CN110097727A - Forest Fire Alarm method and system based on fuzzy Bayesian network - Google Patents
Forest Fire Alarm method and system based on fuzzy Bayesian network Download PDFInfo
- Publication number
- CN110097727A CN110097727A CN201910358732.0A CN201910358732A CN110097727A CN 110097727 A CN110097727 A CN 110097727A CN 201910358732 A CN201910358732 A CN 201910358732A CN 110097727 A CN110097727 A CN 110097727A
- Authority
- CN
- China
- Prior art keywords
- fire
- forest
- probability
- unmanned plane
- module
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 238000007689 inspection Methods 0.000 claims abstract description 25
- 239000000779 smoke Substances 0.000 claims description 20
- 238000005286 illumination Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 11
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 9
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 235000019504 cigarettes Nutrition 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 2
- 229910052799 carbon Inorganic materials 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims description 2
- 230000003647 oxidation Effects 0.000 claims 1
- 238000007254 oxidation reaction Methods 0.000 claims 1
- 239000003500 flue dust Substances 0.000 abstract description 5
- 239000007789 gas Substances 0.000 description 13
- 238000012544 monitoring process Methods 0.000 description 11
- 238000012549 training Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910002090 carbon oxide Inorganic materials 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000001314 paroxysmal effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
-
- 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
- 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
-
- 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
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/10—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using wireless transmission systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Abstract
The present invention is the Forest Fire Alarm method and system based on fuzzy Bayesian network, belongs to security against fire field, the method is as follows: the multiple sensors of UAV flight carry out inspection to forest along setting path, and the Data Concurrent for sensing running region in real time is sent to earth station；Earth station combines local fine day number and inflammable plant number to carry out inflammable grade classification processing, carries out fire alarm according to temperature, humidity, flue dust, gas information and just judges；After each sensing data of ground station reception, sensing data is handled using fuzzy Bayesian network, calculates and obtains fire probability；When fire probability is higher, earth station by fire alarm signal, whether there is fire, fire real-time condition and location information to be sent to forest management center；When fire probability is lower, unmanned plane is along setting path constant-level flight.The present invention is handled sensing data by fuzzy Bayesian network algorithm, can accurately calculate fire probability, accurately knows fire condition at the first time convenient for related personnel.
Description
Technical field
The present invention relates to security against fire fields, and in particular to Forest Fire Alarm method based on fuzzy Bayesian network and
System.
Background technique
The definition of forest fire is: in wood land, the paroxysmal combustion for causing to lose the large stretch of forest artificially controlled
It burns, and rate of propagation is very fast.Forest fire protection is the important component prevented and reduced natural disasters of China, protection to the forest reserves and
The development of excellent ecological environment is all of great importance, and has significant impact to the development of Chinese energy.
The mode that manually lookout, monitoring remote video, satellite remote sensing and unmanned plane patrol mainly is adopted in forest fire protection monitoring.
Ren Gong, which looks at mode, to be taken turns at keeping watch within operator on duty 24 hours in commanding elevation She Li lookout post, due to artificial carelessness and fault,
So that many fire behaviors fail to find early, delay is put out the fire the time for meeting, causes serious consequence.Monitoring remote video mode is in forest zone
A large amount of video surveillance point is built, monitoring point is equipped with video camera, real-time pictures are transmitted to monitoring by wired or wireless network
Center is monitored in real time by center personnel.Which does not need directly to accredit personnel and goes up manually very to forest zone scene, but remote
Hardly possible identification early stage fire behavior.Especially visible light camera monitoring system, at night, almost without the light of detectable spectral region
According to, it is almost very dark on video image, it is difficult to find and judge forest fires.Even if changing thermal infrared video monitoring into, forest ring
Border is complicated, is easy the presence of monitoring dead point, to cause a hidden trouble.Satellite remote sensing mode is by finding after the processing to remote sensing photo
Forest fires, but satellite can only find the forest fires of large area, can not find in fire early stage；There is also remote sensing images resolution ratio simultaneously
Insufficient, the problems such as flexibility is poor.Unmanned plane patrols comparatively a little more prominent, and well adapting to property and in real time in the air
Property.
In the prior art, sensor, setting infrared video camera or camera are carried on unmanned plane, by infrared photography
The shooting image of instrument carries out the processing such as thermal imagery difference, smog analysis；Or video is shot by camera and carries out figure in earth station
As processing, identify that the possibility of fire occurs or a situation arises.Since infrared thermal imager is imaged by the temperature difference, and the general objectives temperature difference
All less, therefore infrared chart image contrast is low, keeps resolve minutiae less able, cannot see mesh clearly through transparent barrier
Mark；And common camera video image processing method cannot be accurately identified that fire may occur or a situation arises.
Summary of the invention
Present invention seek to address that the technical problems existing in the prior art, on the one hand propose based on fuzzy Bayesian network
Forest Fire Alarm method, handled according to sensing data, local fine day number and inflammable plant number graduation, intuitive judgment should
Whether region has a possibility that fire occurs；When that fire may occur, by fuzzy Bayesian network algorithm to sensor number
According to being handled, fire probability can be accurately calculated, to carry out work of suing and labouring.
Another aspect of the present invention is to propose the forest fire early-warning system based on fuzzy Bayesian network.
The present invention is based on the Forest Fire Alarm methods of fuzzy Bayesian network, comprising:
S1, UAV flight's temperature sensor, sense smoke sensor, humidity sensor and gas sensor are along setting path pair
Forest carries out inspection, and the Data Concurrent for sensing running region in real time is sent to earth station；And by forest image, unmanned plane running region
Location information be transmitted to earth station；
S2, earth station combine local fine day number and inflammable plant number to carry out inflammable grade classification processing, according to temperature, wet
Degree, flue dust, gas information carry out fire alarm and just judge；
After S3, each sensing data of ground station reception step S1, sensing data, meter are handled using fuzzy Bayesian network
Calculate obtain fire probability, if fire probability is higher, continue with unmanned plane transmission sensing data and intuitive judgment without
The man-machine forest image sent back, obtains the real-time condition of the region forest；If fire probability is lower, earth station, which sends, to continue to patrol
Signal is examined to unmanned plane, unmanned plane continues to carry out inspection to forest along setting path；
When S4, fire probability are higher, earth station by fire alarm signal, whether have fire, fire real-time condition and position
Confidence breath is sent to forest management center；When fire probability is lower, the unmanned plane is along setting path constant-level flight.
