein the target area comprises a fire disaster area and Simulating a fire spreading process based on the fire spreading speed, and visually displaying the fire spreading process through a data display module; the central analysis module identifies the material type in the target area, divides the target area into a plurality of subareas according to the identification result, and comprises the following steps: Acquiring the zone condition data corresponding to a target zone, wherein the target zone is generated according to the expansion of a set area according to a fire occurrence position; identifying a plurality of material types in the regional condition data, and dividing the target region into a plurality of subareas according to the material types, wherein the material types in the subareas are consistent or the inflammability grades are consistent; the hub analysis module determines the fire spread rates for a number of sub-regions based on raw data, including: splicing or laminating the original data based on a target area to obtain target data; extracting model input data corresponding to the subareas from the target data, wherein the model input data comprises environment data and area condition data corresponding to the subareas; And inputting the model input data into a speed prediction model to obtain the output fire spreading speed, wherein the speed prediction model is constructed based on an artificial intelligent model.
  2. 2. The intelligent fire early warning system based on multi-source data according to claim 1, wherein the central analysis module is respectively in communication and/or electrical connection with the data display module and a plurality of the edge analysis modules, and the data display module is used for data display; The edge analysis module is configured according to a configuration rule, and the edge analysis module is connected with the data acquisition equipment, wherein the configuration rule comprises configuration based on an area or configuration based on a data type.
  3. 3. The intelligent fire early warning system based on multi-source data according to claim 2, wherein the central analysis module generates a data acquisition signal before the edge analysis module acquires the basic data, and sends the data acquisition signal to the edge analysis module, comprising: Receiving multi-source data, wherein the multi-source data comprises video data sent by an intelligent terminal and a watchtower, and the intelligent terminal comprises a mobile phone and a computer; Identifying and analyzing the video data based on an image analysis technology, marking fire levels according to analysis results, and judging whether to generate a data acquisition signal based on the fire levels; And when the fire grade is greater than a grade threshold, generating a data acquisition signal and transmitting the data acquisition signal to a plurality of edge analysis modules, wherein the grade threshold is set according to experience.
  4. 4. The intelligent fire early warning system based on multi-source data according to claim 3, wherein the edge analysis module performs data processing on the basic data to obtain the raw data, and the method comprises the following steps: Extracting the environment data in the basic data, and rendering and generating an environment distribution image based on the environment data and the configuration rule, wherein the environment data comprises wind power, wind direction, temperature or humidity; Extracting the region condition data in the basic data, and rendering based on the region condition data and the configuration rule to generate a region condition distribution image, wherein the region condition data comprises DEM data and material type data; And carrying out matching processing on the environment distribution image and the area condition distribution image to obtain original data.
  5. 5. The multi-source data based fire intelligent pre-warning system of claim 1, wherein combining the artificial intelligence model with standard training data trains to obtain the speed prediction model, comprising: standard training data is obtained, wherein the standard training data is the corresponding fire spreading speed of various material types in different fire simulation environments; and expanding the standard training data by an interpolation method, and training the constructed artificial intelligent model by the expanded data to obtain the speed prediction model.
  6. 6. The intelligent fire early warning system based on multi-source data according to claim 5, wherein the central analysis module simulates and acquires a fire spreading process of a target area according to fire spreading speeds of a plurality of subareas, and displays the fire spreading process through the data display module, and And acquiring corresponding fire spreading time based on the set boundary calculation or acquiring corresponding fire spreading area based on the set time calculation, and carrying out resource scheduling according to the fire spreading time or the fire spreading area.

Description

Fire intelligent early warning system based on multisource data Technical Field The invention belongs to the field of fire early warning, relates to a fire intelligent early warning technology based on multi-source data, and in particular relates to a fire intelligent early warning system based on multi-source data. Background Fire is extremely destructive and difficult to dispose of. It not only causes property loss and air pollution, but also causes various effects on the health of people. Various measures are tried to be taken aiming at fire disaster early warning people, but the intelligent early warning requirement of the full-time and full-space cannot be met. The prior art (the invention patent application with publication number of CN 113139272A) discloses a forest fire spreading prediction method, a device, equipment and a storage medium, wherein fire data in the current time period is input into a forest fire spreading speed model constructed based on a cellular automaton algorithm to obtain a forest fire spreading prediction result, and the accuracy of the forest fire spreading prediction result is improved. The prior art is mainly applied to prediction of fire spread of forest fires, the prediction of fire spread is carried out only on the basis of fire data, and considered influence factors are single, so that the fire spread precision cannot be ensured, and the method cannot be applied to various fire early warning scenes; therefore, a fire intelligent early warning system based on multi-source data is needed. Disclosure of Invention The invention aims to at least solve one of the technical problems in the prior art, and therefore provides an intelligent fire early warning system based on multi-source data, which is used for solving the technical problems that in the prior art, in the prediction of fire spread, the fire spread precision cannot be ensured and the intelligent fire early warning system cannot be applied to various fire early warning scenes due to single considered influencing factors. In order to achieve the above purpose, the first aspect of the present invention provides a fire intelligent early warning system based on multi-source data, which comprises a central analysis module, a data display module and a plurality of edge analysis modules, wherein the data display module and the plurality of edge analysis modules are connected with the central analysis module, and the edge analysis modules are connected with data acquisition equipment; The edge analysis module is used for collecting basic data through a data collecting device connected with the edge analysis module when a fire occurs, wherein the basic data comprises environment data and area condition data, and Performing data processing on the basic data to obtain original data, and sending the original data to the central analysis module, wherein the data processing comprises data screening and data integration; the central analysis module is used for identifying a target area according to the area condition data and dividing the target area into a plurality of subareas according to the identification result, wherein the target area comprises a fire disaster area and And simulating a fire spreading process based on the fire spreading speed, and visually displaying the fire spreading process through a data display module. Preferably, the central analysis module is respectively in communication and/or electric connection with the data display module and the plurality of edge analysis modules, and the data display module is used for data display; The edge analysis module is configured according to a configuration rule, and the edge analysis module is connected with the data acquisition equipment, wherein the configuration rule comprises configuration based on an area or configuration based on a data type. Preferably, before the edge analysis module collects the basic data, a data collection signal is generated by the hub analysis module and sent to the edge analysis module, including: Receiving multi-source data, wherein the multi-source data comprises video data sent by an intelligent terminal and a watchtower, and the intelligent terminal comprises a mobile phone and a computer; Identifying and analyzing the video data based on an image analysis technology, marking fire levels according to analysis results, and judging whether to generate a data acquisition signal based on the fire levels; And when the fire grade is greater than a grade threshold, generating a data acquisition signal and transmitting the data acquisition signal to a plurality of edge analysis modules, wherein the grade threshold is set according to experience. Preferably, the edge analysis module performs data processing on the basic data to obtain the original data, including: Extracting the environment data in the basic data, and rendering and generating an environment distribution image based on the environment data and the configuration rule, wherein t