CN112735072B - Forest region dynamic and forest region fire early warning cloud platform based on Internet of things - Google Patents
Forest region dynamic and forest region fire early warning cloud platform based on Internet of things Download PDFInfo
- Publication number
- CN112735072B CN112735072B CN202110013155.9A CN202110013155A CN112735072B CN 112735072 B CN112735072 B CN 112735072B CN 202110013155 A CN202110013155 A CN 202110013155A CN 112735072 B CN112735072 B CN 112735072B
- Authority
- CN
- China
- Prior art keywords
- fire
- area
- forest
- forest region
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 230000004927 fusion Effects 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000013500 data storage Methods 0.000 claims description 35
- 238000011156 evaluation Methods 0.000 claims description 26
- 238000012795 verification Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 16
- 238000007500 overflow downdraw method Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 13
- 230000007613 environmental effect Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000012545 processing Methods 0.000 description 6
- 238000012937 correction Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- G06T5/70—
-
- G06T5/92—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/50—Safety; Security of things, users, data or systems
Abstract
The invention discloses a forest area dynamic and forest area fire early warning cloud platform based on the Internet of things, relates to the technical field of forest area early warning, and solves the technical problems that the advantages of the Internet cannot be fully utilized and advance early warning on forest area fire cannot be realized in the existing scheme; the fire monitoring module is arranged, and the fire monitoring module combines multiple technologies, so that the fire monitoring accuracy is improved, and the early warning efficiency is improved; the forest region dynamic prediction module is arranged, and prediction is carried out by combining the fusion model, so that the prediction precision is improved, and a foundation is laid for protection preparation of workers; the system is provided with the display scheduling module and the alarm scheduling module, so that personnel can be scheduled to process the fire in the forest area in time, the expansion of the fire is prevented, and the occurrence of heavy loss is avoided.
Description
Technical Field
The invention belongs to the field of forest area early warning, relates to the technology of Internet of things, and particularly relates to a forest area dynamic and forest area fire early warning cloud platform based on the Internet of things.
Background
Forests play an important role in maintaining the balance of land ecosystems and improving the ecological environment. The forest resources are few, the coverage rate is low, the structure and the quality of forest seeds are not ideal enough, and the overall situation is quite severe: forest fires are main disasters which harm forest resources, and prevention and reduction of the forest fires are important components of forestry work. The occurrence of forest fires is a result of the combined action of extremely complex natural factors and human factors, and forest fire monitoring plays a very important role in forest protection.
The invention patent with the publication number of CN104240427A provides a forest fire prevention monitoring system based on the Internet of things, which comprises a plurality of temperature sensors, a power supply, a microprocessor, a wireless communication module, a data communication module and a master control platform, wherein the temperature sensors, the power supply, the microprocessor, the wireless communication module, the data communication module and the master control platform are arranged on the ground; the metal-resistant RFID tag is provided with a unique ID identification, the ID is managed in a database of the master control station, and the longitude and latitude position of the fire-proof early warning station, the telephone of the contact person and the forest characteristics of the corresponding area are given to the corresponding ID identification.
The scheme not only has a traditional monitoring alarm system, but also the RFID tag endows each fireproof early warning platform with a unique ID, manages the ID in a background management database, and endows the corresponding ID with the longitude and latitude position of the fireproof early warning platform, the telephone of a contact person and the forest characteristics of a corresponding area; the scheme only sets ID management on the basis of the traditional monitoring alarm system, cannot fully utilize the advantages of the Internet, and cannot early warn forest fires in advance; therefore, the above solution still needs further improvement.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides a forest region dynamic and forest region fire early warning cloud platform based on the Internet of things.
The purpose of the invention can be realized by the following technical scheme: a forest region dynamic and forest region fire early warning cloud platform based on the Internet of things comprises a processor, an alarm scheduling module, a display scheduling module, a data storage module, a fire monitoring module, a forest region monitoring module and a forest region dynamic prediction module;
the monitoring of fire monitoring module combination setting at the inside first thing of forest zone allies oneself with equipment to forest zone conflagration includes:
optionally, taking a first temperature sensor as a circle center, dividing a circular area by taking R1 as a radius, marking the circular area as a first area, and acquiring a temperature mean value of the first area and marking the temperature mean value as a first temperature mean value; simultaneously selecting four temperature sensors on the edge of the first area as reference sensors, using the reference sensors as circle centers, using R1 as a radius to define circular areas and respectively marking the circular areas as a second area, a third area, a fourth area and a fifth area, obtaining temperature mean values of the four areas of the second area, the third area, the fourth area and the fifth area and marking the temperature mean values as second temperature mean values; the R1 is a radius threshold, and R1>5, in meters;
labeling the first and second temperature means as YWJ and EWJ, respectively; when EWJ is smaller than YWJ, shooting an image of an area where the first temperature sensor is located through a high-definition camera, and marking the image as a verification image after image preprocessing; the image preprocessing comprises image segmentation, image denoising and gray level transformation;
acquiring a gray average value, a gray maximum value and a gray minimum value of a pixel point in a verification image, and respectively marking the gray average value, the gray maximum value and the gray minimum value as HJZ, HZZ and HZX; by the formula
Acquiring a fire evaluation coefficient MPX; wherein α 1 is a proportionality coefficient, and α 1 is a real number greater than 0; when the fire evaluation coefficient MPX meets L1-theta and MPX and L1+ theta, judging that the fire disaster happens in the first area; wherein L1 is a fire assessment coefficient threshold, and L1>0；
Acquiring the area of a fire area, and marking the area as QM; when the area L2 is not more than QM, the area of the forest fire is judged to be large, and a fire early warning signal is respectively sent to the display scheduling module and the alarm scheduling module through the processor; otherwise, sending a fire early warning signal to a display scheduling module through the processor; wherein L2 is a zone area threshold and L2 is a real number greater than 0;
and sending the sending record of the fire early warning signal to a data storage module for storage through a processor.