In a preferred embodiment, in the step S3, earth station uses fuzzy Bayesian network algorithm process sensor
The process of data is as follows:
S31, using the Parameter Learning Algorithm of structure learning algorithm and successive ignition optimizing, establish the shellfish of fire early-warning system
This network model of leaf, utilizes established model, is tentatively judged according to temperature, humidity, smokescope and carbonomonoxide concentration
Open fire probability, smoldering fire probability and without fiery probability；
S32, the fuzzy controller for establishing fire early-warning system, by open fire probability, smoldering fire probability and without fiery probability three
Input of the signal as fuzzy controller, carries out fuzzy logic processes and anti fuzzy method is handled, and it is general to finally obtain accurate fire
Rate.
From the above technical scheme, Forest Fire Alarm method of the present invention according to sensing data, local fine day number and
Inflammable plant number carries out graduation processing, can be used for whether the intuitive judgment region has a possibility that fire occurs, and sends out when possible
When calamity of lighting a fire, sensing data is handled by fuzzy Bayesian network algorithm, fire probability can be accurately calculated, be convenient for
Related personnel accurately knows fire condition at the first time；Fire can be predicted in time by fire alarm signal, be conducive to forest
Protection related personnel is ready, and handles fire as early as possible, reduces loss.And unmanned function carries out forest image transmitting simultaneously, just
Field condition is observed in earth station, can be reduced the operand of earth station, the inspection range accelerated polling rate, expand unmanned plane；
The continuous stable data of the readily available sensor of unmanned plane constant-level flight are handled convenient for follow-up data.Forest fire of the present invention is pre-
Alarm method realizes automatic monitoring, automatic identification and automatic feedback, more efficient, more intelligently conserve forests.
The present invention is based on the forest fire early-warning systems of fuzzy Bayesian network, including at least one unmanned plane and ground
It stands；
Unmanned plane carries out inspection to forest according to respective setting path, be provided on unmanned plane processor, temperature sensor,
Feel smoke sensor, humidity sensor, gas sensor, GPS module, wireless transport module, camera and driving assembly, temperature passes
The humidity input terminal of the connection of the temperature input of sensor output end and processor, humidity sensor output end and processor connects,
The sense cigarette input terminal for feeling smoke sensor output end and processor connects, gas sensor output end, camera output end respectively with
The video inputs of processor connect；The control terminal of driving assembly and the drive output of processor connect；
Earth station includes the wireless communication module being wirelessly connected with the wireless transport module of unmanned plane, by obscuring Bayes
The data processing platform (DPP) and gsm module that network algorithm handles sensing data, the output end of wireless communication module with
Data processing platform (DPP) connection, the output end of data processing platform (DPP) and the input terminal of gsm module connect；Ground station reception unmanned plane hair
The sensing data and fire alarm signal sent；Gsm module is connect by wireless network with forest management center.
From the above technical scheme, forest fire early-warning system of the present invention passes through temperature sensor, feels smoke sensor, is wet
Temperature, flue dust, humidity and the gas information of sensor, gas sensor acquisition unmanned plane running region are spent, and is classified
Processing intuitively rough can judge whether the region has a possibility that fire occurs；Data processing platform (DPP) is by obscuring Bayes
Network algorithm can be accurately identified that fire may occur or a situation arises, accurately know fire feelings at the first time convenient for related personnel
Condition；It is convenient for notifying related management personnel to prevent and handle in time fire information by gsm module.The system can prop up simultaneously
More unmanned planes are held, inspection range is wide；High module real-time monitoring unmanned plane is surveyed perpendicular to the height on ground, height is will test and inputs
To processor, the storage unit inside processor stores preset height, will monitoring height acquisition difference compared with preset height,
Driving assembly operation is controlled according to difference processor, adjusts unmanned plane height, makes its constant-level flight, and then obtain shooting angle phase
Same stabilization image is conducive to subsequent image processing.
Detailed description of the invention
Fig. 1 is Forest Fire Alarm method flow diagram in the embodiment of the invention.
Fig. 2 is the Bayesian network model structure chart of Forest Fire Alarm method in the embodiment of the invention.
Fig. 3 is the system block diagram of forest fire early-warning system in the embodiment of the invention.
Fig. 4 is forest fire early-warning system functional diagram in the embodiment of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to
The embodiment of attached drawing description is exemplary, and for explaining only the invention, and is not construed as limiting the claims.
In the description of the present invention, it is to be understood that, term " longitudinal direction ", " transverse direction ", "upper", "lower", "front", "rear",
The orientation or position of the instructions such as "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" are based on the figure
Orientation or positional relationship, is merely for convenience of describing the description that simplifies of the invention, rather than the device of indication or suggestion meaning or
Element must have a particular orientation, be constructed and operated in a specific orientation, therefore be not considered as limiting the invention.
In the description of the present invention, unless otherwise specified and limited, it should be noted that term " installation ", " connected ",
" connection " shall be understood in a broad sense, for example, it may be mechanical connection or electrical connection, the connection being also possible to inside two elements can
, can also indirectly connected through an intermediary, for the ordinary skill in the art to be to be connected directly, it can basis
Concrete condition understands the concrete meaning of above-mentioned term.
Fig. 1 show a kind of flow chart of embodiment of Forest Fire Alarm method of the present invention, comprising steps of
S1, UAV flight's temperature sensor, sense smoke sensor, humidity sensor and gas sensor are along setting path pair
Forest carries out inspection, and the Data Concurrent for sensing running region in real time is sent to earth station；Forest image is transmitted to earth station, is convenient for
Field condition is observed by earth station, and the synchronous location information for sending unmanned plane running region is to earth station.
In step sl, the setting method of the inspection route of unmanned plane are as follows: use the starting point of GPS module setting inspection route
And terminal, optimal path is planned by Grid decomposition.In the transmission of every batch of sensing data, binding has the real-time position of unmanned plane
Information；And/or in the transmission of fire alarm signal, binding has the real-time location information of unmanned plane, is convenient for sensing data and fire
Calamity pre-warning signal is accurately corresponding with location information.
S2, earth station combine local fine day number and inflammable plant number to carry out inflammable grade classification processing, according to temperature, wet
Degree, flue dust, gas information carry out fire alarm and just judge:
Local fine day number and inflammable plant number can be used for whether the intuitive judgment region has a possibility that fire occurs, may
Property it is larger when, send unmanned plane carry out inspection；
When temperature is greater than or equal to temperature alarming threshold value and/or humidity less than or equal to humidity alarm threshold value and/or one
When content of carbon oxide is greater than or equal to carbon monoxide content threshold value and/or smoke content greater than or equal to smoke content threshold value, increase
Add the frequency for sending data as fire alarm signal to earth station, unmanned plane hovering, real-time transmission corresponding data to earth station；
When temperature be lower than temperature alarming threshold value, and humidity be higher than humidity alarm threshold value, and carbon monoxide content be lower than an oxygen
Change carbon content threshold value, and smoke content be lower than smoke content threshold value when, unmanned plane along setting path continue to forest carry out inspection.
