CN113435848A - Fire early warning system and method based on big data simulation - Google Patents
Fire early warning system and method based on big data simulation Download PDFInfo
- Publication number
- CN113435848A CN113435848A CN202110743365.3A CN202110743365A CN113435848A CN 113435848 A CN113435848 A CN 113435848A CN 202110743365 A CN202110743365 A CN 202110743365A CN 113435848 A CN113435848 A CN 113435848A
- Authority
- CN
- China
- Prior art keywords
- fire
- target area
- distribution
- data
- peripheral
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004088 simulation Methods 0.000 title claims abstract description 18
- 230000002093 peripheral effect Effects 0.000 claims abstract description 97
- 238000004364 calculation method Methods 0.000 claims abstract description 49
- 238000007405 data analysis Methods 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 86
- 238000012549 training Methods 0.000 claims description 46
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 43
- 239000001569 carbon dioxide Substances 0.000 claims description 43
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 42
- 229910052760 oxygen Inorganic materials 0.000 claims description 42
- 239000001301 oxygen Substances 0.000 claims description 42
- 238000012937 correction Methods 0.000 claims description 18
- 238000010191 image analysis Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000003745 diagnosis Methods 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 5
- 238000012806 monitoring device Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims description 2
- 238000009472 formulation Methods 0.000 claims 1
- 238000012216 screening Methods 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 10
- 230000008859 change Effects 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 230000002265 prevention Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 241000196324 Embryophyta Species 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 241000723346 Cinnamomum camphora Species 0.000 description 1
- 244000166124 Eucalyptus globulus Species 0.000 description 1
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
- G08B17/117—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means by using a detection device for specific gases, e.g. combustion products, produced by the fire
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Emergency Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Geometry (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computer Graphics (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to the technical field of fire early warning, in particular to a fire early warning system and a fire early warning method based on big data simulation, wherein the system comprises: and the flying device is configured for scanning the target area at high altitude and acquiring image information of the target area and target area data related to the fire in real time. The fire early warning method based on the big data is characterized in that a three-dimensional model of a target area is built, and then data information is collected in real time to finish fire early warning of the target area, in the early warning process, the analysis accuracy is improved by using a big data analysis mode, meanwhile, the data of the peripheral area and the target area are corrected by using various calculation modes, the accuracy of the early warning is greatly improved, meanwhile, early warning of fire of the target area is achieved, the probability of fire occurrence can be obtained when the fire does not occur, and then the fire is prevented in the bud.
Description
Technical Field
The invention belongs to the technical field of fire early warning, and particularly relates to a fire early warning system and method based on big data simulation.
Background
The fire early warning is to find the fire in the initial stage of the fire, and inform the fire fighters to put out the fire in time or evacuate nearby people. The stage is characterized in that the local temperature of a fire point is higher, the burning area is not large, and the burning development is mostly slow, so that the fire is found in time in the initial stage of the fire and alarms at the first time, and valuable time can be provided for timely controlling the fire.
The fire early warning method in the prior art mainly comprises an early warning method based on a physical sensor and an early warning method based on a thermal imaging camera, for example, a smoke alarm monitors the change of smoke concentration in the air of a fire or electricity utilization area and then initiates early warning, or the thermal imaging camera analyzes the heat energy distribution and temperature of the fire or electricity utilization area and gives an alarm when the temperature of the fire or electricity utilization area is higher than a fire alarm set value.
A patent with the patent number of CN102568146B discloses a fire early warning and early eliminating system based on infrared thermal images, and an infrared thermal imager is used for collecting the infrared thermal images of monitored equipment; the image analysis controller is used for analyzing the infrared thermal image and generating an analysis result; and the fire alarm and linkage controller is used for generating a control signal according to the analysis result of the image analysis controller. By acquiring the infrared thermal image of the equipment and analyzing the distribution and the change of the temperature field of the equipment, the fire disaster is prevented, and the possibility of the fire disaster of the equipment is reduced; and the early fire elimination can be realized by linking with the fixed-point fire extinguishing device, so that the timeliness of fire treatment is improved.
Therefore, in the prior art, although the fire early warning can be realized by aiming at the acquisition and analysis of the real-time data of the site, the fire development can not be prevented in time even if the early warning can be completed. Because the fire condition is often developed to the early stage in the early warning mode after the collected data are analyzed. Therefore, the method can simulate and predict the fire condition on the spot, and pre-warn the fire to the extent of weather forecast, so that prevention can be performed in advance before the fire occurs, and the occurrence rate of the fire is greatly reduced.
Disclosure of Invention
In view of the above, the main object of the present invention is to provide a fire early warning system and method based on big data simulation, which complete fire early warning for a target area by constructing a three-dimensional model of the target area and then collecting data information in real time, and in the early warning process, not only the analysis accuracy is improved by using an analysis mode of big data, but also the data of a peripheral area and the target area are corrected by using various calculation modes, so that the early warning accuracy is greatly improved, and meanwhile, early warning of a fire in the target area is realized, and when a fire does not occur, the occurrence probability of the fire can be obtained, thereby preventing the fire from happening in the future.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
fire early warning system based on big data simulation, the system includes:
the flight device is configured for scanning a target area at high altitude and acquiring image information of the target area and target area data related to a fire in real time; the target area data includes at least: the carbon dioxide concentration distribution, the humidity distribution, the temperature distribution and the oxygen concentration distribution of the target area;
the target area three-dimensional model building device is configured and used for building a target area three-dimensional model based on the acquired image information of the target area;
the peripheral area monitoring device is configured for carrying out high-altitude scanning on a peripheral area surrounding a target area and acquiring peripheral area data related to a fire in real time; the peripheral region data at least includes: the carbon dioxide concentration distribution, the humidity distribution, the temperature distribution and the oxygen concentration distribution of the peripheral area;
the image analysis unit is configured to firstly perform image analysis based on the image information of the target area acquired in real time so as to judge whether the target area has a fire or not and obtain a judgment result;
the data analysis unit is configured for carrying out data distribution analysis on carbon dioxide concentration, humidity, temperature and oxygen concentration of the target area and the peripheral area based on the target area data and the peripheral area data to obtain a data analysis result;
the big data analysis unit is configured to calculate the probability of fire in the target area by using a preset fire judgment tree model based on the data analysis result obtained by the data analysis unit to obtain a probability calculation result;
the early warning unit is configured to perform fire early warning in a target area based on the judgment result obtained by the image analysis unit and the probability calculation result of the big data analysis unit, and specifically includes: if the judgment result judges that the target area has a fire, directly carrying out fire occurrence early warning; and if the probability calculation result of the big data analysis unit shows that the fire in the target area exceeds a set threshold value, performing fire early warning.