Further, the forest zone monitoring module is used for monitoring the environment of the forest zone, and comprises:
obtaining tree species in the forest area, and marking the tree species as i, i-1, 2, … …, n;
acquiring a temperature mean value and a humidity mean value of a region where the tree species i are located in real time, and respectively marking the temperature mean value and the humidity mean value as WZ and SZ;
obtaining an environment evaluation coefficient HPxi of the tree species i by the formula HPxi ═ alpha 2 x (WZ-YWZ) + alpha 3 x (SZ-YSZ); wherein alpha 2 and alpha 3 are both proportionality coefficients, alpha 2 and alpha 3 are both real numbers greater than 0, YWZ is the optimal temperature value for the growth of the tree species i, and YSZ is the optimal humidity value for the growth of the tree species i;
when the environment evaluation coefficient HPxi meets 0< HPxi is not more than L3, judging that the growing environment of the tree species i is appropriate, and sending an environment green signal to the display scheduling module through the processor; when the environment evaluation coefficient HPxi meets the condition that L3< HPxi is not more than L4, judging that the growing environment of the tree seed i is not good enough, and sending an environment yellow signal to the display scheduling module through the processor; when the environment evaluation coefficient HPxi meets L4< HPxi, judging that the growing environment of the tree species i is abnormal, and sending an environment red signal to a display scheduling module through a processor; wherein L3 and L4 are environment assessment coefficient thresholds, and L3 and L4 are both real numbers greater than 0;
sending the sending record of the environment early warning signal to a data storage module for storage through a processor; the environment early warning signal comprises an environment green signal, an environment yellow signal and an environment red signal.
Furthermore, the forest region dynamic prediction module comprises a fire prediction unit and a forest region dynamic prediction unit; the forest region dynamic state refers to the change of the planting area and the planting quantity of the tree species i in the forest region; the fire prediction unit is used for predicting forest fire according to fire history data and comprises:
acquiring fire history data in a data storage module; the fire history data refers to the occurrence record of fire in the forest area; the fire history data comprises a fire occurrence area, a temperature value and a humidity value in the area, tree species in the area, a monthly rainfall average value in the area and a fire occurrence date;
constructing a fusion model; the fusion model is constructed by combining a support vector machine model and an error reverse feedback propagation neural network with a fusion mode, wherein the fusion mode comprises a linear weighting fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
generating a training set, a verification set and a test set from fire history data according to a set proportion; training, verifying and testing the fusion model through the training set, the verifying set and the testing set, judging that the training of the fusion model is finished when the target precision of the fusion model meets the requirement, and marking the trained fusion model as a prediction model;
acquiring future data in a forest area; the future data comprises a prediction date, a temperature value and a humidity value in the forest region at the prediction date, and a tree species and monthly rainfall mean value; inputting future data into a prediction model to obtain a fire prediction result;
respectively sending the fire prediction result to a display scheduling module and a data storage module through a processor;
the forest region dynamic prediction unit is used for predicting forest region dynamics according to forest region dynamic historical data and comprises the following steps:
acquiring forest region dynamic data in a data storage module; the forest region dynamic data comprise planting area and planting quantity of tree seeds i in the forest region within a set time range, temperature change, humidity change and PM2.5 content change; the set time range includes the past three months, the past six months, and the past twelve months;
generating a training set, a verification set and a test set from forest region dynamic data according to a set proportion; acquiring a prediction model by combining a training set, a verification set and a test set with a fusion model;
acquiring environmental prediction data in a forest region; the environmental prediction data includes predicted temperature changes, humidity changes, and PM2.5 changes;
combining the environmental prediction data with a prediction model to obtain a forest region dynamic prediction result; and respectively sending the forest region dynamic prediction result to a data storage module and a display scheduling module through a processor.
