Remote forest fire early warning system based on Internet of Things

Abstract

The invention discloses a remote forest fire early warning system based on the Internet of Things, and belongs to the technical field of forest fire prevention prediction, and the remote forest fire early warning method based on the Internet of Things comprises the steps: dividing a to-be-early-warned region into a plurality of sub-regions, obtaining the weight of a fire danger factor index of each sub-region, obtaining the dryness index of each sub-region, and obtaining the weight of the fire danger factor index of each sub-region; and determining a fire danger early warning coefficient of each sub-region according to the weight of the fire danger factor index of each sub-region and the corresponding drying index, and determining a fire danger condition of the corresponding sub-region based on the fire danger early warning coefficient. The remote forest fire early warning system based on the Internet of Things comprises a division module, an acquisition module, a judgment module, a calculation module I, a calculation module II and a storage module, so that the fire danger condition of an area is judged, and then the fire danger condition is transmitted to a command center, so that potential fire risks of a forest can be found in advance, and the probability of occurrence of forest fire is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of forest fire prevention prediction, and more specifically, to a remote forest fire early warning system based on the Internet of Things. Background Art

[0002] On the road of progress of modern Chinese society, the forest system, as a key part of the ecosystem, plays a vital role in the development of human society and environmental protection. However, forest fires, as a major disaster of the ecological environment, often have a serious impact on people's life safety. Therefore, we need to continuously strengthen the research on forest fire prevention and control mechanisms, and use modern advanced technologies to enhance our prevention and control and early warning capabilities.

[0003] However, at present, China generally adopts advanced scientific and technological early warning methods such as remote sensing satellite monitoring and forest protection aircraft patrols. This is a monitoring method that adapts to its large continuous forest area and sparse human activities. However, my country, especially the southern provinces, has scattered forest areas and frequent human activities. Forest fires are mostly caused by human activities. Remote sensing satellite monitoring and forest protection aircraft patrols are difficult to meet my country's forest fire prevention needs. According to traditional manual patrol technology or watchtower monitoring technology, it is time-consuming and laborious, and the effect is not good. Moreover, forest monitors often only discover forest fires and extinguish them after they occur. This makes it impossible to predict forest fires in advance, address factors that may cause forest fires in advance, and deploy firefighting work in a timely manner.

[0004] Therefore, it is necessary to provide a remote forest fire early warning system based on the Internet of Things to solve the above problems. Summary of the invention

[0005] The present invention provides a remote forest fire early warning system based on the Internet of Things, which can improve the problem in related technologies that forest fires cannot be predicted and simulated before they occur.

[0006] In a first aspect, the embodiment of the present application provides a remote forest fire warning method based on the Internet of Things, which adopts the following technical solution: dividing the area to be warned into multiple sub-areas; Obtaining the weight of the fire risk factor index of each of the sub-areas; Determining a dryness index for each of the sub-areas based on the current time; Determine the fire risk warning coefficient of each sub-region based on the weight of the fire risk factor index of each sub-region and the corresponding dryness index; The fire risk situation of the corresponding sub-area is determined based on the fire risk warning coefficient; wherein the fire risk situation indicates the probability of fire occurrence.

[0007] The above technical solution in the embodiment of the present application has at least the following technical effects: by obtaining the fire risk warning coefficient of the forest i sub-area, the fire risk situation of the area can be judged, and then the fire risk situation is transmitted to the command center, which can help to discover the potential fire risk of the forest in advance, provide early warning for the government and relevant departments, so that preventive measures can be taken in time, and then according to the fire risk level, firefighting resources such as firefighters, fire trucks, firefighting equipment and materials can be reasonably allocated to improve the efficiency of firefighting. Fires can cause huge economic losses, including property losses, crop damage and infrastructure damage. Prediction helps to reduce these losses and help identify high-risk areas, so as to take targeted measures to reduce the frequency of fires. With the intensification of climate change, the frequency and severity of forest fires may increase. Prediction helps to cope with such changes and reduce the impact of fires on society.

[0008] In an embodiment, the dryness index of each sub-area is calculated based on the current time according to the following formula: , is the drying index, and T is the current time.

[0009] In an embodiment, the first warning coefficient of each sub-region is determined based on the weight of the fire risk factor index of each sub-region and the corresponding dryness index; When the first warning coefficient is less than a first threshold, determining the first warning coefficient as a fire risk warning coefficient; The determining the fire risk situation of the corresponding sub-area based on the fire risk warning coefficient includes: The fire risk situation is determined to be no risk or low risk based on the first warning coefficient.