Further, the data analysis unit includes: the target area data processing unit is configured to perform horizontal division and vertical division on the three-dimensional model of the target area, at least three horizontal areas are obtained through the horizontal division, at least two vertical areas are obtained through the vertical division, and then the target area data are distributed into the corresponding vertical areas and the corresponding horizontal areas; the first data calculation unit is configured to perform data calculation based on the obtained two longitudinal areas, and specifically includes: respectively calculating the average value of the distribution of the carbon dioxide in each longitudinal area, the average value of the humidity distribution of the target area, the average value of the temperature distribution of the target area and the average value of the oxygen concentration distribution of the target area; calculating the sum of each average value to obtain the distribution sum of carbon dioxide in the longitudinal area, the humidity distribution sum of the target area, the temperature distribution sum of the target area and the oxygen concentration distribution sum of the target area; the second data calculation unit is configured to perform data calculation based on the obtained three horizontal areas, and specifically includes: respectively calculating the extreme difference of the distribution of carbon dioxide in each transverse area, the extreme difference of the humidity distribution of the target area, the extreme difference of the temperature distribution of the target area and the extreme difference of the oxygen concentration distribution of the target area; and solving the product value of each average value to obtain the distribution product value of carbon dioxide in the longitudinal area, the humidity distribution product value of the target area, the temperature distribution product value of the target area and the oxygen concentration distribution product value of the target area; a third data calculation unit configured to perform a tie value calculation based on the peripheral area data to obtain an average value of the distribution of carbon dioxide in the peripheral area, an average value of the humidity distribution in the peripheral area, an average value of the temperature distribution in the peripheral area, and an average value of the oxygen concentration distribution in the peripheral area; and simultaneously, calculating the range difference based on the data of the peripheral area to obtain the range difference of the distribution of carbon dioxide in the peripheral area, the range difference of the humidity distribution in the peripheral area, the range difference of the temperature distribution in the peripheral area and the range difference of the oxygen concentration distribution in the peripheral area.
Further, the data analysis result obtained by the data analysis unit of the big data analysis unit uses a preset big data judgment tree model to calculate the probability of fire in the target area, and the method for obtaining the probability calculation result comprises the following steps: constructing a fire judgment tree model, extracting fire big data from a cloud end as a training sample S of the judgment tree model, obtaining fire characteristic attributes according to the training sample S and using the fire characteristic attributes as input variables x of the judgment tree modeli(ii) a The fire signature attributes include at least: the first data calculation unit, the second data calculation unit and the third data calculation unit calculate the obtained results; each input variable xiAll have their corresponding classification xijWhere i is 1, 2, …, n, j is represented by its corresponding xiDetermining a classification value; according to the fire characteristic attribute, introducing offset correction variables which are respectively as follows: average value a of distribution of carbon dioxide in each longitudinal region1Average value a of humidity distribution in target area2Average value a of temperature distribution in target region3And the average value a of the oxygen concentration distribution in the target region4(ii) a Selecting the optimal branch variable of the judgment tree model according to the fire occurrence mutation gain rate T of the training sample S; extracting the data analysis result obtained by the data analysis unit and cutting branches from bottom to top to obtain the fire diagnosis result output variable CkWherein k is 1, 2 and 3; c1、C2And C3Respectively corresponding to possible, no and yes; the introduced diagnosis correction variable ratio is: extreme difference in carbon dioxide distribution in each cross-sectional area b1Extreme difference in humidity distribution in target area b2Extreme difference in temperature distribution in target region b3And the extreme difference b of the oxygen concentration distribution in the target area4(ii) a Constructing a naive Bayes model of the fire, and extracting a decision tree model containing the above from big fire dataThe screened characteristic attribute data is reconstructed into a training sample D, and all output variables in the judgment tree model are extracted to be C1The node of (2) obtains the characteristic attribute classification x passed by each node from top to bottomijAnd defining the characteristic attribute set Y owned by the r-th noderComprises the following steps: y isr＝{y1，y2，...，ymM is the number of characteristic attributes owned by the corresponding node, and the output variable C on the r-th node is obtained by calculation by using a Bayes formula1Probability of fire P (C)1|y1*y2*...*ym)。
Further, when extracting the characteristic attribute data including the screened judgment tree model from the fire big data and reconstructing a training sample D, correcting the characteristic attribute data by using a characteristic correcting variable; the feature correcting variables include: distribution and value d of carbon dioxide in longitudinal region1Target area humidity distribution and value d2Target area temperature distribution and value d3And the oxygen concentration distribution and the value d of the target area4。
Further, the output variable on the r-th node is calculated by using a Bayesian formula to be C1Probability of fire P (C)1|y1*y2*...*ym) Then, the first peripheral correction variable will also be used for correction; the first peripheral correcting variable includes: average value s of distribution of carbon dioxide in peripheral region1Average value s of humidity distribution in peripheral region2Average value s of temperature distribution in peripheral region3And the average value s of the oxygen concentration distribution in the peripheral region4。
Further, the output variable on the r-th node calculated by using the Bayesian formula is C1Probability of fire P (C)1|y1*y2*...*ym) Thereafter, the result will also be corrected using the second peripheral correction variable; the second peripheral correcting variable includes: extreme difference s in distribution of carbon dioxide in peripheral region5Extreme difference s in the humidity distribution in the peripheral region6Pole of temperature distribution in peripheral areaDifference s7And the extreme difference s of the oxygen concentration distribution in the peripheral region8。
Further, the method for correcting by using the first peripheral correcting variable comprises the following steps: the input variables are calculated as follows: c1*(0.1s1+0.2s2+0.3s3+0.4s4) The result obtained is used as a new input variable C1。
Further, the method for correcting using the second peripheral correcting variable includes: probability of fire P (C)1|y1*y2*…*ym) After calculation using the following formula: p (C)1|y1*y2*…*ym)*(0.1s5+0.2s6+0.3s7+0.4s8) The result is obtained as a new probability of fire P (C)1|y1*y2*…*ym)。
Further, the fire occurrence mutation gain rate T is calculated as follows:
t＝Info(S)-Info(Xi)；T＝t/Info(Xi) (ii) a Wherein | S | is the total number of samples of the training sample S; freq (C)kAnd S) is the term C in the training sample SkThe number of samples of fire-like diagnostic results; freq (c)kxij) For inclusion of input variable x in training sample SiThe classification value is xijIs of CkThe number of samples of fire-like diagnostic results; x is the number ofiFor inclusion of input variable x in training sample SiThe number of samples of (a);xijfor inclusion of input variable x in training sample SiThe classification value is xijThe number of samples of (a); info (S) is the information entropy of the training sample S; info (X)i) As fire characteristic attribute xiConditional entropy in the training sample S; info (x)ij) Classifying x for fire signature attributesijConditional entropy in the training sample S; t is fire characteristic attribute xiThe fire is increased abruptly.