Further, the display scheduling module is used for scheduling forest region workers, and comprises:
when the display scheduling module receives the fire early warning signal, acquiring the sending position of the fire early warning signal and marking the sending position as a target position;
the method comprises the steps of obtaining forest region workers nearest to a target position and marking the forest region workers as target workers, planning a route between the target position and the target workers through a third-party map platform and marking the route as a working route, and sending the working route and the target position to an intelligent terminal of the target workers; the third party map platform comprises a Baidu map and a Gade map; the number of the target persons is not less than 2 persons;
forest workers arrive at the target position to process when receiving the working route and the target position; and forest region workers can send alarm help-seeking signals to the alarm scheduling module through the intelligent terminal; and the scheduling records of the forest region workers are sent to the data storage module for storage through the processor.
Furthermore, the alarm scheduling module is in communication connection with a police service platform and a fire alarm platform; the alarm scheduling module schedules police officers and fire fighters according to the received alarm signal; the alarm signal comprises an alarm help-seeking signal and a fire early warning signal.
Furthermore, the first internet of things equipment is in communication connection with the fire monitoring module, the first internet of things equipment is arranged in the forest area at the same interval, and geographical coordinates installed on the first internet of things equipment are stored in the data storage module; the first internet of things device at least comprises a first temperature sensor and a high-definition camera.
Furthermore, the processor is respectively in communication connection with the alarm scheduling module, the display scheduling module, the data storage module, the fire monitoring module, the forest region monitoring module and the forest region dynamic prediction module, the data storage module is in communication connection with the display scheduling module, and the display scheduling module is in communication connection with the alarm scheduling module.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention is provided with a fire monitoring module, which is used for the fire in the forest area; the method comprises the steps of dividing a first area on the basis of a temperature sensor, judging a fire disaster in the first area by combining a second area, a third area, a fourth area and a fifth area, and then acquiring the area of the fire disaster area by combining a high-definition camera and a remote sensing image; the fire monitoring module combines a plurality of technologies, which is beneficial to improving the fire monitoring precision and improving the early warning efficiency;
2. the invention is provided with a forest region dynamic prediction module, wherein the forest region dynamic prediction module comprises a fire prediction unit and a forest region dynamic prediction unit; forecasting future fire occurrence conditions and forest area dynamic change conditions in the forest area through fire history data and forest area dynamic data; the forest region dynamic prediction module is combined with the fusion model to carry out prediction, so that the prediction precision is improved, and a foundation is laid for the worker to prepare for protection;
3. the invention is provided with a display scheduling module and an alarm scheduling module; when the display scheduling module receives the fire early warning signal, acquiring the sending position of the fire early warning signal and marking the sending position as a target position; the method comprises the steps of obtaining forest region workers nearest to a target position and marking the forest region workers as target workers, planning a route between the target position and the target workers through a third-party map platform and marking the route as a working route, and sending the working route and the target position to an intelligent terminal of the target workers; forest workers arrive at the target position to process when receiving the working route and the target position; and forest region workers can send alarm help-seeking signals to the alarm scheduling module through the intelligent terminal; when a fire disaster occurs in the forest area, the personnel are dispatched in time to process the fire disaster, so that the fire disaster is prevented from being enlarged, and the occurrence of heavy loss is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of the principle of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides three embodiments:
the first embodiment is as follows:
a forest region dynamic and forest region fire early warning cloud platform based on the Internet of things comprises a processor, an alarm scheduling module, a display scheduling module, a data storage module, a fire monitoring module, a forest region monitoring module and a forest region dynamic prediction module;
the monitoring of fire monitoring module combination setting at the inside first thing of forest zone allies oneself with equipment to forest zone conflagration includes:
optionally, taking a first temperature sensor as a circle center, dividing a circular area by taking R1 as a radius, marking the circular area as a first area, and acquiring a temperature mean value of the first area and marking the temperature mean value as a first temperature mean value; simultaneously selecting four temperature sensors on the edge of the first area as reference sensors, using the reference sensors as circle centers, using R1 as a radius to define circular areas and respectively marking the circular areas as a second area, a third area, a fourth area and a fifth area, obtaining temperature mean values of the four areas of the second area, the third area, the fourth area and the fifth area and marking the temperature mean values as second temperature mean values; the R1 is a radius threshold, and R1>5, in meters;
labeling the first and second temperature means as YWJ and EWJ, respectively; when EWJ is smaller than YWJ, shooting an image of an area where the first temperature sensor is located through a high-definition camera, and marking the image as a verification image after image preprocessing; the image preprocessing comprises image segmentation, image denoising and gray level transformation;
acquiring a gray average value, a gray maximum value and a gray minimum value of a pixel point in a verification image, and respectively marking the gray average value, the gray maximum value and the gray minimum value as HJZ, HZZ and HZX; by the formula
Acquiring a fire evaluation coefficient MPX; wherein α 1 is a proportionality coefficient, and α 1 is a real number greater than 0; when the fire evaluation coefficient MPX meets L1-theta and MPX and L1+ theta, judging that the fire disaster happens in the first area; wherein L1 is a fire assessment coefficient threshold, and L1>0；
Acquiring the area of a fire area, and marking the area as QM; when the area L2 is not more than QM, the area of the forest fire is judged to be large, and a fire early warning signal is respectively sent to the display scheduling module and the alarm scheduling module through the processor; otherwise, sending a fire early warning signal to a display scheduling module through the processor; wherein L2 is a zone area threshold and L2 is a real number greater than 0;
and sending the sending record of the fire early warning signal to a data storage module for storage through a processor.