[0010] In an embodiment, when the first warning coefficient is greater than or equal to a first threshold, the surface temperature of the corresponding sub-area and the fire risk factor index weight corresponding to the surface temperature are obtained, and the relative humidity of the corresponding sub-area and the fire risk factor index weight corresponding to the relative humidity are obtained; Determine a second warning coefficient based on the surface temperature of the corresponding sub-area and the weight of the fire risk factor index corresponding to the surface temperature, and determine a third warning coefficient based on the relative humidity of the corresponding sub-area and the weight of the fire risk factor index corresponding to the relative humidity; Adding the first warning coefficient, the second warning coefficient and the third warning coefficient to obtain a fire risk warning coefficient; The determining the fire risk situation of the corresponding sub-area based on the fire risk warning coefficient includes: Based on the fire risk warning coefficient, when the fire risk warning coefficient is greater than a first threshold or less than a second threshold, determining the fire risk situation as a medium risk based on the fire risk warning coefficient; When the fire risk warning coefficient is greater than a second threshold, determining the fire risk situation as high risk based on the fire risk warning coefficient; Report fire danger situation to the command center.

[0011] In an embodiment, when the fire risk situation is medium risk or high risk, a thermal infrared image is obtained through thermal infrared data, the surface temperature data is obtained as F (x, y), and the surface temperature of the sub-area is determined based on the sensor constant, the atmospheric constant and the field of view temperature obtained by the sensor; (x,y)= ; F (x, y) is the surface temperature data, where x, y are pixel coordinates, N is the sensor constant, K is the atmospheric constant, and G is the field of view temperature. is the surface temperature.

[0012] In an embodiment, the fire point of the forest is determined based on the surface temperature of each of the sub-areas; When the ground surface temperature is greater than a fire point threshold, determining the ground surface temperature as a fire point; Then the (x, y) data is processed through a median filter to mark all the pixels that meet the threshold conditions, i.e., the fire point locations; Report the fire location to the command center.

[0013] In the embodiment, the fire trend prediction unit is used to perform trend prediction analysis on the real-time fire in the forest i sub-region; the operation process of the fire trend prediction unit is as follows: according to the information collected from each i sub-region, the fire trend prediction unit is obtained. The wind speed, wind direction, topography, vegetation distribution and phenological index parameters of the sub-region are simulated through the fire spread simulation model to obtain the fire spread scenario of the i sub-region. The fire spread speed, direction and fire power in the sub-area are calculated to obtain the burned area of ​​the i sub-area from 1h to 24h and the burned biomass of the i sub-area from 1h to 24h.

[0014] Second aspect: The remote forest fire early warning system based on the Internet of Things provided by the present invention adopts the following technical solutions: A division module is used to divide the area to be warned into multiple sub-areas; An acquisition module, used to acquire the weight of the fire risk factor index of each sub-area; A calculation module I is used to obtain a dryness index of each sub-area at the current time; A calculation module II is used to obtain the weight of the fire risk factor index of each sub-area and the corresponding dryness index to determine the fire risk warning coefficient of each sub-area; A judgment module is used to obtain the fire risk warning coefficient to determine the fire risk situation of the corresponding sub-area; wherein the fire risk situation indicates the probability of fire occurrence. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flowchart of a remote forest fire warning method based on the Internet of Things provided in Example 1 of the present application; Figure 2 This is a system structure diagram of the remote forest fire warning system based on the Internet of Things provided in Example 2 of the present application. DETAILED DESCRIPTION

[0016] Forest monitors often only discover forest fires and extinguish them after they occur. This makes it impossible to predict forest fires in advance, address factors that may cause forest fires in advance, and deploy firefighting work in a timely manner.

[0017] Based on this, in order to improve the problem in the related art that it is impossible to predict and simulate forest fires before they occur, the embodiments of the present application provide the following solutions. Embodiment 1, the present application embodiment provides a remote forest fire early warning method based on the Internet of Things, adopting the following technical solution: Please refer to Figure 1 , remote forest fire warning methods based on the Internet of Things include: S100, dividing the area to be warned into multiple sub-areas; In a possible implementation of this embodiment, the area to be warned is divided into multiple sub-areas, and these sub-areas are divided according to geographical location, terrain conditions, etc., which can more accurately reflect the fire risks in different areas.