A fire early warning method based on big data simulation.
According to the fire early warning system and method based on big data simulation, a three-dimensional model of a target area is built, and then data information is collected in real time to finish fire early warning on the target area. The method is mainly realized by the following steps:
1. acquiring target area data: according to the method, the image information and the environmental data of the target area are collected to carry out fire early warning on the target area, the collected image information only carries out early warning after a fire disaster happens, the collected environmental data predicts the fire disaster happening to the target area to obtain the probability of the fire disaster happening to the target area, and then early warning and prevention are carried out before the fire disaster happens, so that the fire disaster happening rate is greatly reduced;
2. processing of target area data: after target area data are collected, firstly mapping the data into a three-dimensional model based on the established three-dimensional model of the target area to form simulation with the target area, and then performing horizontal and vertical segmentation under the three-dimensional model to obtain a segmented result, and calculating different characteristic values of data distribution aiming at the horizontal area and the vertical area obtained after segmentation, so that the advantages of completely finding the characteristics of the data distribution of the target area, and further correcting the result predicted by a prediction model by using the characteristics to improve the accuracy rate are achieved;
3. the inventive algorithm: when the fire occurrence probability is calculated, big data are used for calling fire big data of a cloud end for training, prediction is carried out based on the established fire prediction model, and therefore the prediction accuracy is improved; meanwhile, the fire disaster judgment tree model used by the invention uses the prior probability of the Bayesian model to predict, and uses a plurality of correction variables obtained after data processing to correct, thereby improving the accuracy of fire disaster prediction.
Drawings
Fig. 1 is a schematic system structure diagram of a fire early warning system based on big data simulation according to an embodiment of the present invention;
fig. 2 is a schematic graph showing the variation of the carbon dioxide concentration distribution and the temperature difference with time in the fire early warning system and method based on big data simulation according to the embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a distribution structure of a target area and a peripheral area of a fire early warning system and method based on big data simulation according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a principle that a target area data processing unit of a fire early warning system and method based on big data simulation distributes target area data to horizontal areas and vertical areas according to an embodiment of the present invention.
Detailed Description
The method of the present invention will be described in further detail below with reference to the accompanying drawings and embodiments of the invention.
Example 1
As shown in fig. 1, a fire early warning system based on big data simulation, the system comprising:
the flight device is configured for scanning a target area at high altitude and acquiring image information of the target area and target area data related to a fire in real time; the target area data includes at least: the carbon dioxide concentration distribution, the humidity distribution, the temperature distribution and the oxygen concentration distribution of the target area;
the target area three-dimensional model building device is configured and used for building a target area three-dimensional model based on the acquired image information of the target area;
the peripheral area monitoring device is configured for carrying out high-altitude scanning on a peripheral area surrounding a target area and acquiring peripheral area data related to a fire in real time; the peripheral region data at least includes: the carbon dioxide concentration distribution, the humidity distribution, the temperature distribution and the oxygen concentration distribution of the peripheral area;
the image analysis unit is configured to firstly perform image analysis based on the image information of the target area acquired in real time so as to judge whether the target area has a fire or not and obtain a judgment result;
the data analysis unit is configured for carrying out data distribution analysis on carbon dioxide concentration, humidity, temperature and oxygen concentration of the target area and the peripheral area based on the target area data and the peripheral area data to obtain a data analysis result;
the big data analysis unit is configured to calculate the probability of fire in the target area by using a preset fire judgment tree model based on the data analysis result obtained by the data analysis unit to obtain a probability calculation result;
the early warning unit is configured to perform fire early warning in a target area based on the judgment result obtained by the image analysis unit and the probability calculation result of the big data analysis unit, and specifically includes: if the judgment result judges that the target area has a fire, directly carrying out fire occurrence early warning; and if the probability calculation result of the big data analysis unit shows that the fire in the target area exceeds a set threshold value, performing fire early warning.
