Forest fire intelligent early warning system based on artificial intelligence

By prioritizing the processing of non-fixed site data in the fire early warning system and combining satellite remote sensing data, the problem of insufficient monitoring and processing accuracy in fire spreading areas is solved, and more efficient fire monitoring and prevention is achieved.

CN119068616APending Publication Date: 2024-12-03NANJING HANMIAO INFORMATION TECHNOLOGY CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411385600.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing fire warning system has insufficient accuracy in monitoring and handling in areas where fire spreads, resulting in the inability to effectively prevent the spread of fires.

Method used

The intelligent forest fire warning system based on artificial intelligence is adopted. Through the combination of monitoring modules and evaluation systems, non-fixed site data are given priority, data weight is adjusted, fire monitoring accuracy is improved, and precise control is carried out in combination with satellite remote sensing data and physical monitoring measures.

Benefits of technology

It reduces the energy consumption of the system, improves the monitoring accuracy of the fire monitoring area, and enhances the ability to prevent fire spread.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068616A_ABST
    Figure CN119068616A_ABST
Patent Text Reader

Abstract

The invention provides a forest fire intelligent early warning system based on artificial intelligence, and the system comprises the following modules: a monitoring module which is divided into a fixed station and a non-fixed station, the evaluation priority of the data of the non-fixed station is higher than the evaluation priority of the data of the fixed station, and the detection module is in communication connection with a transmission module; the evaluation system is divided into an early warning mode and an emergency mode, a hardware module operated by the evaluation system is in communication connection with the transmission module, and the early warning mode and the emergency mode in the evaluation system are mainly different from the starting amount of non-fixed stations in operation, so that the operation energy consumption of the whole system is reduced; through a combined monitoring measure of a fixed station and a non-fixed station, the monitoring precision of the system on a monitoring area is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention mainly relates to the field of fire warning, and in particular to an intelligent forest fire warning system based on artificial intelligence. Background Art

[0002] Using artificial intelligence to provide early warning of forest fires in the southwest, changes in fire spread, and assessment of affected areas requires the use of a large number of sensors such as smoke sensors, long-range infrared detection, long-range television monitoring, and lidar technology to collect various data in the target area, and then submit the data to the artificial intelligence model for comprehensive evaluation.

[0003] The current fire warning system developed based on artificial intelligence has become more and more perfect. It can provide timely warning of fires, predict the development of fires and assess the affected area. It also takes into account the need to arrange relevant emergency personnel to enter the scene to carry out fire fighting operations after a fire occurs.

[0004] The inventor proposed an artificial intelligence-based intelligent forest fire warning system. Based on the current artificial intelligence fire warning model, the weights of the collected data are modified and adjusted, and combined with physical monitoring measures, precise control and prevention of fire spread are carried out in the fire area, thereby reducing the system operation energy consumption and monitoring accuracy. Summary of the invention

[0005] 1. Problems to be solved by the invention: The present invention provides an artificial intelligence-based intelligent forest fire early warning system, which is used to solve the technical problem of insufficient accuracy in monitoring and processing of fire spread areas in existing fire predictions mentioned in the above background technology.

[0006] 2. Technical solution: To achieve the above object, the technical solution provided by the present invention is: an artificial intelligence-based forest fire intelligent early warning system, comprising the following modules: The monitoring module is divided into fixed sites and non-fixed sites, the evaluation priority of the non-fixed site data is higher than the evaluation priority of the fixed site data, and the detection module is communicatively connected with the transmission module.

[0007] The evaluation system is divided into an early warning mode and an emergency mode, and the hardware module running the evaluation system is communicatively connected with the transmission module.

[0008] Furthermore, the monitoring module includes a smoke detection module, a video monitoring module, a temperature monitoring module, a humidity monitoring module, a wind speed monitoring module, a wind direction monitoring module, a liquid level sensor and a flow meter, and a fixed site in the monitoring module receives satellite remote sensing data.

[0009] The fixed site may be pre-installed with a smoke detection module and / or a video monitoring module and / or a temperature monitoring module and / or a humidity monitoring module and / or a wind speed monitoring module and / or a wind direction monitoring module.

[0010] The non-fixed site may be pre-installed with a smoke detection module and / or a video monitoring module and / or a temperature monitoring module and / or a humidity monitoring module and / or a wind speed monitoring module and / or a wind direction monitoring module, and the non-fixed site may adopt a drone and / or an airship and / or a ground vehicle and / or a water vessel, etc.

[0011] Furthermore, the satellite remote sensing data includes vegetation coverage data and water resource distribution data for the monitored area; The water resources distribution data should focus on the water flow, using the conventional formula Q = SV; Wherein, S is the cross-sectional area of ​​the water area to be measured, and V is the water flow velocity of the water area to be measured; The cross-sectional curve of the cross-sectional area to be measured is discretized into a number of sampling points. After the water depth value of each sampling point is obtained based on the liquid level sensor, it is calculated by the following mathematical formula: ; in: Δd——sampling interval; h i ——water depth at point i; n——number of sampling points; S——Channel cross-sectional area.