Further, the forest zone monitoring module is used for monitoring the environment of the forest zone, and comprises:
obtaining tree species in the forest area, and marking the tree species as i, i-1, 2, … …, n;
acquiring a temperature mean value and a humidity mean value of a region where the tree species i are located in real time, and respectively marking the temperature mean value and the humidity mean value as WZ and SZ;
obtaining an environment evaluation coefficient HPxi of the tree species i by the formula HPxi ═ alpha 2 x (WZ-YWZ) + alpha 3 x (SZ-YSZ); wherein alpha 2 and alpha 3 are both proportionality coefficients, alpha 2 and alpha 3 are both real numbers greater than 0, YWZ is the optimal temperature value for the growth of the tree species i, and YSZ is the optimal humidity value for the growth of the tree species i;
when the environment evaluation coefficient HPxi meets 0< HPxi is not more than L3, judging that the growing environment of the tree species i is appropriate, and sending an environment green signal to the display scheduling module through the processor; when the environment evaluation coefficient HPxi meets the condition that L3< HPxi is not more than L4, judging that the growing environment of the tree seed i is not good enough, and sending an environment yellow signal to the display scheduling module through the processor; when the environment evaluation coefficient HPxi meets L4< HPxi, judging that the growing environment of the tree species i is abnormal, and sending an environment red signal to a display scheduling module through a processor; wherein L3 and L4 are environment assessment coefficient thresholds, and L3 and L4 are both real numbers greater than 0;
sending the sending record of the environment early warning signal to a data storage module for storage through a processor; the environment early warning signal comprises an environment green signal, an environment yellow signal and an environment red signal.
Furthermore, the forest region dynamic prediction module comprises a fire prediction unit and a forest region dynamic prediction unit; the forest region dynamic state refers to the change of the planting area and the planting quantity of the tree species i in the forest region; the fire prediction unit is used for predicting forest fire according to fire history data and comprises:
acquiring fire history data in a data storage module; the fire history data refers to the occurrence record of fire in the forest area; the fire history data comprises a fire occurrence area, a temperature value and a humidity value in the area, tree species in the area, a monthly rainfall average value in the area and a fire occurrence date;
constructing a fusion model; the fusion model is constructed by combining a support vector machine model and an error reverse feedback propagation neural network with a fusion mode, wherein the fusion mode comprises a linear weighting fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
generating a training set, a verification set and a test set from fire history data according to a set proportion; training, verifying and testing the fusion model through the training set, the verifying set and the testing set, judging that the training of the fusion model is finished when the target precision of the fusion model meets the requirement, and marking the trained fusion model as a prediction model;
acquiring future data in a forest area; the future data comprises a prediction date, a temperature value and a humidity value in the forest region at the prediction date, and a tree species and monthly rainfall mean value; inputting future data into a prediction model to obtain a fire prediction result;
respectively sending the fire prediction result to a display scheduling module and a data storage module through a processor;
the forest region dynamic prediction unit is used for predicting forest region dynamics according to forest region dynamic historical data and comprises the following steps:
acquiring forest region dynamic data in a data storage module; the forest region dynamic data comprise planting area and planting quantity of tree seeds i in the forest region within a set time range, temperature change, humidity change and PM2.5 content change; the set time range includes the past three months, the past six months, and the past twelve months;
generating a training set, a verification set and a test set from forest region dynamic data according to a set proportion; acquiring a prediction model by combining a training set, a verification set and a test set with a fusion model;
acquiring environmental prediction data in a forest region; the environmental prediction data includes predicted temperature changes, humidity changes, and PM2.5 changes;
combining the environmental prediction data with a prediction model to obtain a forest region dynamic prediction result; and respectively sending the forest region dynamic prediction result to a data storage module and a display scheduling module through a processor.
Further, the display scheduling module is used for scheduling forest region workers, and comprises:
when the display scheduling module receives the fire early warning signal, acquiring the sending position of the fire early warning signal and marking the sending position as a target position;
the method comprises the steps of obtaining forest region workers nearest to a target position and marking the forest region workers as target workers, planning a route between the target position and the target workers through a third-party map platform and marking the route as a working route, and sending the working route and the target position to an intelligent terminal of the target workers; the third party map platform comprises a Baidu map and a Gade map; the number of the target persons is not less than 2 persons;
forest workers arrive at the target position to process when receiving the working route and the target position; and forest region workers can send alarm help-seeking signals to the alarm scheduling module through the intelligent terminal; and the scheduling records of the forest region workers are sent to the data storage module for storage through the processor.