[0018] S200, obtaining the weight of the fire risk factor index of each of the sub-areas; Optionally, local fire rescue departments or disaster prevention centers provide data and analysis related to fire risks, and obtain the weights of fire risk factor indicators for each sub-region through their databases. These indicators may include temperature, humidity, wind speed, etc., which are important factors affecting the occurrence of fires. We assign different weights to these indicators according to their different importance.

[0019] S300, determining a dryness index of each of the sub-areas based on the current time; Optionally, S300, determining a dryness index of each sub-area based on the current time, includes: Calculate the drying index of each of the sub - regions according to the following formula based on the current time: , is the drying index, and T is the current time.

[0020] is the drying index of the sub - region at the current time, and T is the current time of the year.

[0021] S400, determine the fire risk warning coefficient of each sub - region based on the weight of the fire risk factor index of each sub - region and the corresponding drying index; S500, determine the fire risk situation of the corresponding sub - region based on the fire risk warning coefficient; wherein, the fire risk situation indicates the probability of a fire occurring Optionally, S400, determining the fire risk warning coefficient of each sub - region based on the weight of the fire risk factor index of each sub - region and the corresponding drying index, includes: S410, determine the first warning coefficient of each sub - region based on the weight of the fire risk factor index of each sub - region and the corresponding drying index; in the case where the first warning coefficient is less than the first threshold, determine the first warning coefficient as the fire risk warning coefficient; Preset fire risk warning coefficient thresholds Z1, Z2; The determining the fire risk situation of the corresponding sub - region based on the fire risk warning coefficient includes: If <Z1, then determine that the fire situation is of low risk or no risk, and execute the feedback step; is the determined fire risk warning coefficient; Determine that the fire risk situation is of no risk and low risk based on the first warning coefficient.

[0022] S420, in the case where the first warning coefficient is greater than or equal to the first threshold, obtain the surface temperature of the corresponding sub - region and the weight of the fire risk factor index corresponding to the surface temperature, and obtain the relative humidity of the corresponding sub - region and the weight of the fire risk factor index corresponding to the relative humidity; Determine the second warning coefficient based on the surface temperature of the corresponding sub - region and the weight of the fire risk factor index corresponding to the surface temperature, and determine the third warning coefficient based on the relative humidity of the corresponding sub - region and the weight of the fire risk factor index corresponding to the relative humidity; Add the first warning coefficient, the second warning coefficient and the third warning coefficient to obtain the fire risk warning coefficient; The determining the fire risk situation of the corresponding sub - region based on the fire risk warning coefficient includes: If Z1 Z2, the fire situation is judged to be of medium risk, and the feedback step is executed; Based on the fire risk warning coefficient, when the fire risk warning coefficient is greater than a first threshold or less than a second threshold, determining the fire risk situation as a medium risk based on the fire risk warning coefficient; like >Z2, it is determined that the probability of fire is low, and the feedback step is executed; When the fire risk warning coefficient is greater than a second threshold, determining the fire risk situation as high risk based on the fire risk warning coefficient; Report fire danger situation to the command center.

[0023] Optionally, S600, when the fire risk situation is medium risk or high risk, obtain a thermal infrared image through thermal infrared data, obtain surface temperature data as F(x, y), obtain sensor constants, atmospheric constants and field of view temperature based on the sensor, and determine the surface temperature of the sub-area; (x,y)= ; F (x, y) is the surface temperature data, where x, y are pixel coordinates, N is the sensor constant, K is the atmospheric constant, and G is the field of view temperature. The surface temperature is obtained by obtaining thermal infrared images through thermal infrared data. The surface temperature data is F (x, y), where x and y are pixel coordinates. The sensor constant N, atmospheric constant K and field temperature G are obtained through the sensor. Optionally, S610, fire point location determination: pre-set a threshold , like (x,y) , then determine (x,y) is marked as a fire point and the feedback step is performed; After passing through the median filter J The (x, y) data is processed to mark all pixels that meet the threshold conditions, that is, the fire point locations. The calculation model is as follows: (x,y)=J (x,y); is the fire point location).

[0024] Feedback: Calculated (x, y) fire point position, the fire point position (x, y) is transmitted to the command center through the network port cable, and then the fire point location is determined. (x,y) to predict the fire trend.

[0025] Optionally, S700, a fire trend prediction unit is used to perform trend prediction analysis on the real-time fire in the forest i sub-region; the operation process of the fire trend prediction unit is as follows: according to the information collected for each i sub-region, the fire trend prediction unit is obtained. The wind speed, wind direction, topography, vegetation distribution and phenological index parameters of the sub-region are simulated through the fire spread simulation model to obtain the fire spread scenario of the i sub-region. The fire spread speed, direction and fire power in the sub-area are calculated to obtain the burned area of ​​the i sub-area from 1h to 24h and the burned biomass of the i sub-area from 1h to 24h.