[0012] Furthermore, in the early warning mode of the evaluation system, the evaluation priority of non-fixed site data is higher than that of fixed site data, and in the emergency mode of the evaluation system, the evaluation priority of non-fixed site data is the same as that of fixed site data.

[0013] Furthermore, the data evaluation process of the evaluation system includes the following steps: The probability of fire in the target area is assessed based on the received smoke data, video surveillance data, temperature data, humidity data, wind speed data, wind direction data and satellite remote sensing data.

[0014] Evaluate the data collected by non-fixed sites and fixed sites. Considering the close monitoring of specific monitoring areas by non-fixed sites, give priority to processing the data of non-fixed sites to save computing power of the evaluation system.

[0015] The data collected by fixed sites is used as the basis for preliminary judgment of fire warnings in the monitoring area. When the probability of fire in the monitoring area is found to increase, non-fixed sites need to intervene to provide the evaluation system with data collected close to the monitoring area.

[0016] Furthermore, in the evaluation results, the weight of non-fixed site data accounts for 0.65 and the weight of fixed site data accounts for 0.35.

[0017] Evaluation of data collected from fixed sites, including: The weight of smoke data is 0.25; The weight of video surveillance data is 0.22; The weight of temperature data is 0.29; The weight of humidity data is 0.12; The weight of wind speed data is 0.06; The weight of wind direction data is 0.06; Evaluation of data collected from non-fixed sites, including: The weight of smoke data is 0.36; The weight of video surveillance data is 0.2; The weight of temperature data is 0.28; The weight of humidity data is 0.1; The weight of wind speed data is 0.03; The weight of wind direction data is 0.03; Determine the fire risk level based on the collected temperature data, humidity data, wind speed data, wind direction data, and smoke data: ; I is the fire danger index, p i , i=1,2,3,4,5 are the five meteorological factor component indexes respectively, λ i , i=1, 2, 3, 4, 5 are the corresponding weight coefficients of the five meteorological factor component indexes at different spatial resolution scales.

[0018] Furthermore, in the evaluation system, the evaluation priority of the temperature data in the fixed site is higher than the evaluation priority of the smoke data.

[0019] In the evaluation system, the evaluation priority of smoke data in non-fixed sites is higher than the evaluation priority of temperature data.

[0020] Furthermore, in the assessment system, when the assessment results are close to the system threshold of 13%, a high fire incidence warning needs to be issued to system users, and equipment in non-fixed locations needs to be closely monitored in key areas. In the assessment system, when the assessment results are close to the system threshold of 6%, an emergency plan needs to be output for reference by system users.

[0021] 3. Beneficial effects: Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects: The present invention provides an intelligent forest fire early warning system based on artificial intelligence. The main difference between the early warning mode and the emergency mode in the evaluation system during operation lies in the number of non-fixed sites enabled, thereby reducing the operating energy consumption of the entire system. Through combined monitoring measures of fixed and non-fixed sites, the monitoring accuracy of the system over the monitoring area is improved.

[0022] The parts not involved in the device are the same as those in the prior art or can be implemented by using the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flow chart of the novel structure of the present invention; Figure 2 A flow chart of the novel structure of the present invention; Figure 3 It is a flow chart of the novel structure of the present invention. DETAILED DESCRIPTION

[0024] To facilitate understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0025] It should be noted that when an element is referred to as being "fixed on" another element, it may be directly on the other element or there may also be a central element; when an element is considered to be "connected to" another element, it may be directly connected to the other element or there may also be a central element; the terms "vertical", "horizontal", "left", "right" and similar expressions used in this article are for illustrative purposes only.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more related listed items. Example

[0027] Reference Figure 1-3 , an artificial intelligence-based forest fire intelligent early warning system, including the following modules: The monitoring module is divided into fixed sites and non-fixed sites, the evaluation priority of the non-fixed site data is higher than the evaluation priority of the fixed site data, and the detection module is communicatively connected with the transmission module.

[0028] The evaluation system is divided into an early warning mode and an emergency mode, and the hardware module running the evaluation system is communicatively connected with the transmission module.

[0029] In this embodiment, the monitoring module includes a smoke detection module, a video monitoring module, a temperature monitoring module, a humidity monitoring module, a wind speed monitoring module, a wind direction monitoring module, a liquid level sensor and a flow meter, and a fixed site in the monitoring module receives satellite remote sensing data.

[0030] The fixed site may be pre-installed with a smoke detection module and / or a video monitoring module and / or a temperature monitoring module and / or a humidity monitoring module and / or a wind speed monitoring module and / or a wind direction monitoring module.