According to the invention, the fire early warning of the target area is completed by constructing the three-dimensional model of the target area and then collecting data information in real time, in the early warning process, the analysis accuracy is improved by using a big data analysis mode, meanwhile, the data of the peripheral area and the target area are corrected by using various calculation modes, the early warning accuracy is greatly improved, meanwhile, the early warning of the fire of the target area is realized, the occurrence probability of the fire can be obtained when the fire does not occur, and further the fire can be prevented in the bud. The method is mainly realized by the following steps:
1. acquiring target area data: according to the method, the image information and the environmental data of the target area are collected to carry out fire early warning on the target area, the collected image information only carries out early warning after a fire disaster happens, the collected environmental data predicts the fire disaster happening to the target area to obtain the probability of the fire disaster happening to the target area, and then early warning and prevention are carried out before the fire disaster happens, so that the fire disaster happening rate is greatly reduced;
2. processing of target area data: after target area data are collected, firstly mapping the data into a three-dimensional model based on the established three-dimensional model of the target area to form simulation with the target area, and then performing horizontal and vertical segmentation under the three-dimensional model to obtain a segmented result, and calculating different characteristic values of data distribution aiming at the horizontal area and the vertical area obtained after segmentation, so that the advantages of completely finding the characteristics of the data distribution of the target area, and further correcting the result predicted by a prediction model by using the characteristics to improve the accuracy rate are achieved;
3. the inventive algorithm: when the fire occurrence probability is calculated, big data are used for calling fire big data of a cloud end for training, prediction is carried out based on the established fire prediction model, and therefore the prediction accuracy is improved; meanwhile, the fire disaster judgment tree model used by the invention uses the prior probability of the Bayesian model to predict, and uses a plurality of correction variables obtained after data processing to correct, thereby improving the accuracy of fire disaster prediction.
Example 2
On the basis of the above embodiment, the data analysis unit includes: the target area data processing unit is configured to perform horizontal division and vertical division on the three-dimensional model of the target area, at least three horizontal areas are obtained through the horizontal division, at least two vertical areas are obtained through the vertical division, and then the target area data are distributed into the corresponding vertical areas and the corresponding horizontal areas; the first data calculation unit is configured to perform data calculation based on the obtained two longitudinal areas, and specifically includes: respectively calculating the average value of the distribution of the carbon dioxide in each longitudinal area, the average value of the humidity distribution of the target area, the average value of the temperature distribution of the target area and the average value of the oxygen concentration distribution of the target area; calculating the sum of each average value to obtain the distribution sum of carbon dioxide in the longitudinal area, the humidity distribution sum of the target area, the temperature distribution sum of the target area and the oxygen concentration distribution sum of the target area; the second data calculation unit is configured to perform data calculation based on the obtained three horizontal areas, and specifically includes: respectively calculating the extreme difference of the distribution of carbon dioxide in each transverse area, the extreme difference of the humidity distribution of the target area, the extreme difference of the temperature distribution of the target area and the extreme difference of the oxygen concentration distribution of the target area; and solving the product value of each average value to obtain the distribution product value of carbon dioxide in the longitudinal area, the humidity distribution product value of the target area, the temperature distribution product value of the target area and the oxygen concentration distribution product value of the target area; a third data calculation unit configured to perform a tie value calculation based on the peripheral area data to obtain an average value of the distribution of carbon dioxide in the peripheral area, an average value of the humidity distribution in the peripheral area, an average value of the temperature distribution in the peripheral area, and an average value of the oxygen concentration distribution in the peripheral area; and simultaneously, calculating the range difference based on the data of the peripheral area to obtain the range difference of the distribution of carbon dioxide in the peripheral area, the range difference of the humidity distribution in the peripheral area, the range difference of the temperature distribution in the peripheral area and the range difference of the oxygen concentration distribution in the peripheral area.
Specifically, a forest fire refers to a forest fire behavior that is not artificially controlled, freely spreads and expands in a forest land, and brings certain harm and loss to forests, forest ecosystems and human beings. Forest fires are natural disasters which are strong in burst, large in destructiveness and difficult to dispose and rescue. Is one kind of fire hazard.
The occurrence and spread of forest fire and the intensity of the fire all have regularity. Besides the above 3 conditions, the occurrence of fire is closely related to the weather (such as high temperature, continuous drought, strong wind, etc.). Raining all year round in tropical rainforests, high humidity in the forests, growing plants all year round, high water content in the bodies and difficult fire hazard. But other forests may have fires in tropical, temperate and cold regions. Generally, the following variation rules apply: the years change periodically. The wet years with much precipitation are not easy to cause fire. Forest fires often occur in arid years with little rainfall, and have cyclic change every year due to the alternation of arid years and humid years. ② seasonal variation. Forest fires often occur in dry seasons in areas where dry and wet seasons are clear within a year. In this case, the rainfall and the water content in the plant are both low, and the ground cover is dry, so that a fire is likely to occur, which is called a fire season (fire prevention period). Forest fires in south China mostly occur in winter and spring, and forest fires in north China mostly occur in spring and autumn. ③ change of day. In one day, the intensity of solar radiant heat is different, the temperature is high at noon, the relative humidity is low, the wind is strong, and the times of forest fire are more; the temperature is low in the morning and evening, the relative humidity is high, the wind is low, and the number of times of forest fire is low.
Furthermore, forest fires are also related to the nature of the combustibles: the tiny dry weeds, dry branches and fallen leaves and the like are the most combustible dangerous fire-leading substances, dry and dead combustible substances are more humid or live combustible substances and broadleaf trees such as coniferous trees, camphor trees, eucalyptus and the like containing a large amount of resin are more combustible than common broadleaf trees. The forest stand with high canopy density is moist and not easy to cause fire; otherwise, it is easy to happen. Forest fires are also related to terrain factors, such as strong sunshine on a sunny slope, high temperature of forest land, easiness in drying combustible materials in the forest, easiness in losing rainwater on a steep slope, and easiness in causing fires due to less soil moisture.