After S3, each sensing data of ground station reception step S1, sensing data, meter are handled using fuzzy Bayesian network
Calculate obtain fire probability, if fire probability is higher, continue with unmanned plane transmission sensing data and intuitive judgment without
The man-machine forest image sent back, obtains the real-time condition of the region forest；If fire probability is lower, earth station, which sends, to continue to patrol
Signal is examined to unmanned plane, unmanned plane continues to carry out inspection to forest along setting path.
When S4, fire probability are higher, earth station by fire alarm signal, whether have fire, fire real-time condition and position
Confidence breath is sent to forest management center；When fire probability is lower, the unmanned plane is along setting path constant-level flight.
Fuzzy control system is to design controller to the control experience and knowledge of controlled system according to people, especially suitable for
It is difficult to the complex object that models or can not model, is easily accepted by people, and algorithm is simple, it is easy to accomplish, and have extremely strong Shandong
Stick.
Bayesian network is also known as belief network, is the extension of Bayes method, is current uncertain knowledge expression and reasoning neck
One of most effective theoretical model in domain.One Bayesian network includes a directed acyclic graph (Directed Acyclic
Graph, DAG) and a conditional probability table set.Each node of DAG indicates a stochastic variable, and can be directly to see
Variable or hidden variable are surveyed, and the directed edge between node represents the cross correlation between node and (is directed toward its sub- section by father node
Point), relationship between expression intensity is carried out with conditional probability, father node does not carry out information representation with prior probability, indicates random and becomes
Condition between amount relies on, and stochastic variable can be the abstract of any problem, such as: test value, observation phenomenon, opinion are consulted；Item
Each of part probability tables element corresponds to unique node in DAG, stores this node for its all direct precursor node
Combination condition probability.Bayesian network has a particularly important property, is exactly that we assert each node before its is direct
After driving the value formulation of node, for this node condition independently of its all indirect forerunner's predecessor node, this property is much like
Markov process.In fact, Bayesian network can be regarded as the nonlinear extensions of Markov chain.Bayesian network is suitable for expression
With analysis is uncertain and probabilistic event, can be from endless applied to the decision for conditionally relying on various control factor
Entirely, reasoning is made in inaccurate or uncertain knowledge or information.
In the present embodiment, fuzzy Bayesian network algorithm is the compound of Fuzzy control system and Bayesian network.Its
In, Bayesian network is a kind of probabilistic graphical models, including directed acyclic graph and conditional probability table set, and Fuzzy control system
The system for being that by fuzzy control.Unmanned plane can also be spaced short period inner sense measured data, such as interval 1 second；Location information
Earth station can be sent to after continuous acquisition, it is preferred that its acquisition time is less than sensor and senses the time.
In the present embodiment, because when a certain region of forest may occur or fire occurs, the temperature meeting in the region
It increases, smoke content increases, and carbon monoxide content increases, humidity decline, therefore when the continuous sunny number in the region, inflammable plant
Number is more, and meets and detect that temperature is greater than or equal to temperature alarming threshold value and humidity less than or equal to humidity alarm threshold value, and
Carbon monoxide content is greater than or equal to carbon monoxide content threshold value and smoke content is greater than or equal in smoke content threshold condition
Either one or two when, the processor control driving assembly inside unmanned plane makes unmanned plane hover in the overhead, continues to pass in real time
Sensing data is sent, earth station's processing is sent to, and continue the forest image of shooting lower section, is sent to related personnel and intuitively sentences
It is disconnected.When five conditions are not satisfied, unmanned plane senses the sensing data below the region and shoots forest image and transmit
To earth station, continues navigation shooting along projected route and send fire alarm signal to earth station, at the same time, earth station is also real
When handle these data and observe forest image carry out intuitive judgment, have found that it is likely that the fire dangerous situation of generation or generation in time, temperature
Degree detection, flue dust detection, Humidity Detection, gas detection are used together, and using four re-detections, are avoided because of temperature sensor, sense cigarette
The fault of fire inspection caused by sensor, humidity sensor and gas sensor chance failure.Temperature alarming threshold value, smoke content
Alarm threshold value, humidity alarm threshold value, carbon monoxide content alarm threshold value are stored in the storage unit inside unmanned plane processor,
Can test of many times obtain, or empirically set.
In the present embodiment, fire alarm signal and when issuing the signal location information earth station meeting of unmanned plane and
When upload to forest management center, earth station is to the fuzzy Bayesian network processing result of sensing data together with location information
Forest management center, unmanned plane and earth station's mode transmitting fire alarm signal and continuation inspection by wireless communication can be uploaded to
Signal can be transmitted by data radio station, can also be transmitted by modes such as WIFI, RFID.
In the present embodiment, unmanned plane can constant-level flight, the sensing data of readily available continuous-stable, convenient for subsequent
Data processing, flying height can be 15 meters, 20 meters, 25 meters or 30 meters etc..
In the present embodiment, in the step S3, earth station uses fuzzy Bayesian network algorithm process sensor number
According to process it is as follows:
S31, fire early-warning system is carried out using structure learning algorithm and using the Parameter Learning Algorithm of successive ignition optimizing
Bayesian network establish, Fig. 2 show the model structure of the embodiment.
The construction of Bayesian network is a complicated task, needs the participation of knowledge engineer and domain expert.In reality
It may be to intersect to carry out and constantly improve repeatedly in border.Needed for the construction of the Bayesian network of equipment oriented diagnosis application
The information wanted comes from multiple channel, such as Hardware Description Manual, production process, test process, repair information and expertise.First
Equipment fault is divided into classification that is each mutually indepedent and completely including, and (each fault category should at least have the boundary that can be distinguished
Limit), Bayesian network model is then built respectively to each fault category, it should be noted that diagnostic model is only breaking down
Shi Qidong, there is no need to model to equipment normal condition.Usual equipment fault is as caused by one or several reasons, these reasons
It may be caused again by the reason of one or several lower levels time.After setting up the node relationships of network, it is also necessary to carry out probability and estimate
Meter.Specific method is assumed that in the case where certain failure cause occurs, and estimates the conditional probability of each node of the failure cause,
The method of this localization probability Estimation can greatly improve efficiency.
1) structure learning algorithm
Bayesian network structure learning is exactly to find one and training under the premise of giving a data sample set D
Sample set D matches best network structure.Algorithm for Bayesian Networks Structure Learning uses K2 scoring algorithm herein, is made with P (G, D)
For score function:
Wherein, P (G) is the prior probability of network structure G；xiFor network node, xiHaveDeng more
A state, i.e.,The corresponding father node of node integrates as Π i, πiFor the configuration of Π i, arrange suitable
Sequence is 1,2,3 ..., qi；NijkIt is quantity the case where meeting "and/or" in data set D, that is, meets
The quantity of the sensing data of " increasing the frequency for sending data as fire alarm signal to earth station "；riIndicate some network
Node (such as xi) riA quantity of state.