[0031] The non-fixed site may be pre-installed with a smoke detection module and / or a video monitoring module and / or a temperature monitoring module and / or a humidity monitoring module and / or a wind speed monitoring module and / or a wind direction monitoring module, and the non-fixed site may adopt a drone and / or an airship and / or a ground vehicle and / or a water vessel, etc.

[0032] In this embodiment, the satellite remote sensing data includes vegetation coverage data and water resource distribution data of the monitored area; The water resources distribution data should focus on the water flow, using the conventional formula Q = SV; Wherein, S is the cross-sectional area of ​​the water area to be measured, and V is the water flow velocity of the water area to be measured; The cross-sectional curve of the cross-sectional area to be measured is discretized into a number of sampling points. After the water depth value of each sampling point is obtained based on the liquid level sensor, it is calculated by the following mathematical formula: ; in: Δd——sampling interval; hi——water depth at point i; n——number of sampling points; S——Channel cross-sectional area.

[0033] In this embodiment, the evaluation priority of non-fixed site data in the early warning mode of the evaluation system is higher than the evaluation priority of fixed site data, and the evaluation priority of non-fixed site data in the emergency mode of the evaluation system is the same as the evaluation priority of fixed site data.

[0034] In this embodiment, the data evaluation process of the evaluation system includes the following steps: The probability of fire in the target area is assessed based on the received smoke data, video surveillance data, temperature data, humidity data, wind speed data, wind direction data and satellite remote sensing data.

[0035] Evaluate the data collected by non-fixed sites and fixed sites. Considering the close monitoring of specific monitoring areas by non-fixed sites, give priority to processing the data of non-fixed sites to save computing power of the evaluation system.

[0036] The data collected by fixed sites is used as the basis for preliminary judgment of fire warnings in the monitoring area. When the probability of fire in the monitoring area is found to increase, non-fixed sites need to intervene to provide the evaluation system with data collected close to the monitoring area.

[0037] In this embodiment, the weight of non-fixed site data in the evaluation result is 0.65 and the weight of fixed site data is 0.35.

[0038] Evaluation of data collected from fixed sites, including: The weight of smoke data is 0.25; The weight of video surveillance data is 0.22; The weight of temperature data is 0.29; The weight of humidity data is 0.12; The weight of wind speed data is 0.06; The weight of wind direction data is 0.06; Evaluation of data collected from non-fixed sites, including: The weight of smoke data is 0.36; The weight of video surveillance data is 0.2; The weight of temperature data is 0.28; The weight of humidity data is 0.1; The weight of wind speed data is 0.03; The weight of wind direction data is 0.03; Determine the fire risk level based on the collected temperature data, humidity data, wind speed data, wind direction data, and smoke data: ; I is the fire danger index, p i , i=1,2,3,4,5 are the five meteorological factor component indexes respectively, λ i , i=1, 2, 3, 4, 5 are the corresponding weight coefficients of the five meteorological factor component indexes at different spatial resolution scales.

[0039] In this embodiment, in the evaluation system, the evaluation priority of the temperature data in the fixed site is higher than the evaluation priority of the smoke data.

[0040] In the evaluation system, the evaluation priority of smoke data in non-fixed sites is higher than the evaluation priority of temperature data.

[0041] In this embodiment, if the evaluation results in the evaluation system are close to the system threshold of 13%, a high fire incidence warning needs to be issued to the system users, and equipment in non-fixed locations needs to be closely monitored in key areas. If the evaluation results in the evaluation system are close to the system threshold of 6%, an emergency plan needs to be output for reference by the system users.

[0042] In this embodiment: In the specific evaluation results, it is necessary to take into account the distribution of vegetation and water resources in the satellite remote sensing data. That is, if the high-probability area of ​​fire is not covered by vegetation, the monitored area is in a normal state and there is no fire risk. The richness of water resources in the monitored area determines the utilization of water resources in the subsequent system emergency plan. The utilization plan needs to combine the distribution of water resources at different altitudes in the monitored area and the water resource reserves to facilitate the subsequent fire-fighting personnel to quickly establish fire isolation zones.

[0043] The main difference between the early warning mode and the emergency mode in the evaluation system is the number of non-fixed sites enabled, which reduces the operating energy consumption of the entire system. Through the combined monitoring measures of fixed and non-fixed sites, the monitoring accuracy of the system over the monitoring area is improved.

[0044] The above-described embodiments only express a certain implementation mode of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the patent scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. An artificial intelligence-based forest fire intelligent early warning system, characterized in that: Includes the following modules: A monitoring module, wherein the monitoring module is divided into fixed sites and non-fixed sites, the evaluation priority of the non-fixed site data is higher than the evaluation priority of the fixed site data, and the detection module is communicatively connected with a transmission module; The evaluation system is divided into an early warning mode and an emergency mode, and the hardware module running the evaluation system is communicatively connected with the transmission module.