[0026] Embodiment 2, the remote forest fire early warning system based on the Internet of Things provided by the present invention adopts the following technical solution: Please refer to Figure 2 , the remote forest fire early warning system based on the Internet of Things includes: A division module is used to divide the area to be warned into multiple sub-areas; Optionally, a division module: the output end is electrically connected to the input end of the storage module to divide the area to be warned into multiple sub-areas, which are divided according to geographical location, terrain conditions, etc., so as to more accurately reflect the fire risks in different areas.

[0027] An acquisition module, used to acquire the weight of the fire risk factor index of each sub-area; Optionally, the output terminal is connected to the input terminal of the storage module for electrical signal connection, and is used to obtain the weight of the fire risk factor index of the i-th sub-area, and the local fire rescue department or disaster prevention center provides data and analysis related to fire risk, and obtains the weight of the fire risk factor index of each sub-area through the database therein, and these indicators may include temperature, humidity, wind speed, etc., which are important factors affecting the occurrence of fire. We assign different weights to these indicators according to their different importance.

[0028] A calculation module I is used to obtain a dryness index of each sub-area at the current time; Optionally, the input terminal is electrically connected to the output terminal of the storage module, and the dryness index of each sub-area is calculated based on the current time according to the following formula: A calculation module II is used to obtain the weight of the fire risk factor index of each sub-area and the corresponding dryness index to determine the fire risk warning coefficient of each sub-area; Optionally, the input end is electrically connected to the output end of the calculation module I, and when the first warning coefficient is less than a first threshold value, the first warning coefficient is determined as a fire risk warning coefficient.

[0029] When the first warning coefficient is greater than or equal to the first threshold, the surface temperature of the corresponding sub-area and the fire risk factor index weight corresponding to the surface temperature are obtained, and the relative humidity of the corresponding sub-area and the fire risk factor index weight corresponding to the relative humidity are obtained, and the first warning coefficient, the second warning coefficient and the third warning coefficient are added together to obtain the fire risk warning coefficient.

[0030] A judgment module is used to obtain the fire risk warning coefficient to determine the fire risk situation of the corresponding sub-area; wherein the fire risk situation indicates the probability of fire occurrence.

[0031] Optionally, the output end is connected to the output end of the calculation module II with an electrical signal. When the first warning coefficient is less than a first threshold, the first warning coefficient is determined as a fire risk warning coefficient, and the fire risk situation is determined to be no risk and low risk based on the first warning coefficient. Based on the fire risk warning coefficient, when the fire risk warning coefficient is greater than the first threshold or less than the second threshold, the fire risk situation is determined to be medium risk based on the fire risk warning coefficient, and when the fire risk warning coefficient is greater than the second threshold, the fire risk situation is determined to be high risk based on the fire risk warning coefficient.

[0032] The implementation principle of the remote forest fire warning system based on the Internet of Things in the embodiment of the present application is as follows: the acquisition module obtains the geographical information of the area to be warned and the historical fire situation information and the weight of the fire risk factor index of the i-th sub-area , and execute calculation module I. When the fire situation is high risk or medium risk, the prediction information is transmitted to the command center, and the calculation module II and the judgment module are executed to locate the fire point. (x,y) data, pair (x,y) data to judge, if (x,y) , then determine (x, y) is marked as a fire point, and then the median filter J is used to filter (x, y) data is processed, all pixels that meet the threshold conditions are marked, and the fire point location is fed back to the command center (x,y), real-time fire point location (x, y) conducts trend forecast analysis and feeds the information back to the command center.

[0033] The above is only a preferred specific implementation of the present invention; however, the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solution and its improved conception within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A remote forest fire early warning method based on the Internet of Things, characterized in that: include: Divide the area to be warned into multiple sub-areas; Obtaining the weight of the fire risk factor index of each of the sub-areas; Determining a dryness index for each of the sub-areas based on the current time; Determine the fire risk warning coefficient of each sub-region based on the weight of the fire risk factor index of each sub-region and the corresponding dryness index; The fire risk situation of the corresponding sub-area is determined based on the fire risk warning coefficient; wherein the fire risk situation indicates the probability of fire occurrence.