Citing son for, if an expert advice there are a specific side or a partial structurtes, meet to
Fixed network structure should be given a higher prior probability.If there is no prior probability to network structure, or do not have
Special preferential network structure is uniformly distributed then prior probability P (G) can be assumed obedience, i.e. P (G)=c, c are normal
Amount.Given a network structure G, conditional probability θijkIt can be estimated by Bayesian estimator:
θijk=E (θijk| D, G)=(Nijk+1)/(Nij+ri)
Wherein, E indicates expectation；Bayes's scoring can be explained are as follows: if for all network structure G, a network
Structure G0There is P (G0, D) and >=P (G, D), then for current data set D, G0It is to be best suitable for D in Bayes's scoring meaning
Network structure；During algorithm is realized, usually formula is simplified, replaces P (G, D) with log (P (G, D)), thus
Obtain the decomposed form of score function:
2) Parameter Learning Algorithm
The parameter learning of Bayesian network on the basis of sample data, seeks the probability distribution of each node of network.It utilizes
Network topology structure and training sample set and priori knowledge determine that the conditional probability at each node of Bayesian network model is close
Degree is denoted as P (θ | G, D).Algorithm for Bayesian Networks Parameter Learning is actually to solve to converge to local nodes optimized parameter
Process.Then initial configuration first finds maximum a posteriori probability it is assumed that and restraining optimal value by two step of iteration E and M.It is right
Data carry out maximal possibility estimation, and simulation is best suitable for the parameter of structure, the specific steps are as follows:
(1) E walks (expectation)
Wherein, E is desired value；D is training sample；Indicate the optimized parameter found, xiCodomain beqiIt is configuration πiPut in order 1,2,3 ..., qi；NijkIt is to meet variate-value in data set D
Xi=xi kAnd πiThe condition frequency of=j；yiIt is the data amount check lost in D；ShIt is Bayesian network knot
Structure selection is assumed.
(2) M walks (maximum estimated)
Maximal possibility estimation function:
MAP estimation:
Wherein, N 'ijkIt is the abundant statistical factors of priori；NijkIt is the abundant statistical factors of sample data.
S32, the fuzzy controller for establishing fire early-warning system.
Using Bayesian network, open fire probability is tentatively judged according to temperature, smokescope and carbonomonoxide concentration, is glowed
Fiery probability and without fiery probability.It must be known by relevant probability between each state using Bayesian network, obtain these parameters
Process is called training.As training Markov model, some known data of training Bayesian network.For example it is instructing
Practice network above, needs to know the related situation such as some cardiovascular diseases and smoking, family's medical history.Compared to markov
The training of chain, Bayesian network is more complicated, and theoretically, it is a NP-complete problem, that is to say, that existing rank
The algorithm that section can not completed in polynomial time.But for certain applications, this training process be can simplify, and
Computationally efficiently realize.
Then, the foundation of the fuzzy controller of fire early-warning system is carried out.Although Bayesian network is dense using temperature, smog
Degree and carbonomonoxide concentration tentatively judge open fire probability, smoldering fire probability, without fiery probability, still, only according to Bayesian network
These three output signals of network output can not accurately judge whether there is fire generation and fire behavior size.Therefore, by pattra leaves
The open fire probability of this network, smoldering fire probability and the input without fiery probability these three output signals as fuzzy controller, carry out
Fuzzy logic processes and anti fuzzy method are handled, and accurate fire probability are finally obtained, to obtain forest fire identifying system
Output accuracy and fault-tolerant ability.
1) fuzzy rule is established
Classify to fire probability, respectively open fire probability, smoldering fire probability, without fiery probability as burning node, combustion
Burn node graduation, open fire probability is divided into that open fire probability big (PB), (PM), open fire probability small (PS), open fire are general in open fire probability
Four grades of rate zero (NP), respectively 0,1,2,3；Smoldering fire probability is respectively divided into smoldering fire probability big (PB), in yin fire probability
(PM), four yin fire probability small (PS), yin fire probability zero (NP) grades, respectively 0,1,2,3；No fiery probability is divided into without fiery probability
Greatly (PB), without (PM) in fiery probability, without small (PS) three grades of fiery probability, respectively 0,1,2；
Fuzzy rule form is " if open fire probability is AiAnd smoldering fire probability is BiAnd no fiery probability is Ci, then fire behavior
Probability of happening is Pi".Wherein Ai、BiAnd CiOpen fire probability, smoldering fire probability, the fuzzy quantization grade without fiery probability are respectively indicated,
PiIt is the quantification gradation of fire behavior probability of happening.According to the specialist field Heuristics of forest fire, and try through a large number of experiments
It gathers, obtains 48 fuzzy inference rules, such as:
If (open fire probability is NP) and (smoldering fire probability is NP) and (without fiery probability is PS) then (fire probability
is PS)；If (open fire probability is NP) and (smoldering fire probability is NP) and (without fiery probability is PM) then (fire probability is
NP)。
2) fuzzy reasoning
With above-mentioned fuzzy control rule " if x is AiAnd y is BiAnd z is Ci, then u is Pi" for, then corresponding mould
Paste implication relation PiIs defined as:
Ri=(Ai×Bi×Ci×Pi)
Wherein, x indicates that open fire probability, y indicate that smoldering fire probability, z indicate that, without fiery probability, u indicates fire behavior probability of happening.It is right
All Fuzzy implication relationships take union, show that fuzzy relation corresponding to all control rules is as follows:
It 3) is " if x is Ai and y is B for fuzzy control ruleiAnd z is Ci, then u is Pi", then pass through fuzzy reasoning
It can obtain based on fuzzy open fire probability A`, smoldering fire probability B`, without the fire probability P under fiery probability C`iAre as follows:
Pi=(A`and B`and C`) × R
Obtained PiIt is a fuzzy set, needs to carry out precision processing, this process is also referred to as anti fuzzy method.Gravity model appoach
Also referred to as moment method is at present using most anti fuzzy method methods.Its feature is to consider fuzzy quantity for information about comprehensively,
Operation is performed simultaneously to be relatively easy to.
Wherein, wdFor anti fuzzy method value；μ (w) is the reasoning results fuzzy set membership function；W is the supported value on domain.It adopts
Precision processing is carried out to fire probability with gravity model appoach, obtains the accurate output of fire probability:
μpi(ui)=∨ [∧ Ai(x)∧Bi(y)∧Ci(z)∧R(x,y,z,u)]
The open fire probability in the region, smoldering fire probability are calculated by establishing Bayesian network model, without fiery probability, and be sent into
Fuzzy system.For being unable to the region of intuitive judgment forest image, fire probability estimation can be rapidly carried out.Pass through setting fire
Calamity threshold value, can effectively distinguish fire may occur or occur fire with there is no fire, and by the size of fire probability,
It may determine that the severity that fire may occur or fire occurs, make counter-measure in time convenient for administrative staff.