Example 3
On the basis of the previous embodiment, the data analysis result obtained by the big data analysis unit uses a preset big data judgment tree model to calculate the probability of fire in the target area, and the method for obtaining the probability calculation result includes: constructing a fire judgment tree model, extracting fire big data from a cloud end as a training sample S of the judgment tree model, obtaining fire characteristic attributes according to the training sample S and using the fire characteristic attributes as input variables x of the judgment tree modeli(ii) a The fire signature attributes include at least: the first data calculation unit, the second data calculation unit and the third data calculation unit calculate the obtained results; each input variable xiAll have their corresponding classification xijWhere the value of i ═ 1, 2, …, n, j is determined by its corresponding x classification value; according to the fire characteristic attribute, introducing offset correction variables which are respectively as follows: average value a of distribution of carbon dioxide in each longitudinal region1Average value a of humidity distribution in target area2Average value a of temperature distribution in target region3And the average value a of the oxygen concentration distribution in the target region4(ii) a Selecting the optimal branch variable of the judgment tree model according to the fire occurrence mutation gain rate T of the training sample S; extracting the data analysis result obtained by the data analysis unit and cutting branches from bottom to top to obtain the fire diagnosis result output variable CkWherein k is 1, 2 and 3; c1、C2And C3Respectively corresponding to possible, no and yes; the introduced diagnosis correction variable ratio is: extreme difference in carbon dioxide distribution in each cross-sectional area b1Extreme difference in humidity distribution in target area b2Extreme difference in temperature distribution in target region b3And the extreme difference b of the oxygen concentration distribution in the target area4(ii) a Constructing a naive Bayes model of the fire, extracting characteristic attribute data containing the screened judgment tree model from big fire data, reconstructing a training sample D, and extracting all output variables C in the judgment tree model1The node of (2) obtains the characteristic attribute classification x passed by each node from top to bottomijAnd defining the characteristic attribute set Y owned by the r-th noderComprises the following steps: y isr＝{y1，y2，...，ymM is the number of characteristic attributes owned by the corresponding node, and the output variable C on the r-th node is obtained by calculation by using a Bayes formula1Probability of fire P (C)1|y1*y2*...*ym)。
Specifically, in general, the probability of event a under the condition of event B (occurrence) is different from the probability of event B under the condition of event a; however, there is a definite relationship between the two, and bayesian rule is the statement of this relationship.
As a canonical principle, bayesian is valid for the interpretation of all probabilities; however, frequency and bayesian have different opinions on how the probabilities are assigned in the application: the frequency semanticie assigns probability according to the frequency of the random event or the number in the total sample; bayesian subscribers assign a value to the probability based on unknown propositions. One result is that bayesian has more opportunities to use bayesian rules.
Example 4
On the basis of the previous embodiment, when extracting the characteristic attribute data including the screened judgment tree model from the fire big data and reconstructing a training sample D, correcting the characteristic attribute data by using a characteristic correcting variable; the feature correcting variables include: distribution and value d of carbon dioxide in longitudinal region1Target area humidity distribution and value d2Target area temperature distribution and value d3And the oxygen concentration distribution and the value d of the target area4。
Specifically, the training sample is also called a training area, and refers to a typical distribution area of various ground feature types determined by an analyst on the remote sensing image. The accuracy of the classification of the direct relation between the selection and the evaluation of the training samples is the key of the supervised classification.
Supervised classification, also known as training classification, refers to a process of identifying pixels of other unknown classes using samples of selected known classes. The sample pixels of the confirmed category refer to those pixels located in the training area, and the category attribute of the sample pixels is determined in advance through visual interpretation, field investigation and the like of the working area image.
Example 5
On the basis of the previous embodiment, the output variable C on the r-th node is obtained by calculation by using a Bayesian formula1Probability of fire P (C)1|y1*y2*…*ym) Then, the first peripheral correction variable will also be used for correction; the first peripheral correcting variable includes: average value s of distribution of carbon dioxide in peripheral region1Average value s of humidity distribution in peripheral region2Average value s of temperature distribution in peripheral region3And the average value s of the oxygen concentration distribution in the peripheral region4。
Example 6
On the basis of the previous embodiment, the output variable on the r-th node is calculated by using a Bayesian formula to be C1Probability of fire P (C)1|y1*y2*…*ym) Thereafter, the result will also be corrected using the second peripheral correction variable; the second peripheral correcting variable includes: extreme difference s in distribution of carbon dioxide in peripheral region5Extreme difference s in the humidity distribution in the peripheral region6Extreme difference s in temperature distribution in peripheral region7And the extreme difference s of the oxygen concentration distribution in the peripheral region8。
Specifically, Humidity (Humidity) represents a physical quantity of the degree of dryness of the atmosphere. The less water vapor contained in a certain volume of air at a certain temperature, the drier the air; the more water vapor, the more humid the air. The degree of dryness of air is called "humidity". In this sense, the physical quantities such as absolute humidity, relative humidity, comparative humidity, mixture ratio, saturation difference, and dew point are commonly used; if the weight of water vapor in the wet steam is expressed as a percentage of the total weight (volume) of the steam, it is referred to as the humidity of the steam. The humidity at which the human body feels comfortable is: the relative humidity is lower than 70%.
Example 7
On the basis of the above embodiment, the method for correcting using the first peripheral correcting variable includes: the input variables are calculated as follows: c1*(0.1s1+0.2s2+0.3s3+0.4s4) The result obtained is used as a new input variable C1。
Example 8
On the basis of the above embodiment, the method for correcting using the second peripheral correcting variable includes: probability of fire P (C)1|y1*y2*...*ym) After calculation using the following formula: p (C)1|y1*y2*...*ym)*(0.1s5+0.2s6+0.3s7+0.4s8) The result is obtained as a new probability of fire P (C)1|y1*y2*...*ym)。
Example 9
On the basis of the above embodiment, the fire occurrence mutation gain rate T is calculated as follows:
t＝Info(S)-Info(Xi)；T＝t/Info(Xi) (ii) a Wherein | S | is the total number of samples of the training sample S; freq (C)kAnd S) is the term C in the training sample SkThe number of samples of fire-like diagnostic results; freq (c)kxij) For inclusion of input variable x in training sample SiThe classification value is xijIs of CkThe number of samples of fire-like diagnostic results; x is the number ofiFor inclusion of input variable x in training sample SiThe number of samples of (a); x is the number ofijFor inclusion of input variable x in training sample SiThe classification value is xijThe number of samples of (a); info (S) is the information entropy of the training sample S; info (X)i) As fire characteristic attribute xiConditional entropy in the training sample S; info (x)ij) Classifying x for fire signature attributesijConditional entropy in the training sample S; t is fire characteristic attribute xiThe fire is increased abruptly.