2. The artificial intelligence-based forest fire intelligent early warning system according to claim 1, characterized in that: The monitoring module includes a smoke detection module, a video monitoring module, a temperature monitoring module, a humidity monitoring module, a wind speed monitoring module, a wind direction monitoring module, a liquid level sensor and a flow meter, and a fixed site in the monitoring module receives satellite remote sensing data; The fixed site may be pre-installed with a smoke detection module and / or a video monitoring module and / or a temperature monitoring module and / or a humidity monitoring module and / or a wind speed monitoring module and / or a wind direction monitoring module; The non-fixed site may be pre-installed with a smoke detection module and / or a video monitoring module and / or a temperature monitoring module and / or a humidity monitoring module and / or a wind speed monitoring module and / or a wind direction monitoring module, and the non-fixed site may adopt a drone and / or an airship and / or a ground vehicle and / or a water vessel, etc.

3. The forest fire intelligent early warning system based on artificial intelligence according to claim 1 is characterized by: The satellite remote sensing data includes vegetation coverage data and water resource distribution data of the monitored area; The water resources distribution data should focus on the water flow, using the conventional formula Q = SV; Wherein, S is the cross-sectional area of ​​the water area to be measured, and V is the water flow velocity of the water area to be measured; The cross-sectional curve of the cross-sectional area to be measured is discretized into a number of sampling points. After the water depth value of each sampling point is obtained based on the liquid level sensor, it is calculated by the following mathematical formula: ; in: Δd——sampling interval; h i ——water depth at point i; n——number of sampling points; S——Channel cross-sectional area.

4. The forest fire intelligent early warning system based on artificial intelligence according to claim 1 is characterized in that: In the early warning mode of the evaluation system, the evaluation priority of non-fixed site data is higher than that of fixed site data, and in the emergency mode of the evaluation system, the evaluation priority of non-fixed site data is the same as that of fixed site data.

5. The forest fire intelligent early warning system based on artificial intelligence according to claim 1 is characterized by: The data evaluation process of the evaluation system includes the following steps: Assess the probability of fire in the target area based on received smoke data, video surveillance data, temperature data, humidity data, wind speed data, wind direction data and satellite remote sensing data; Evaluate the data collected by non-fixed sites and fixed sites. Considering the close monitoring of non-fixed sites in specific monitoring areas, give priority to the data of non-fixed sites to save computing power of the evaluation system. The data collected by fixed sites is used as the basis for preliminary judgment of fire warnings in the monitoring area. When the probability of fire in the monitoring area is found to increase, non-fixed sites need to intervene to provide the evaluation system with data collected close to the monitoring area.

6. The forest fire intelligent early warning system based on artificial intelligence according to claim 1 is characterized in that: In the evaluation results, the weight of non-fixed site data accounts for 0.65% and the weight of fixed site data accounts for 0.35; Evaluation of data collected from fixed sites, including: The weight of smoke data is 0.25; The weight of video surveillance data is 0.22; The weight of temperature data is 0.29; The weight of humidity data is 0.12; The weight of wind speed data is 0.06; The weight of wind direction data is 0.06; Evaluation of data collected from non-fixed sites, including: The weight of smoke data is 0.36; The weight of video surveillance data is 0.2; The weight of temperature data is 0.28; The weight of humidity data is 0.1; The weight of wind speed data is 0.03; The weight of wind direction data is 0.03; Determine the fire risk level based on the collected temperature data, humidity data, wind speed data, wind direction data, and smoke data: ; I is the fire danger index, p i , i=1,2,3,4,5 are the five meteorological factor component indexes respectively, λ i , i=1, 2, 3, 4, 5 are the corresponding weight coefficients of the five meteorological factor component indexes at different spatial resolution scales.

7. The artificial intelligence-based forest fire intelligent early warning system according to claim 1, characterized in that: In the evaluation system, the evaluation priority of temperature data in fixed sites is higher than the evaluation priority of smoke data; In the evaluation system, the evaluation priority of smoke data in non-fixed sites is higher than the evaluation priority of temperature data.

8. The forest fire intelligent early warning system based on artificial intelligence according to claim 1 is characterized by: In the assessment system, when the assessment results are close to the system threshold of 13%, a high fire incidence warning needs to be issued to the system users, and equipment in non-fixed locations needs to be monitored closely in key areas. In the assessment system, when the assessment results are close to the system threshold of 6%, an emergency plan needs to be output for the reference of the system users.

Citation Information

Cited By

  • Forest monitoring method and device based on satellite and computer readable storage medium

    CN119337297A

  • Satellite-based forest monitoring method, device, and computer-readable storage medium

    CN119337297B