In the present embodiment, since there are certain trueness errors for probability calculation, in order to safety, can more accurately incite somebody to action
Fire threshold value is set as lower value, and such as 30%.In the present embodiment, it may be configured as a constant interval, it can be according to season, day
Gas situation or wind speed size variation value.It, can be by fire such as autumn and winter perhaps high temperature or in the case where having strong wind
Residual value is set as the smaller value in constant interval, on the contrary then be set as the larger value in constant interval.It is detected in this way can
Fire signal can occur and generation fire signal is more acurrate, closer in actual environment, have time enough convenient for administrative staff
Reply, and make most appropriate counter-measure.
In step sl, the setting method of the inspection route of unmanned plane are as follows: use the starting point of GPS module setting inspection route
And terminal, optimal path is planned by Grid decomposition.In the transmission of every batch of sensing data, binding has the real-time position of unmanned plane
Information；And/or in the transmission of fire alarm signal, binding has the real-time location information of unmanned plane, is convenient for sensing data and fire
Calamity pre-warning signal is accurately corresponding with location information.In the present embodiment, optimal path can be for being capable of avoidance and apart from shortest
Path.
In the present embodiment, after the completion of sensing data sensing, or after generation fire alarm signal, real-time position is obtained
Confidence breath, location information data is inserted into sensing data or fire alarm signal.
In step sl, further include illumination set-up procedure, there is enough intensities of illumination, really when guaranteeing that camera is taken pictures
The validity of forest image observed by protecting.Illumination set-up procedure is as follows: sensing intensity of illumination, when intensity of illumination is strong lower than illumination
When spending threshold value, headlamp supplementary light is opened；When intensity of illumination is greater than or equal to intensity of illumination threshold value, headlamp is closed.
In the present embodiment, the illumination intensity value of intensity of illumination threshold value optional dusk or any time at dawn, and store
In memory inside the unmanned plane processor.
Forest fire early-warning system of the present invention, as shown in Figure 3,4, including at least one unmanned plane and earth station.Wherein:
Unmanned plane carries out inspection to forest according to respective setting path, be provided on unmanned plane processor, temperature sensor,
Feel smoke sensor, humidity sensor, gas sensor, GPS module, wireless transport module, camera and driving assembly, temperature passes
The humidity input terminal of the connection of the temperature input of sensor output end and processor, humidity sensor output end and processor connects,
The sense cigarette input terminal for feeling smoke sensor output end and processor connects, gas sensor output end, camera output end and processing
The video inputs of device connect；The control terminal of driving assembly and the drive output of processor connect.Unmanned plane can also be further
Including surveying high module, the height input terminal for surveying high module height output end and processor is connected.
Earth station includes the wireless communication module being wirelessly connected with the wireless transport module of unmanned plane, by obscuring Bayes
The data processing platform (DPP) and gsm module that network algorithm handles sensing data, the output end of wireless communication module with
Data processing platform (DPP) connection, the output end of data processing platform (DPP) and the input terminal of gsm module connect.Ground station reception unmanned plane hair
The sensing data and fire alarm signal sent.Gsm module is connect by wireless network with forest management center, in forest management
The heart is server or the handheld terminal of forest management personnel.
In the present embodiment, camera can be selected high definition and take photo by plane camera, the wireless transport module of unmanned plane and ground
The wireless connection for the wireless communication module stood can pass through data radio station.The interface protocol that general data radio station uses has TTL to connect
Mouthful, RS485 interface and RS232 interface, but there are also CAN-BUS bus interface, frequency have 2.4GHZ, 433MHZ,
900MHZ, 915MHZ, general 433MHZ's is more, because 433MHZ is an open frequency range, along with 433MHZ wavelength is longer,
The advantages such as penetration power is strong are so the 433MHZ that most of civilian users are typically all, distance are differed in 5 kms to 15 kms, very
It is extremely farther.The wireless connection of the wireless communication module of the wireless transport module and earth station of unmanned plane can also pass through such as WIFI etc.
Other radio communications are realized.Driving assembly includes the components such as motor, propeller.MCU+ can be selected in the data processing platform (DPP) of earth station
The high speed data processing device of FPGA isomery.
In the present embodiment, it surveys high module and is based on light wave or the high function of electromagnetic distance measurement principle realization survey.Survey Gao Mo
Block includes the meter for being mounted on infrared transmission module outside the bottom of unmanned engine room and infrared receiving module and processor and being internally integrated
When device；The infrared emission end of the control terminal of infrared transmission module and processor connects, the digital output end of infrared transmission module with
The infrared receiver end of processor connects, and infrared transmission module control interval time t transmitting infrared waves to ground by processor, by
Infrared receiving module receives reflected infrared waves, passes through timer record transmitting and receiving time difference.
Surveying high module can also be using such as flowering structure: including antenna, transmitting match circuit, receiving match circuit and radio frequency core
Piece, radio frequency chip emit modulated analog signal to the input terminal for emitting match circuit, emit the output end and antenna of match circuit
Input terminal connection, the output end of antenna connect with the input terminal of reception match circuit, receives the output end of match circuit and penetrates
The receiving end of frequency chip connects, and radio frequency chip is connect by communication interfaces such as SPI, I2C with processor, when radio frequency chip is with interval
Between t emit modulated analog signal to emitting match circuit, while sending timing commencing signal to processor；Modulated analog signal by
Antenna emits to ground, and reflected electromagnetic wave signal is transferred to reception match circuit by antenna, then reaches radio frequency chip,
Radio frequency chip synchronizes after receiving sends timing pick-off signal to processor, obtains time difference by processor.Due to unmanned plane
Route speed is much smaller compared to the light velocity or velocity of electromagnetic wave, processor time difference obtained divided by after 2 multiplied by the light velocity
Obtain drone flying height.Time t can be positive integer minute, such as 2 minutes, 4 minutes.Processor is by actual measurement flying height and in advance
If flying height is compared processing, so that the power of decision driving assembly increases and decreases.Preferably, antenna can be arranged in perpendicular to the ground
Outside the bottom of unmanned engine room.
In the present embodiment, unmanned plane further includes headlamp and optical sensor, the output end of optical sensor and processing
The illumination input terminal of device connects, and the Lighting control end of processor and the opening end of headlamp connect, and headlamp is set close to camera
It sets, guarantees that there is enough intensities of illumination when camera is taken pictures, it is ensured that intuitively receive the fire condition of forest image.