Example 10
A fire early warning method based on big data simulation.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process and related description of the system described above may refer to the corresponding process in the foregoing method embodiments, and will not be described herein again.
It should be noted that, the system provided in the foregoing embodiment is only illustrated by dividing the functional units, and in practical applications, the functions may be distributed by different functional units according to needs, that is, the units or steps in the embodiments of the present invention are further decomposed or combined, for example, the units in the foregoing embodiment may be combined into one unit, or may be further decomposed into multiple sub-units, so as to complete all or the functions of the units described above. The names of the units and steps involved in the embodiments of the present invention are only for distinguishing the units or steps, and are not to be construed as unduly limiting the present invention.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes and related descriptions of the storage device and the processing device described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
Those of skill in the art would appreciate that the various illustrative elements, method steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that programs corresponding to the elements, method steps may be located in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. To clearly illustrate this interchangeability of electronic hardware and software, various illustrative components and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as electronic hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The terms "first," "second," and the like are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The terms "comprises," "comprising," or any other similar term are intended to cover a non-exclusive inclusion, such that a process, method, article, or unit/apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or unit/apparatus.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent modifications or substitutions of the related art marks may be made by those skilled in the art without departing from the principle of the present invention, and the technical solutions after such modifications or substitutions will fall within the protective scope of the present invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (10)
1. Fire early warning system based on big data simulation, its characterized in that, the system includes:
the flight device is configured for scanning a target area at high altitude and acquiring image information of the target area and target area data related to a fire in real time; the target area data includes at least: the carbon dioxide concentration distribution, the humidity distribution, the temperature distribution and the oxygen concentration distribution of the target area;
the target area three-dimensional model building device is configured and used for building a target area three-dimensional model based on the acquired image information of the target area;
the peripheral area monitoring device is configured for carrying out high-altitude scanning on a peripheral area surrounding a target area and acquiring peripheral area data critical to a fire in real time; the peripheral region data at least includes: the carbon dioxide concentration distribution, the humidity distribution, the temperature distribution and the oxygen concentration distribution of the peripheral area;
the image analysis unit is configured to firstly perform image analysis based on the image information of the target area acquired in real time so as to judge whether the target area has a fire or not and obtain a judgment result;
the data analysis unit is configured for carrying out data distribution analysis on carbon dioxide concentration, humidity, temperature and oxygen concentration of the target area and the peripheral area based on the target area data and the peripheral area data to obtain a data analysis result;
the big data analysis unit is configured to calculate the probability of fire in the target area by using a preset fire judgment tree model based on the data analysis result obtained by the data analysis unit to obtain a probability calculation result;
the early warning unit is configured to perform fire early warning in a target area based on the judgment result obtained by the image analysis unit and the probability calculation result of the big data analysis unit, and specifically includes: if the judgment result judges that the target area has a fire, directly carrying out fire occurrence early warning; and if the probability calculation result of the big data analysis unit shows that the fire in the target area exceeds a set threshold value, performing fire early warning.
2. The system of claim 1, wherein the data analysis unit comprises: the target area data processing unit is configured to perform horizontal division and vertical division on the three-dimensional model of the target area, at least three horizontal areas are obtained through the horizontal division, at least two vertical areas are obtained through the vertical division, and then the target area data are distributed into the corresponding vertical areas and the corresponding horizontal areas; the first data calculation unit is configured to perform data calculation based on the obtained two longitudinal areas, and specifically includes: respectively calculating the average value of the distribution of the carbon dioxide in each longitudinal area, the average value of the humidity distribution of the target area, the average value of the temperature distribution of the target area and the average value of the oxygen concentration distribution of the target area; calculating the sum of each average value to obtain the distribution sum of carbon dioxide in the longitudinal area, the humidity distribution sum of the target area, the temperature distribution sum of the target area and the oxygen concentration distribution sum of the target area; the second data calculation unit is configured to perform data calculation based on the obtained three horizontal areas, and specifically includes: respectively calculating the extreme difference of the distribution of carbon dioxide in each transverse area, the extreme difference of the humidity distribution of the target area, the extreme difference of the temperature distribution of the target area and the extreme difference of the oxygen concentration distribution of the target area; and solving the product value of each average value to obtain the distribution product value of carbon dioxide in the longitudinal area, the humidity distribution product value of the target area, the temperature distribution product value of the target area and the oxygen concentration distribution product value of the target area; a third data calculation unit configured to perform a tie value calculation based on the peripheral area data to obtain an average value of the distribution of carbon dioxide in the peripheral area, an average value of the humidity distribution in the peripheral area, an average value of the temperature distribution in the peripheral area, and an average value of the oxygen concentration distribution in the peripheral area; and simultaneously, calculating the range difference based on the data of the peripheral area to obtain the range difference of the distribution of carbon dioxide in the peripheral area, the range difference of the humidity distribution in the peripheral area, the range difference of the temperature distribution in the peripheral area and the range difference of the oxygen concentration distribution in the peripheral area.