2. The remote forest fire early warning method based on the Internet of Things according to claim 1 is characterized in that: The step of determining the dryness index of each sub-area based on the current time includes: The dryness index of each sub-area is calculated based on the current time according to the following formula: , is the drying index, and T is the current time.

3. The remote forest fire early warning method based on the Internet of Things according to claim 2 is characterized in that: The determining of the fire risk warning coefficient of each sub-region based on the weight of the fire risk factor index of each sub-region and the corresponding dryness index includes: Determine a first warning coefficient for each of the sub-areas based on the weight of the fire risk factor index of each of the sub-areas and the corresponding dryness index; When the first warning coefficient is less than a first threshold, determining the first warning coefficient as a fire risk warning coefficient; The determining the fire risk situation of the corresponding sub-area based on the fire risk warning coefficient includes: The fire risk situation is determined to be no risk or low risk based on the first warning coefficient.

4. The remote forest fire early warning method based on the Internet of Things according to claim 3 is characterized in that: The determining of the fire risk warning coefficient of each sub-region based on the weight of the fire risk factor index of each sub-region and the corresponding dryness index includes: When the first warning coefficient is greater than or equal to the first threshold, obtaining the surface temperature of the corresponding sub-area and the fire risk factor index weight corresponding to the surface temperature, and obtaining the relative humidity of the corresponding sub-area and the fire risk factor index weight corresponding to the relative humidity; Determine a second warning coefficient based on the surface temperature of the corresponding sub-area and the weight of the fire risk factor index corresponding to the surface temperature, and determine a third warning coefficient based on the relative humidity of the corresponding sub-area and the weight of the fire risk factor index corresponding to the relative humidity; Adding the first warning coefficient, the second warning coefficient and the third warning coefficient to obtain a fire risk warning coefficient; The determining the fire risk situation of the corresponding sub-area based on the fire risk warning coefficient includes: Based on the fire risk warning coefficient, when the fire risk warning coefficient is greater than a first threshold or less than a second threshold, determining the fire risk situation as medium risk based on the fire risk warning coefficient; When the fire risk warning coefficient is greater than a second threshold, determining the fire risk situation as high risk based on the fire risk warning coefficient; Report fire danger situation to the command center.

5. The remote forest fire early warning method based on the Internet of Things according to claim 4 is characterized in that: The method further comprises: When the fire risk is medium risk or high risk, a thermal infrared image is obtained through thermal infrared data, and the surface temperature data is obtained as F(x, y), and the surface temperature of the sub-area is determined based on the sensor constant, the atmospheric constant and the field of view temperature; (x,y)= ; F (x, y) is the surface temperature data, where x, y are pixel coordinates, N is the sensor constant, K is the atmospheric constant, and G is the field of view temperature. is the surface temperature.

6. The remote forest fire early warning method based on the Internet of Things according to claim 5 is characterized in that: The method further comprises: Determining the fire point of the forest based on the surface temperature of each of the sub-areas; When the ground surface temperature is greater than a fire point threshold, determining the ground surface temperature as a fire point; Then pass the median filter to (x, y) data is processed to mark all pixels that meet the threshold conditions, i.e., the fire point locations; Report the fire location to the command center.

7. The remote forest fire early warning method based on the Internet of Things according to claim 6 is characterized in that: Fire trend prediction unit: used to perform trend prediction analysis on real-time fire in forest i sub-area; the operation process of the fire trend prediction unit is as follows: according to the information collected from each i sub-area, the fire trend prediction unit obtains the fire trend of the forest i sub-area. The wind speed, wind direction, topography, vegetation distribution and phenological index parameters of the sub-region are simulated through the fire spread simulation model to obtain the fire spread scenario of the i sub-region. The fire spread speed, direction and fire power in the sub-area are calculated to obtain the burned area of ​​the i sub-area from 1h to 24h and the burned biomass of the i sub-area from 1h to 24h.

8. A remote forest fire early warning system based on the Internet of Things, used to implement the remote forest fire early warning method based on the Internet of Things as claimed in any one of claims 1 to 7, characterized in that: The system comprises: A division module is used to divide the area to be warned into multiple sub-areas; An acquisition module, used to acquire the weight of the fire risk factor index of each sub-area; A calculation module I is used to obtain a dryness index of each sub-area at the current time; A calculation module II is used to obtain the weight of the fire risk factor index of each sub-area and the corresponding dryness index to determine the fire risk warning coefficient of each sub-area; A judgment module is used to obtain the fire risk warning coefficient to determine the fire risk situation of the corresponding sub-area; wherein the fire risk situation indicates the probability of fire occurrence.

Images