In the present embodiment, gsm module is connect by wireless network with forest management center, and forest management center is service
Device or the handheld terminal of forest management personnel are convenient for related management personnel timely learning fire information.Gsm module can directly be sent out
It send notifying messages to collect to administrative staff, the server of fire information to forest management center also can be transmitted, administrative staff pass through
Webpage is checked.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention, and in the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Finally it is emphasized that the above description is only a preferred embodiment of the present invention, it is not intended to restrict the invention, it is right
For those skilled in the art, these embodiments can be carried out without departing from the principle and spirit of the present invention
A variety of change, modification, replacement and modification, all within the spirits and principles of the present invention, any modification for being made, equivalent replacement,
Improve etc., it should all be included in the protection scope of the present invention.
Claims (10)
1. the Forest Fire Alarm method based on fuzzy Bayesian network characterized by comprising
S1, UAV flight's temperature sensor, sense smoke sensor, humidity sensor and gas sensor are along setting path to forest
Inspection is carried out, the Data Concurrent for sensing running region in real time is sent to earth station；And by the position of forest image, unmanned plane running region
Confidence breath is transmitted to earth station；
S2, earth station combine local fine day number and inflammable plant number to carry out inflammable grade classification processing, according to temperature, humidity, cigarette
Dirt, gas information carry out fire alarm and just judge；
After S3, each sensing data of ground station reception step S1, sensing data is handled using fuzzy Bayesian network, calculating obtains
Fire probability is obtained, if fire probability is higher, continues with the sensing data and intuitive judgment unmanned plane of unmanned plane transmission
The forest image sent back, obtains the real-time condition of the region forest；If fire probability is lower, earth station, which sends, continues inspection letter
Number to unmanned plane, unmanned plane continues to carry out inspection to forest along setting path；
When S4, fire probability are higher, earth station by fire alarm signal, whether there is fire, fire real-time condition and position to believe
Breath is sent to forest management center；When fire probability is lower, the unmanned plane is along setting path constant-level flight.
2. Forest Fire Alarm method according to claim 1, which is characterized in that in the step S3, earth station is used
The process of fuzzy Bayesian network algorithm process sensing data is as follows:
S31, using the Parameter Learning Algorithm of structure learning algorithm and successive ignition optimizing, establish the Bayes of fire early-warning system
Network model utilizes established model, tentatively judges open fire according to temperature, humidity, smokescope and carbonomonoxide concentration
Probability, smoldering fire probability and without fiery probability；
S32, the fuzzy controller for establishing fire early-warning system, by open fire probability, smoldering fire probability and without three signals of fiery probability
As the input of fuzzy controller, carries out fuzzy logic processes and anti fuzzy method is handled, finally obtain accurate fire probability.
3. Forest Fire Alarm method according to claim 2, which is characterized in that the first deterministic process of step S2 are as follows:
Local fine day number and inflammable plant number are used for whether the intuitive judgment region to have a possibility that fire occurs, and possibility is larger
When, it sends unmanned plane and carries out inspection；
When temperature is greater than or equal to temperature alarming threshold value and/or humidity less than or equal to humidity alarm threshold value and/or an oxidation
When carbon content is greater than or equal to carbon monoxide content threshold value and/or smoke content greater than or equal to smoke content threshold value, increase hair
Send the frequency of data as fire alarm signal to earth station, unmanned plane hovering, real-time transmission corresponding data to earth station；
When temperature be lower than temperature alarming threshold value, and humidity be higher than humidity alarm threshold value, and carbon monoxide content be lower than carbon monoxide
Content threshold value, and smoke content be lower than smoke content threshold value when, unmanned plane along setting path continue to forest carry out inspection；
Structure learning algorithm described in step S31 uses K2 scoring algorithm, is used as score function with P (G, D):
Wherein, P (G) is the prior probability of network structure G；xiFor network node, xiHaveEtc. multiple shapes
State, i.e.,The corresponding father node of node integrates as Π i, πiFor the configuration of Π i, putting in order is 1,
2,3,...,qi；NijkIt is to meet " to increase the frequency for sending data as fire alarm in data set D
Signal is to earth station " sensing data quantity；riIndicate the r of some network nodeiA quantity of state.
4. Forest Fire Alarm method according to claim 2, which is characterized in that Parameter Learning Algorithm described in step S31
To solve the process for converging to local nodes optimized parameter, first initial configuration, then found most by two step of iteration E and M
Big posterior probability it is assumed that and restrain optimal value, maximal possibility estimation is carried out to data, simulation is best suitable for the parameter of structure.
5. Forest Fire Alarm method according to claim 1, which is characterized in that in step sl, the inspection of unmanned plane
The setting method of route are as follows: using the beginning and end of GPS module setting inspection route, best road is planned by Grid decomposition
Diameter.
6. Forest Fire Alarm method according to claim 1, which is characterized in that further include illumination tune in step sl
Synchronizing is rapid: sensing intensity of illumination opens headlamp supplementary light when intensity of illumination is lower than intensity of illumination threshold value；When illumination is strong
When degree is greater than or equal to intensity of illumination threshold value, headlamp is closed.
7. the forest fire early-warning system based on fuzzy Bayesian network, which is characterized in that including at least one unmanned plane and ground
Face station；
Unmanned plane carries out inspection to forest according to respective setting path, and processor, temperature sensor, sense cigarette are provided on unmanned plane
Sensor, humidity sensor, gas sensor, GPS module, wireless transport module, camera and driving assembly, temperature sensor
The humidity input terminal of the connection of the temperature input of output end and processor, humidity sensor output end and processor connects, and feels cigarette
The sense cigarette input terminal of sensor output and processor connection, gas sensor output end, camera output end respectively with processing
The video inputs of device connect；The control terminal of driving assembly and the drive output of processor connect；
Earth station includes the wireless communication module being wirelessly connected with the wireless transport module of unmanned plane, passes through fuzzy Bayesian network
The data processing platform (DPP) and gsm module that algorithm handles sensing data, the output end and data of wireless communication module
Processing platform connection, the output end of data processing platform (DPP) and the input terminal of gsm module connect；What ground station reception unmanned plane was sent
Sensing data and fire alarm signal；Gsm module is connect by wireless network with forest management center.
8. forest fire early-warning system according to claim 7, which is characterized in that the unmanned plane further includes surveying Gao Mo
The height input terminal of block, the height output end and processor of surveying high module connects.
9. forest fire early-warning system according to claim 8, which is characterized in that described to survey high module including being mounted on nothing
The timer that infrared transmission module and infrared receiving module and processor outside the man-machine bilge are internally integrated；Infrared emission
The control terminal of module and the infrared emission end of processor connect, and the digital output end of infrared transmission module and the infrared of processor connect
Receiving end connection, infrared transmission module control interval time t transmitting infrared waves to ground by processor, are connect by infrared receiving module
Reflected infrared waves are received, timer record transmitting and receiving time difference are passed through.