Furthermore, the alarm scheduling module is in communication connection with a police service platform and a fire alarm platform; the alarm scheduling module schedules police officers and fire fighters according to the received alarm signal; the alarm signal comprises an alarm help-seeking signal and a fire early warning signal.
Furthermore, the first internet of things equipment is in communication connection with the fire monitoring module, the first internet of things equipment is arranged in the forest area at the same interval, and geographical coordinates installed on the first internet of things equipment are stored in the data storage module; the first internet of things device at least comprises a first temperature sensor and a high-definition camera.
Furthermore, the processor is respectively in communication connection with the alarm scheduling module, the display scheduling module, the data storage module, the fire monitoring module, the forest region monitoring module and the forest region dynamic prediction module, the data storage module is in communication connection with the display scheduling module, and the display scheduling module is in communication connection with the alarm scheduling module.
Example two: the difference between the second embodiment and the first embodiment is that fire monitoring is realized by image analysis;
a forest region dynamic and forest region fire early warning cloud platform based on the Internet of things comprises a processor, an alarm scheduling module, a display scheduling module, a data storage module, a fire monitoring module, a forest region monitoring module and a forest region dynamic prediction module;
the fire condition monitoring module monitors the fire in the forest zone by combining the remote sensing image, and comprises the following steps:
acquiring a remote sensing image in real time and carrying out remote sensing image processing on the remote sensing image to acquire a standard image; the standard image covers a forest area, and the remote sensing image processing comprises geometric correction, atmospheric correction, image fusion and image splicing;
combining a remote sensing processing technology with a standard image to obtain a fire occurrence condition and a fire area;
and the processor is used for sending the fire occurrence condition and the area of the fire area to the display scheduling module and the data storage module.
Example three: the difference between the third embodiment and the first and second embodiments is that fire monitoring is realized by combining the first internet of things device and the remote sensing image;
the fire monitoring module is used for the monitoring to forest zone conflagration, include:
optionally, taking a first temperature sensor as a circle center, dividing a circular area by taking R1 as a radius, marking the circular area as a first area, and acquiring a temperature mean value of the first area and marking the temperature mean value as a first temperature mean value; simultaneously selecting four temperature sensors on the edge of the first area as reference sensors, using the reference sensors as circle centers, using R1 as a radius to define circular areas and respectively marking the circular areas as a second area, a third area, a fourth area and a fifth area, obtaining temperature mean values of the four areas of the second area, the third area, the fourth area and the fifth area and marking the temperature mean values as second temperature mean values; the R1 is a radius threshold, and R1>5, in meters;
labeling the first and second temperature means as YWJ and EWJ, respectively; when the YWJ is more than or equal to EWJ-mu and less than or equal to EWJ + mu, shooting an image of the area where the first temperature sensor is located through a high-definition camera, and marking the image as a verification image after image preprocessing; the image preprocessing comprises image segmentation, image denoising and gray level transformation;
acquiring a gray average value, a gray maximum value and a gray minimum value of a pixel point in a verification image, and respectively marking the gray average value, the gray maximum value and the gray minimum value as HJZ, HZZ and HZX; by the formula
Acquiring a fire evaluation coefficient MPX; wherein α 1 is a proportionality coefficient, and α 1 is a real number greater than 0; when the fire evaluation coefficient MPX meets L1-theta and MPX and L1+ theta, judging that the fire disaster happens in the first area; wherein L1 is a fire hazard assessment systemNumber threshold, and L1>0, mu is a proportionality coefficient, and theta is belonged to [0.1,0.5 ]]；
When a fire disaster occurs in the first area, acquiring a remote sensing image in real time, and processing the remote sensing image to acquire a standard image; the standard image covers the first area, and the remote sensing image processing comprises geometric correction, atmospheric correction, image fusion and image splicing;
combining a remote sensing processing technology with a standard image to obtain a fire occurrence condition and a fire area;
and the processor is used for sending the fire occurrence condition and the area of the fire area to the display scheduling module and the data storage module.
The above formulas are all calculated by removing dimensions and taking numerical values thereof, the formula is a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest real situation, and the preset parameters and the preset threshold value in the formula are set by the technical personnel in the field according to the actual situation or obtained by simulating a large amount of data.