3. The system of claim 2, wherein the big data analysis unit calculates the probability of fire in the target area using a preset big data decision tree model from the data analysis result obtained by the big data analysis unit, and the method of obtaining the probability calculation result comprises: constructing a fire judgment tree model, extracting fire big data from a cloud end as a training sample S of the judgment tree model, obtaining fire characteristic attributes according to the training sample S and using the fire characteristic attributes as input variables x of the judgment tree modeli(ii) a The fire signature attributes include at least: the first data calculation unit, the second data calculation unit and the third data calculation unit calculate the obtained results; each input variable xiAll have their corresponding classification xijWhere i is 1, 2, …, n, j is represented by its corresponding xiDetermining a classification value; according to the fire characteristic attribute, introducing offset correction variables which are respectively as follows: average value a of distribution of carbon dioxide in each longitudinal region1Average value a of humidity distribution in target area2Average value a of temperature distribution in target region3And the average value a of the oxygen concentration distribution in the target region4(ii) a According to said training sample SSelecting the optimal branch variable of the judgment tree model according to the fire occurrence mutation gain rate T; extracting the data analysis result obtained by the data analysis unit and cutting branches from bottom to top to obtain the fire diagnosis result output variable CkWherein k is 1, 2 and 3; c1、C2And C3Respectively corresponding to possible, no and yes; the introduced diagnosis correction variable ratio is: extreme difference in carbon dioxide distribution in each cross-sectional area b1Extreme difference in humidity distribution in target area b2Extreme difference in temperature distribution in target region b3And the extreme difference b of the oxygen concentration distribution in the target area4(ii) a Constructing a naive Bayes model of the fire, extracting characteristic attribute data containing the screened judgment tree model from big fire data, reconstructing a training sample D, and extracting all output variables C in the judgment tree model1The node of (2) obtains the characteristic attribute classification x passed by each node from top to bottomijAnd defining the characteristic attribute set Y owned by the r-th noderComprises the following steps: y isr＝{y1，y2，...，ymM is the number of characteristic attributes owned by the corresponding node, and the output variable C on the r-th node is obtained by calculation by using a Bayes formula1Probability of fire P (C)1|y1*y2*...*ym)。
4. The system of claim 3, wherein when extracting the fire big data containing the characteristic attribute data after screening the judgment tree model and reconstructing the training sample D, the characteristic attribute data is corrected by using the characteristic correcting variable; the feature correcting variables include: distribution and value d of carbon dioxide in longitudinal region1Target area humidity distribution and value d2Target area temperature distribution and value d3And the oxygen concentration distribution and the value d of the target area4。
5. The system of claim 4, wherein the output variable at the r-th node calculated using bayesian formula is C1Probability of fire P (C)1|y1*y2*...*ym) Then, the first peripheral correction variable will also be used for correction; the first peripheral correcting variable includes: average value s of distribution of carbon dioxide in peripheral region1Average value s of humidity distribution in peripheral region2Average value s of temperature distribution in peripheral region3And the average value s of the oxygen concentration distribution in the peripheral region4。
6. The system of claim 5, wherein the output variable at the r-th node calculated using bayesian formulation is C1Probability of fire P (C)1|y1*y2*...*ym) Thereafter, the result will also be corrected using the second peripheral correction variable; the second peripheral correcting variable includes: extreme difference s in distribution of carbon dioxide in peripheral region5Extreme difference s in the humidity distribution in the peripheral region6Extreme difference s in temperature distribution in peripheral region7And the extreme difference s of the oxygen concentration distribution in the peripheral region8。
7. The system of claim 6, wherein the method of correcting using the first peripheral correction variable comprises: the input variables are calculated as follows: c1*(0.1s1+0.2s2+0.3s3+0.4s4) The result obtained is used as a new input variable C1。
8. The system of claim 7, wherein the method of correcting using the second peripheral correcting variable comprises: probability of fire P (C)1|y1*y2*...*ym) After calculation using the following formula: p (C)1|y1*y2*...*ym)*(0.1S5+0.2s6+0.3s7+0.4s8) The result is obtained as a new probability of fire P (C)1|y1*y2*...*ym)。
9. The system of claim 8, wherein the fire occurrence catastrophe gain rate T is calculated as follows:
t＝Info(S)-Info(Xi)；T＝t/Info(Xi) (ii) a Wherein | S | is the total number of samples of the training sample S; freq (C)kAnd S) is the term C in the training sample SkThe number of samples of fire-like diagnostic results; freq (c)kxij) Classifying the input variable xx in the training sample S into xijIs of CkThe number of samples of fire-like diagnostic results; x is the number ofiFor inclusion of input variable x in training sample SiThe number of samples of (a); x is the number ofijFor inclusion of input variable x in training sample SiThe classification value is xijThe number of samples of (a); info (S) is the information entropy of the training sample S; info (X)i) As fire characteristic attribute xiConditional entropy in the training sample S; info (x)ij) Classifying x for fire signature attributesijConditional entropy in the training sample S; t is fire characteristic attribute xiThe fire is increased abruptly.