10. forest fire early-warning system according to claim 8, which is characterized in that the high module of survey includes antenna, hair
It penetrates match circuit, receive match circuit and radio frequency chip, radio frequency chip emits the defeated of modulated analog signal extremely transmitting match circuit
Enter end, the input terminal of the output end and antenna that emit match circuit connects, the output end of antenna and the input for receiving match circuit
The receiving end of end connection, the output end and radio frequency chip that receive match circuit connects, and radio frequency chip is connect with processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910358732.0A CN110097727A (en) | 2019-04-30 | 2019-04-30 | Forest Fire Alarm method and system based on fuzzy Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910358732.0A CN110097727A (en) | 2019-04-30 | 2019-04-30 | Forest Fire Alarm method and system based on fuzzy Bayesian network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110097727A true CN110097727A (en) | 2019-08-06 |
Family
ID=67446417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910358732.0A Pending CN110097727A (en) | 2019-04-30 | 2019-04-30 | Forest Fire Alarm method and system based on fuzzy Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097727A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930632A (en) * | 2019-11-01 | 2020-03-27 | 杨勇 | Early warning system based on artificial intelligence |
| CN110992633A (en) * | 2019-12-18 | 2020-04-10 | 深圳市科敏传感器有限公司 | Double-period forest fire prevention early warning method |
| CN111127806A (en) * | 2019-12-30 | 2020-05-08 | 重庆市海普软件产业有限公司 | Comprehensive forest fire prevention monitoring system and method based on multiple sensors |
| CN111583569A (en) * | 2020-04-30 | 2020-08-25 | 深圳市前海用电物联网科技有限公司 | Electric fire detection method and system of causal model |
| CN111739243A (en) * | 2020-05-14 | 2020-10-02 | 电子科技大学 | D-S evidence theory-based fire state detection method |
| CN111798127A (en) * | 2020-07-02 | 2020-10-20 | 北京石油化工学院 | Chemical industry park inspection robot path optimization system based on dynamic fire risk intelligent assessment |
| CN112330915A (en) * | 2020-10-29 | 2021-02-05 | 五邑大学 | Unmanned aerial vehicle forest fire prevention early warning method and system, electronic equipment and storage medium |
| CN112464813A (en) * | 2020-11-26 | 2021-03-09 | 国网北京市电力公司 | Method and device for monitoring mountain fire |
| CN112885021A (en) * | 2021-01-27 | 2021-06-01 | 上海大学 | Multi-sensor fire prediction method and system based on composite algorithm |
| WO2021130531A1 (en) * | 2019-12-27 | 2021-07-01 | Instituto De Sistemas E Robótica | Method, device and system for the detection of a flame condition, in particular for the detection of a forest fire |
| CN113129569A (en) * | 2021-04-13 | 2021-07-16 | 辰安天泽智联技术有限公司 | Fusion type fire-fighting Internet of things monitoring and early warning signal identification method |
| CN113205669A (en) * | 2021-04-13 | 2021-08-03 | 清华大学合肥公共安全研究院 | Fused fire-fighting Internet of things monitoring and early warning method |
| CN113256275A (en) * | 2021-07-14 | 2021-08-13 | 支付宝(杭州)信息技术有限公司 | Expert system updating method, service processing method and device |
| CN113435848A (en) * | 2021-06-30 | 2021-09-24 | 山东强力消防工程有限公司 | Fire early warning system and method based on big data simulation |
| CN114155694A (en) * | 2021-12-27 | 2022-03-08 | 北京卓翼智能科技有限公司 | Automatic cruise and have high temperature early warning function unmanned aerial vehicle |
| CN114758465A (en) * | 2022-03-30 | 2022-07-15 | 南京林业大学 | Forest protection method based on unmanned cluster cooperative intelligent technology |
| CN116139428A (en) * | 2023-02-28 | 2023-05-23 | 生态环境部南京环境科学研究所 | Early warning method based on forest ecosystem damage |
| CN116824462A (en) * | 2023-08-30 | 2023-09-29 | 贵州省林业科学研究院 | Forest intelligent fireproof method based on video satellite |
| CN116978203A (en) * | 2023-09-25 | 2023-10-31 | 四川天地宏华导航设备有限公司 | Intelligent system and method based on fire control |
| CN117783453A (en) * | 2024-02-27 | 2024-03-29 | 杨凌职业技术学院 | Real-time monitoring system for forestry fire prevention |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090114794A (en) * | 2008-04-30 | 2009-11-04 | (주)브로드웨이브 | The techic of sensing and tracking spreaded forest fire |
| CN104318347A (en) * | 2014-09-30 | 2015-01-28 | 上海电力学院 | Power transmission line icing state assessment method based on information fusion of multiple sensors |
| CN108285071A (en) * | 2018-01-25 | 2018-07-17 | 暨南大学 | A kind of elevator Gernral Check-up method based on Bayesian network |
| CN108346254A (en) * | 2018-04-19 | 2018-07-31 | 贵州大学 | A kind of forest fire monitoring system based on unmanned plane |
| CN108416963A (en) * | 2018-05-04 | 2018-08-17 | 湖北民族学院 | Forest Fire Alarm method and system based on deep learning |
| CN108734913A (en) * | 2018-05-31 | 2018-11-02 | 重庆大学 | Forest fire patrol alarm system based on unmanned plane image recognition and method |
| 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 |
-
2019
- 2019-04-30 CN CN201910358732.0A patent/CN110097727A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090114794A (en) * | 2008-04-30 | 2009-11-04 | (주)브로드웨이브 | The techic of sensing and tracking spreaded forest fire |
| CN104318347A (en) * | 2014-09-30 | 2015-01-28 | 上海电力学院 | Power transmission line icing state assessment method based on information fusion of multiple sensors |
| CN108285071A (en) * | 2018-01-25 | 2018-07-17 | 暨南大学 | A kind of elevator Gernral Check-up method based on Bayesian network |
| CN108346254A (en) * | 2018-04-19 | 2018-07-31 | 贵州大学 | A kind of forest fire monitoring system based on unmanned plane |
| CN108416963A (en) * | 2018-05-04 | 2018-08-17 | 湖北民族学院 | Forest Fire Alarm method and system based on deep learning |
| CN108734913A (en) * | 2018-05-31 | 2018-11-02 | 重庆大学 | Forest fire patrol alarm system based on unmanned plane image recognition and method |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 赵志成: "基于ARM的机车火灾智能报警灭火系统", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930632B (en) * | 2019-11-01 | 2021-12-21 | 杨勇 | Early warning system based on artificial intelligence |
| CN110930632A (en) * | 2019-11-01 | 2020-03-27 | 杨勇 | Early warning system based on artificial intelligence |
| CN110992633A (en) * | 2019-12-18 | 2020-04-10 | 深圳市科敏传感器有限公司 | Double-period forest fire prevention early warning method |