The working principle of the invention is as follows:
optionally, taking a first temperature sensor as a circle center, dividing a circular area by taking R1 as a radius, marking the circular area as a first area, and acquiring a temperature mean value of the first area and marking the temperature mean value as a first temperature mean value; simultaneously selecting four temperature sensors on the edge of the first area as reference sensors, using the reference sensors as circle centers, using R1 as a radius to define circular areas and respectively marking the circular areas as a second area, a third area, a fourth area and a fifth area, obtaining temperature mean values of the four areas of the second area, the third area, the fourth area and the fifth area and marking the temperature mean values as second temperature mean values; labeling the first and second temperature means as YWJ and EWJ, respectively; when EWJ is smaller than YWJ, shooting an image of an area where the first temperature sensor is located through a high-definition camera, and marking the image as a verification image after image preprocessing; acquiring a gray average value, a gray maximum value and a gray minimum value of pixel points in the verification image, and acquiring a fire evaluation coefficient MPX; wherein α 1 is a proportionality coefficient, and α 1 is a real number greater than 0; when the fire evaluation coefficient MPX meets L1-theta and MPX and L1+ theta, judging that the fire disaster happens in the first area; acquiring the area of a fire area, and marking the area as QM; when the area L2 is not more than QM, the area of the forest fire is judged to be large, and a fire early warning signal is respectively sent to the display scheduling module and the alarm scheduling module through the processor; otherwise, sending a fire early warning signal to a display scheduling module through the processor;
obtaining tree species i in a forest area; acquiring a temperature mean value and a humidity mean value of a region where the tree species i are located in real time, and respectively marking the temperature mean value and the humidity mean value as WZ and SZ; obtaining an environment evaluation coefficient HPxi of the tree species i; when the environment evaluation coefficient HPxi meets 0< HPxi is not more than L3, judging that the growing environment of the tree species i is appropriate, and sending an environment green signal to the display scheduling module through the processor; when the environment evaluation coefficient HPxi meets the condition that L3< HPxi is not more than L4, judging that the growing environment of the tree seed i is not good enough, and sending an environment yellow signal to the display scheduling module through the processor; when the environment evaluation coefficient HPxi meets L4< HPxi, judging that the growing environment of the tree species i is abnormal, and sending an environment red signal to a display scheduling module through a processor;
when the display scheduling module receives the fire early warning signal, acquiring the sending position of the fire early warning signal and marking the sending position as a target position; the method comprises the steps of obtaining forest region workers nearest to a target position and marking the forest region workers as target workers, planning a route between the target position and the target workers through a third-party map platform and marking the route as a working route, and sending the working route and the target position to an intelligent terminal of the target workers; forest workers arrive at the target position to process when receiving the working route and the target position; and forest region workers can send alarm help-seeking signals to the alarm scheduling module through the intelligent terminal; and the scheduling records of the forest region workers are sent to the data storage module for storage through the processor.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (6)
1. A forest region dynamic and forest region fire early warning cloud platform based on the Internet of things is characterized by comprising a processor, an alarm scheduling module, a display scheduling module, a data storage module, a fire monitoring module, a forest region monitoring module and a forest region dynamic prediction module;
the monitoring of fire monitoring module combination setting at the inside first thing of forest zone allies oneself with equipment to forest zone conflagration includes:
optionally, taking a first temperature sensor as a circle center, dividing a circular area by taking R1 as a radius, marking the circular area as a first area, and acquiring a temperature mean value of the first area and marking the temperature mean value as a first temperature mean value; simultaneously selecting four temperature sensors on the edge of the first area as reference sensors, using the reference sensors as circle centers, using R1 as a radius to define circular areas and respectively marking the circular areas as a second area, a third area, a fourth area and a fifth area, obtaining temperature mean values of the four areas of the second area, the third area, the fourth area and the fifth area and marking the temperature mean values as second temperature mean values; the R1 is a radius threshold, and R1>5, in meters;
labeling the first and second temperature means as YWJ and EWJ, respectively; when EWJ is smaller than YWJ, shooting an image of the area where the first temperature sensor is located through a high-definition camera, and marking the image as a verification image after image preprocessing; the image preprocessing comprises image segmentation, image denoising and gray level transformation;
acquiring a gray average value, a gray maximum value and a gray minimum value of a pixel point in a verification image, and minimizing the gray average value, the gray maximum value and the gray minimum valueValues are marked HJZ, HZZ, and HZX, respectively; by the formula
Acquiring a fire evaluation coefficient MPX; wherein α 1 is a proportionality coefficient, and α 1 is a real number greater than 0; when the fire evaluation coefficient MPX meets L1-theta and MPX and L1+ theta, judging that the fire disaster happens in the first area; wherein L1 is a fire assessment coefficient threshold, and L1 > 0;
acquiring the area of a fire area, and marking the area as QM; when the area L2 is not more than QM, the area of the forest fire is judged to be large, and a fire early warning signal is respectively sent to the display scheduling module and the alarm scheduling module through the processor; otherwise, sending a fire early warning signal to a display scheduling module through the processor; wherein L2 is a zone area threshold and L2 is a real number greater than 0;
and sending the sending record of the fire early warning signal to a data storage module for storage through a processor.