10. Fire early warning method based on big data simulation based on the system of one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110743365.3A CN113435848B (en) | 2021-06-30 | 2021-06-30 | Fire early warning system and method based on big data simulation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110743365.3A CN113435848B (en) | 2021-06-30 | 2021-06-30 | Fire early warning system and method based on big data simulation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113435848A true CN113435848A (en) | 2021-09-24 |
| CN113435848B CN113435848B (en) | 2022-05-17 |
Family
ID=77758601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110743365.3A Active CN113435848B (en) | 2021-06-30 | 2021-06-30 | Fire early warning system and method based on big data simulation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113435848B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114237072A (en) * | 2022-02-28 | 2022-03-25 | 南京迈特望科技股份有限公司 | Intelligent household door lock integrated control system and method applying cloud control technology |
| CN114255562A (en) * | 2022-01-26 | 2022-03-29 | 山东奥深智能工程有限公司 | Wisdom fire control early warning system based on thing networking |
| CN115063942A (en) * | 2022-08-04 | 2022-09-16 | 广东广宇科技发展有限公司 | Fire-fighting fire re-ignition monitoring and early warning method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090315722A1 (en) * | 2008-06-20 | 2009-12-24 | Billy Hou | Multi-wavelength video image fire detecting system |
| CN109448295A (en) * | 2018-11-24 | 2019-03-08 | 石家庄市圣铭科技有限公司 | A kind of forest, grassland fireproofing prewarning monitoring system |
| CN110097727A (en) * | 2019-04-30 | 2019-08-06 | 暨南大学 | Forest Fire Alarm method and system based on fuzzy Bayesian network |
| WO2020111934A1 (en) * | 2018-11-29 | 2020-06-04 | Mimos Berhad | A method and system for detection of natural disaster occurrence |
| CN111915847A (en) * | 2020-08-13 | 2020-11-10 | 成都万江港利科技股份有限公司 | Refined rainfall forecasting system and early warning method thereof |
| CN112613483A (en) * | 2021-01-05 | 2021-04-06 | 中国科学技术大学 | Outdoor fire early warning method based on semantic segmentation and recognition |
| CN112950880A (en) * | 2021-01-26 | 2021-06-11 | 特斯联科技集团有限公司 | Fire early warning method and system based on big data |
| CN113011224A (en) * | 2019-12-19 | 2021-06-22 | 李韵涵 | Coal mine fire early warning method based on video image |
-
2021
- 2021-06-30 CN CN202110743365.3A patent/CN113435848B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090315722A1 (en) * | 2008-06-20 | 2009-12-24 | Billy Hou | Multi-wavelength video image fire detecting system |
| CN109448295A (en) * | 2018-11-24 | 2019-03-08 | 石家庄市圣铭科技有限公司 | A kind of forest, grassland fireproofing prewarning monitoring system |
| WO2020111934A1 (en) * | 2018-11-29 | 2020-06-04 | Mimos Berhad | A method and system for detection of natural disaster occurrence |
| CN110097727A (en) * | 2019-04-30 | 2019-08-06 | 暨南大学 | Forest Fire Alarm method and system based on fuzzy Bayesian network |
| CN113011224A (en) * | 2019-12-19 | 2021-06-22 | 李韵涵 | Coal mine fire early warning method based on video image |
| CN111915847A (en) * | 2020-08-13 | 2020-11-10 | 成都万江港利科技股份有限公司 | Refined rainfall forecasting system and early warning method thereof |
| CN112613483A (en) * | 2021-01-05 | 2021-04-06 | 中国科学技术大学 | Outdoor fire early warning method based on semantic segmentation and recognition |
| CN112950880A (en) * | 2021-01-26 | 2021-06-11 | 特斯联科技集团有限公司 | Fire early warning method and system based on big data |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114255562A (en) * | 2022-01-26 | 2022-03-29 | 山东奥深智能工程有限公司 | Wisdom fire control early warning system based on thing networking |
| CN114237072A (en) * | 2022-02-28 | 2022-03-25 | 南京迈特望科技股份有限公司 | Intelligent household door lock integrated control system and method applying cloud control technology |
| CN115063942A (en) * | 2022-08-04 | 2022-09-16 | 广东广宇科技发展有限公司 | Fire-fighting fire re-ignition monitoring and early warning method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113435848B (en) | 2022-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113435848B (en) | Fire early warning system and method based on big data simulation | |
| Kingra et al. | Application of remote sensing and GIS in agriculture and natural resource management under changing climatic conditions. | |
| Duane et al. | Predictive modelling of fire occurrences from different fire spread patterns in Mediterranean landscapes | |
| Gentine et al. | Land–atmosphere interactions in the tropics–a review | |
| Baldocchi et al. | Does day and night sampling reduce spurious correlation between canopy photosynthesis and ecosystem respiration? | |
| de Almeida et al. | Improvements of the MODIS Gross Primary Productivity model based on a comprehensive uncertainty assessment over the Brazilian Amazonia | |
| Liu et al. | Combined effects of climate and land management on watershed vegetation dynamics in an arid environment | |
| França et al. | Pre-harvest sugarcane burning emission inventories based on remote sensing data in the state of São Paulo, Brazil | |
| Hirano et al. | Energy balance and evapotranspiration changes in a larch forest caused by severe disturbance during an early secondary succession | |
| Meng et al. | Landsat-based monitoring of southern pine beetle infestation severity and severity change in a temperate mixed forest | |
| Faramarzi et al. | Detection of vegetation changes in relation to normalized difference vegetation index (NDVI) in semi-arid rangeland in western Iran | |
| Dolman et al. | The role of the land surface in Sahelian climate: HAPEX-Sahel results and future research needs | |
| Berger et al. | The impact of rain events on CO2 emissions from contrasting land use systems in semi-arid West African savannas | |
| Zerouali et al. | A cloud-integrated GIS for forest cover loss and land use change monitoring using statistical methods and geospatial technology over northern Algeria | |
| CN115424136A (en) | Forest canopy health evaluation method and system combining remote sensing and forest map | |
| Wu et al. | Assessing evapotranspiration observed from ECOSTRESS using flux measurements in agroecosystems | |
| de Oliveira Silveira et al. | Estimating aboveground biomass loss from deforestation in the savanna and semi-arid biomes of brazil between 2007 and 2017 | |
| Tatishvili et al. | The Use of Structured Data for Drought Evaluation in Georgia | |
| Krupa et al. | Considerations for establishing relationships between ambient ozone (O3) and adverse crop response | |
| Calle et al. | Forest fires and remote sensing | |
| van Dijk et al. | 2 Climate variability and institutional fexibility | |
| Sudiana et al. | Assessing forest fire potential in Kalimantan Island, Indonesia, using satellite and surface weather data | |
| Laurence et al. | Estimation of the spatial pattern of surface relative humidity using ground based radar measurements and its application to disease risk assessment | |
| Yagci et al. | Mapping and monitoring of soil moisture, evapotranspiration, and agricultural drought | |
| Shobairi et al. | Vegetation Fractional Coverage (VFC) Estimation of Planted and Natural Zones Based on Remote Sensing |
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 |