| WO2021130531A1 (en) * | 2019-12-27 | 2021-07-01 | Instituto De Sistemas E Robótica | Method, device and system for the detection of a flame condition, in particular for the detection of a forest fire |
| CN111127806A (en) * | 2019-12-30 | 2020-05-08 | 重庆市海普软件产业有限公司 | Comprehensive forest fire prevention monitoring system and method based on multiple sensors |
| CN111583569A (en) * | 2020-04-30 | 2020-08-25 | 深圳市前海用电物联网科技有限公司 | Electric fire detection method and system of causal model |
| CN111739243A (en) * | 2020-05-14 | 2020-10-02 | 电子科技大学 | D-S evidence theory-based fire state detection method |
| CN111798127A (en) * | 2020-07-02 | 2020-10-20 | 北京石油化工学院 | Chemical industry park inspection robot path optimization system based on dynamic fire risk intelligent assessment |
| CN111798127B (en) * | 2020-07-02 | 2022-08-23 | 北京石油化工学院 | Chemical industry park inspection robot path optimization system based on dynamic fire risk intelligent assessment |
| CN112330915B (en) * | 2020-10-29 | 2023-02-28 | 五邑大学 | Unmanned aerial vehicle forest fire prevention early warning method and system, electronic equipment and storage medium |
| CN112330915A (en) * | 2020-10-29 | 2021-02-05 | 五邑大学 | Unmanned aerial vehicle forest fire prevention early warning method and system, electronic equipment and storage medium |
| CN112464813A (en) * | 2020-11-26 | 2021-03-09 | 国网北京市电力公司 | Method and device for monitoring mountain fire |
| CN112885021A (en) * | 2021-01-27 | 2021-06-01 | 上海大学 | Multi-sensor fire prediction method and system based on composite algorithm |
| CN113129569A (en) * | 2021-04-13 | 2021-07-16 | 辰安天泽智联技术有限公司 | Fusion type fire-fighting Internet of things monitoring and early warning signal identification method |
| CN113205669A (en) * | 2021-04-13 | 2021-08-03 | 清华大学合肥公共安全研究院 | Fused fire-fighting Internet of things monitoring and early warning method |
| CN113205669B (en) * | 2021-04-13 | 2022-07-19 | 清华大学合肥公共安全研究院 | Fused fire-fighting Internet of things monitoring and early warning method |
| CN113435848A (en) * | 2021-06-30 | 2021-09-24 | 山东强力消防工程有限公司 | Fire early warning system and method based on big data simulation |
| CN113256275B (en) * | 2021-07-14 | 2021-11-02 | 支付宝(杭州)信息技术有限公司 | Expert system updating method, service processing method and device |
| CN113256275A (en) * | 2021-07-14 | 2021-08-13 | 支付宝(杭州)信息技术有限公司 | Expert system updating method, service processing method and device |
| CN114155694A (en) * | 2021-12-27 | 2022-03-08 | 北京卓翼智能科技有限公司 | Automatic cruise and have high temperature early warning function unmanned aerial vehicle |
| CN114758465A (en) * | 2022-03-30 | 2022-07-15 | 南京林业大学 | Forest protection method based on unmanned cluster cooperative intelligent technology |
| CN114758465B (en) * | 2022-03-30 | 2024-03-15 | 南京林业大学 | Forest protection method based on unmanned cluster cooperative intelligent technology |
| CN116139428A (en) * | 2023-02-28 | 2023-05-23 | 生态环境部南京环境科学研究所 | Early warning method based on forest ecosystem damage |
| CN116139428B (en) * | 2023-02-28 | 2023-09-15 | 生态环境部南京环境科学研究所 | Early warning method based on forest ecosystem damage |
| CN116824462A (en) * | 2023-08-30 | 2023-09-29 | 贵州省林业科学研究院 | Forest intelligent fireproof method based on video satellite |
| CN116824462B (en) * | 2023-08-30 | 2023-11-07 | 贵州省林业科学研究院 | Forest intelligent fireproof method based on video satellite |
| CN116978203A (en) * | 2023-09-25 | 2023-10-31 | 四川天地宏华导航设备有限公司 | Intelligent system and method based on fire control |
| CN116978203B (en) * | 2023-09-25 | 2023-12-26 | 四川天地宏华导航设备有限公司 | Intelligent system and method based on fire control |
| CN117783453A (en) * | 2024-02-27 | 2024-03-29 | 杨凌职业技术学院 | Real-time monitoring system for forestry fire prevention |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097727A (en) | Forest Fire Alarm method and system based on fuzzy Bayesian network | |
| CN108416963A (en) | Forest Fire Alarm method and system based on deep learning | |
| US7991187B2 (en) | Intelligent image smoke/flame sensor and detection system | |
| CN109961157B (en) | Inspection method and system of solar photovoltaic power generation system | |
| CN109885083A (en) | Transmission line of electricity fining inspection flying platform and method for inspecting based on laser radar | |
| CN110321853A (en) | Distribution cable external force damage prevention system based on video intelligent detection | |
| CN106054928A (en) | All-region fire generation determination method based on unmanned plane network | |
| CN206990108U (en) | A kind of fiery cigarette monitoring system based on unmanned plane | |
| CN111044052B (en) | Unmanned aerial vehicle self-adaptive navigation system and method based on intelligent sensing | |
| Owayjan et al. | Firoxio: Forest fire detection and alerting system | |
| CN110553549B (en) | Low altitude aircraft command control system | |
| CN109035665A (en) | A kind of novel forest fire early-warning system and fire alarm method | |
| CN112002095A (en) | Fire early warning method in mine tunnel | |
| CN103761827A (en) | Fire monitor system | |
| CN109377701A (en) | The real-time early warning system and method for transmission line forest fire fire behavior development trend | |
| CN110825112B (en) | Oil field dynamic invasion target tracking system and method based on multiple unmanned aerial vehicles | |
| Beachly et al. | UAS-Rx interface for mission planning, fire tracking, fire ignition, and real-time updating | |
| CN109361728A (en) | A kind of classification Incident Reporting System and method based on the multi-source sensing data degree of association | |
| CN204375138U (en) | Based on the intelligent early-warning system of people's current density recognition technology | |
| CN116187740A (en) | Mountain fire monitoring method and system along power transmission line | |
| CN103871192A (en) | Efficient intelligent fire-preventing early warning system and method | |
| CN113536564B (en) | Unmanned bee colony autonomous collaborative assessment method and system based on virtual simulation | |
| Rahman et al. | Computer vision-based wildfire smoke detection using UAVs | |
| CN114283548A (en) | Fire continuous monitoring method and system for unmanned aerial vehicle | |
| CN117270569A (en) | Mountain fire identification inspection method based on dynamic path planning |
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 |