2. The Internet of things-based forest region dynamic and forest region fire early warning cloud platform of claim 1, wherein the forest region monitoring module is used for monitoring the environment of a forest region, and comprises:
obtaining tree species in the forest area, and marking the tree species as i, i-1, 2, … …, n;
acquiring a temperature mean value and a humidity mean value of a region where the tree species i are located in real time, and respectively marking the temperature mean value and the humidity mean value as WZ and SZ;
obtaining an environment evaluation coefficient HPxi of the tree species i by the formula HPxi ═ alpha 2 x (WZ-YWZ) + alpha 3 x (SZ-YSZ); wherein alpha 2 and alpha 3 are both proportionality coefficients, alpha 2 and alpha 3 are both real numbers greater than 0, YWZ is the optimal temperature value for the growth of the tree species i, and YSZ is the optimal humidity value for the growth of the tree species i;
when the environment evaluation coefficient HPxi meets 0< HPxi < L3, judging that the growing environment of the tree species i is appropriate, and sending an environment green signal to the display scheduling module through the processor; when the environment evaluation coefficient HPxi meets the condition that L3 is larger than HPxi and is not larger than L4, judging that the growing environment of the tree seed i is not good enough, and sending an environment yellow signal to the display scheduling module through the processor; when the environment evaluation coefficient HPxi meets the condition that L4 is less than HPxi, judging that the growing environment of the tree species i is abnormal, and sending an environment red signal to a display scheduling module through a processor; wherein L3 and L4 are environment assessment coefficient thresholds, and L3 and L4 are both real numbers greater than 0;
sending the sending record of the environment early warning signal to a data storage module for storage through a processor; the environment early warning signal comprises an environment green signal, an environment yellow signal and an environment red signal.
3. The Internet of things-based forest region dynamic and forest region fire early warning cloud platform as claimed in claim 1, wherein the forest region dynamic prediction module comprises a fire prediction unit and a forest region dynamic prediction unit; the forest region dynamic state refers to the change of the planting area and the planting quantity of the tree species i in the forest region; the fire prediction unit is used for predicting forest fire according to fire history data and comprises:
acquiring fire history data in a data storage module; the fire history data refers to the occurrence record of fire in the forest area; the fire history data comprises a fire occurrence area, a temperature value and a humidity value in the area, tree species in the area, a monthly rainfall average value in the area and a fire occurrence date;
constructing a fusion model; the fusion model is constructed by combining a support vector machine model and an error reverse feedback propagation neural network with a fusion mode, wherein the fusion mode comprises a linear weighting fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
generating a training set, a verification set and a test set from fire history data according to a set proportion; training, verifying and testing the fusion model through the training set, the verifying set and the testing set, judging that the training of the fusion model is finished when the target precision of the fusion model meets the requirement, and marking the trained fusion model as a prediction model;
acquiring future data in a forest area; the future data comprises a prediction date, a temperature value and a humidity value in the forest region at the prediction date, and a tree species and monthly rainfall mean value; inputting future data into a prediction model to obtain a fire prediction result;
respectively sending the fire prediction result to a display scheduling module and a data storage module through a processor;
the forest region dynamic prediction unit is used for predicting forest region dynamics according to forest region dynamic historical data and comprises the following steps:
acquiring forest region dynamic data in a data storage module; the forest region dynamic data comprise planting area and planting quantity of tree seeds i in the forest region within a set time range, temperature change, humidity change and PM2.5 content change; the set time range includes the past three months, the past six months, and the past twelve months;
generating a training set, a verification set and a test set from forest region dynamic data according to a set proportion; acquiring a prediction model by combining a training set, a verification set and a test set with a fusion model;
acquiring environmental prediction data in a forest region; the environmental prediction data includes predicted temperature changes, humidity changes, and PM2.5 changes;
combining the environmental prediction data with a prediction model to obtain a forest region dynamic prediction result; and respectively sending the forest region dynamic prediction result to a data storage module and a display scheduling module through a processor.
4. The Internet of things-based forest region dynamic and forest region fire early warning cloud platform of claim 1, wherein the display scheduling module is used for scheduling forest region workers, and comprises:
when the display scheduling module receives the fire early warning signal, acquiring the sending position of the fire early warning signal and marking the sending position as a target position;
the method comprises the steps of obtaining forest region workers nearest to a target position and marking the forest region workers as target workers, planning a route between the target position and the target workers through a third-party map platform and marking the route as a working route, and sending the working route and the target position to an intelligent terminal of the target workers; the third party map platform comprises a Baidu map and a Gade map; the number of the target persons is not less than 2 persons;
forest workers arrive at the target position to process when receiving the working route and the target position; and forest region workers can send alarm help-seeking signals to the alarm scheduling module through the intelligent terminal; and the scheduling records of the forest region workers are sent to the data storage module for storage through the processor.
5. The Internet of things-based forest region dynamic and forest region fire early warning cloud platform according to claim 1, wherein the alarm scheduling module is in communication connection with a police service platform and a fire alarm platform; the alarm scheduling module schedules police officers and fire fighters according to the received alarm signal; the alarm signal comprises an alarm help-seeking signal and a fire early warning signal.
6. The Internet of things-based forest region dynamic and forest region fire early warning cloud platform according to claim 1, wherein the first Internet of things equipment is in communication connection with the fire monitoring module, the first Internet of things equipment is arranged in a forest region at the same intervals, and geographic coordinates installed on the first Internet of things equipment are stored in the data storage module; the first internet of things device at least comprises a first temperature sensor and a high-definition camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110013155.9A CN112735072B (en) | 2021-01-06 | 2021-01-06 | Forest region dynamic and forest region fire early warning cloud platform based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110013155.9A CN112735072B (en) | 2021-01-06 | 2021-01-06 | Forest region dynamic and forest region fire early warning cloud platform based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112735072A CN112735072A (en) | 2021-04-30 |
| CN112735072B true CN112735072B (en) | 2022-03-04 |
Family
ID=75590001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110013155.9A Active CN112735072B (en) | 2021-01-06 | 2021-01-06 | Forest region dynamic and forest region fire early warning cloud platform based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112735072B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7280696B2 (en) * | 2002-05-20 | 2007-10-09 | Simmonds Precision Products, Inc. | Video detection/verification system |
| TWI264684B (en) * | 2004-11-16 | 2006-10-21 | Univ Nat Kaohsiung Applied Sci | Fire detection method and system applying with image acquisition |
| JP5158632B2 (en) * | 2008-01-16 | 2013-03-06 | 清水建設株式会社 | Fire monitoring device and fire monitoring method |
| CN102236947B (en) * | 2010-04-29 | 2012-08-29 | 中国建筑科学研究院 | Flame monitoring method and system based on video camera |
| CN104715562A (en) * | 2015-04-01 | 2015-06-17 | 成都桑莱特科技股份有限公司 | Method and system for early warning electric transmission line wildfires |
| CN106997461B (en) * | 2017-03-28 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| CN111476964A (en) * | 2020-03-04 | 2020-07-31 | 宁波财经学院 | Remote forest fire prevention monitoring system and method |
| CN112133052B (en) * | 2020-09-22 | 2022-09-20 | 岭澳核电有限公司 | Image fire detection method for nuclear power plant |
-
2021
- 2021-01-06 CN CN202110013155.9A patent/CN112735072B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112735072A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110599727B (en) | Emergency command management system for forest fire | |
| KR102108754B1 (en) | Realtime forest fire danger rating system in north korea | |
| US20180025458A1 (en) | Self-customizing, multi-tenanted mobile system and method for digitally gathering and disseminating real-time visual intelligence on utility asset damage enabling automated priority analysis and enhanced utility outage response | |
| CN111121862A (en) | Air-space-ground integrated atmospheric environment monitoring system and method | |
| Vega-Rodríguez et al. | Low cost LoRa based network for forest fire detection | |
| CN112308292B (en) | Method for drawing fire risk grade distribution map | |
| KR102108752B1 (en) | Method for realtime forest fire danger rating forecasting in north korea | |
| JP5172227B2 (en) | Emergency information communication system, emergency information communication method, and emergency information communication program | |
| CN104992254B (en) | Mountain fire based on power grid GIS and the meteorological trend pre-judging method combined | |
| CN108924733A (en) | User device, earthquake alarm server and earthquake alarm method thereof | |
| CN109522380A (en) | A kind of power grid disaster comprehensive monitoring warning data system and method towards mobile application | |
| CN107506903A (en) | A kind of method for managing security and device | |
| CN112380301A (en) | Weather modification service information platform | |
| CN112966933A (en) | Multidimensional wind disaster fine early warning method combining meteorological station and numerical prediction | |
| CN102750456B (en) | earthquake damage assessment system | |
| CN114862160A (en) | Earthquake remote sensing emergency rescue information acquisition method | |
| CN113284026A (en) | Big data wisdom garden management system | |
| McFayden et al. | Risk assessment for wildland fire aerial detection patrol route planning in Ontario, Canada | |
| CN115824975A (en) | Human living environment monitoring system based on domestic high-resolution remote sensing satellite | |
| CN116739245A (en) | Intelligent fire-fighting city alarm receiving and scheduling system | |
| CN109471205B (en) | Monitoring and early warning method based on gridding meteorological data in power grid operation | |
| CN114511432A (en) | Digital country management service system based on block chain | |
| CN110728433A (en) | Land parcel resident population measuring and calculating method based on mobile phone signaling | |
| CN112735072B (en) | Forest region dynamic and forest region fire early warning cloud platform based on Internet of things | |
| KR102108755B1 (en) | Realtime forest fire danger rating system in north korea on mobile network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |