CN110135016A - A kind of multidimensional fire-fighting data fusion analysis method neural network based - Google Patents
A kind of multidimensional fire-fighting data fusion analysis method neural network based Download PDFInfo
- Publication number
- CN110135016A CN110135016A CN201910342957.7A CN201910342957A CN110135016A CN 110135016 A CN110135016 A CN 110135016A CN 201910342957 A CN201910342957 A CN 201910342957A CN 110135016 A CN110135016 A CN 110135016A
- Authority
- CN
- China
- Prior art keywords
- fire
- neural network
- parameter
- scene
- multidimensional
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 title claims abstract description 22
- 230000004927 fusion Effects 0.000 title claims abstract description 17
- 235000019504 cigarettes Nutrition 0.000 claims abstract description 26
- 238000003062 neural network model Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 5
- 108010074506 Transfer Factor Proteins 0.000 claims abstract description 4
- 239000000843 powder Substances 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 230000000644 propagated effect Effects 0.000 claims description 4
- 230000035807 sensation Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 18
- 230000004913 activation Effects 0.000 description 12
- 230000009471 action Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 230000001537 neural effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of multidimensional fire-fighting data fusion analysis methods neural network based, include the following steps: step 1, establish with the state parameter of live cigarette sense, the temperature parameter at scene, the temperature warning threshold parameter at scene and the vital signs parameter at scene as input, it take occurrence index as the neural network model of output, and the neural network model of foundation is trained, according to the implicit layer number of training result and the error transfer factor neural network model of actual alarm result, until accuracy rate is not less than desired value；Step 2, with trained neural network model, the condition of a disaster analysis is carried out to the state parameter of the live cigarette sense obtained in real time, the temperature parameter at scene, the temperature warning threshold parameter at scene and the vital signs parameter at scene.Compared with prior art, the present invention obtains the operating condition of field device in time, carries out data analysis convenient for platform.Field condition is judged in time by the video information that infrared photography provides, and can be remotely operated fire extinguisher and be put out a fire.
Description
Technical field
The present invention relates to security against fire field, specially a kind of multidimensional fire-fighting data fusion analysis neural network based
Method.
Background technique
Currently, with economic rapid development, the public places such as large-scale luxurious hotels, hotel, office building, shopping plaza
It is more and more.This kind of public place scale is big, combustible is more, increases the difficulty for fire extinguishing of taking precautions against natural calamities to a certain extent.For upper
Background is stated, most places are to carry out fire alarm using free-standing cigarette sense, are permitted however, traditional free-standing cigarette sense exists
More problems: can only carry out simple onsite alarming, warning message can not be notified the external world；Equipment can not obtain when breaking down
Know, without equipment rolling inspection function；Lack the analysis processing function of exogenous data platform, it can not automatic discrimination alarm fire
Situations such as；Lack real-time video interlink when alarm fire, can not remotely check field condition.
Summary of the invention
The technical problem to be solved by the present invention is in view of the deficiency of the prior art, and provide a kind of raising
The multidimensional fire-fighting data fusion analysis method neural network based of fire forecast accuracy rate.
In order to solve the above technical problems, the technical solution adopted by the present invention is that:
A kind of multidimensional fire-fighting data fusion analysis method neural network based, which comprises the steps of:
Step 1 is established with the state parameter of live cigarette sense, the temperature parameter at scene, live temperature warning threshold parameter
And the vital signs parameter at scene is input, take occurrence index as the neural network model of output, and to the nerve net of foundation
Network model is trained, according to the implicit layer number of training result and the error transfer factor neural network model of actual alarm result,
Until accuracy rate is not less than desired value；
Step 2, with trained neural network model, to the temperature of the state parameter of the live cigarette sense obtained in real time, scene
The vital signs parameter for spending parameter, the temperature warning threshold parameter at scene and scene carries out the condition of a disaster analysis.
The device data obtains by the following method:
Field device is connected to the client host at scene；
Client host is connected to fire control platform, and the facility information of oneself is sent fire control platform by client host.
The field device includes cigarette propagated sensation sensor, infrared photography sensor, suspended type ultrafine dry powder fire extinguisher and life
Characteristic detector；Wherein cigarette propagated sensation sensor is used to detect the state parameter of live cigarette sense；Infrared photography sensor is existing for detecting
The temperature parameter of field；Vital signs detector is used to detect the vital signs parameter at scene；Suspended type ultrafine dry powder fire extinguisher is used
It puts out a fire on site.
Acquisition primary equipment data per second simultaneously carry out the condition of a disaster conjunction analysis, judge whether the place of monitoring has fire, such as analyze
There is fire then to issue alarm.
Long connection, the listening thread including starting fire control platform are established between client host and fire control platform, monitoring refers to
Fixed port numbers；Client host creates socket, is connected to specified services end；Client host sends data；Fire control platform
Client host data are deposited into database.
The facility information includes: cigarette sense title, position, state；Infrared camera title, position, state, temperature, temperature
Spend threshold value；Life detectors title, position, state；Suspended automatic dry powder extinguisher title, position, quantity.
The output occurrence index of the neural network is that 0-1 is judged as pre- as 0.5≤occurrence index < 0.85
It is alert, when occurrence index >=0.85, it is judged as alarm.
The desired value is 95%.
Technical solution of the present invention has the advantages that
1. obtaining the operating condition (fault message, warning information, temperature information, life-information) etc. of field device in time
Deng convenient for platform progress data analysis.
2. judging field condition in time by the video information that infrared photography provides, fire extinguisher can be remotely operated and gone out
Fire.
Detailed description of the invention
It, below will be to tool in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Body embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing be some embodiments of the present invention, for those of ordinary skill in the art, what is do not made the creative labor
Under the premise of, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the neural network model schematic diagram in the embodiment of the present invention；
Fig. 2 is the flow chart of data processing schematic diagram in the embodiment of the present invention.
Specific embodiment
Technical solution of the present invention is clearly and completely described below in conjunction with attached drawing, it is clear that described reality
Applying example is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without making creative work belongs to what the present invention protected
Range.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ",
" connected ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integrally connect
It connects；It can be mechanical connection, be also possible to be electrically connected；Can be directly connected, can also indirectly connected through an intermediary,
It can also be the connection inside two elements, can be wireless connection, be also possible to wired connection.For the common of this field
For technical staff, the concrete meaning of above-mentioned term in the present invention can be understood with concrete condition.
In addition, as long as technical characteristic involved in invention described below different embodiments is each other not
Constituting conflict can be combined with each other.
The present invention is based on the multidimensional fire-fighting data fusion analysis methods of neural network, with cigarette sense, infrared photography, suspension
The device datas such as formula superfine powder fire extinguisher, vital signs detector pass through platform comprehensive data analysis, multidimensional fire-fighting data
The fire alarm processing method of fusion, process are as described in Figure 2, comprising:
Step 1: field device is by being typically wire connected to live client host；
Step 2: client host establishes long connection with fire control platform by socket；
Step 3: after long connection is established, the facility information of oneself is sent fire control platform by client host；
Step 4: the neural network that the specific data of equipment are fed to platform is carried out to the training of model；
Step 5: according to the implicit layer number of the error transfer factor model of result and actual alarm result, until accuracy rate not
Lower than desired value；
Step 6: after training, the parameter of model being retained in the included database of fire control platform, number of devices is waited
According to analyze the condition of a disaster.
The neural network model used in the embodiment of the present invention is including input layer, implicit for radial basis neural network
Layer and output layer, mathematical model are as follows:
The input layer of RBF neural is the sension unit being made of multiple signal source nodes, as network model with it is defeated
Enter the interface channel of variable, the input parameter of input layer of the present invention includes the state parameter x of smoke sensor device1, infrared photography pass
The temperature parameter x of sensor2, alarm threshold parameter x3And the vital signs parameter x that vital signs detector obtains4；Hidden layer
(middle layer) is to select the Nonlinear Mapping of specific radial basic function, in order to sample characteristics is extracted, to sample in part
Response is generated in range；Output layer is finally obtained entirely by the operation of the part to a kind of linear transformation of hidden layer output
The output of network.
Radial base (RBF) neural network chooses activation primitive of the radial basis function as Hidden unit, constitutes hidden layer.
So-called radial basis function is exactly a kind of radially symmetrical nonlinear function about a certain group of determination in space, function
Input be such as Euclidean distance distance function, when the distance between input signal and some central point (base) are bigger, then this
The corresponding activation primitive activation degree in a center is lower.This characteristic is commonly known as local distribution characteristic.
It is compared with multilayer perceptron (such as BP neural network), the hidden layer neuron activation letter of multilayer perceptron
Number is usually chosen to hard limiting function, more often selects Sigmoidal function, and RBF neural then selects radial base
Function.The activation primitive of radial base (RBF) neural network can choose diversified forms, comprising:
Gaussian function:
Reflected sigmoidal function:
Inverse Multiquadric function:
In formula, δiIt is the variable for representing activation primitive and expanding constant (Spread) or width, δiNumerical value it is smaller, then activate
Function is narrower, selects performance better.
The input signal of model of the present invention are as follows:
X=(x1,x2,x3,x4)
Wherein x1For cigarette sense state parameter, value 0 or 1；x4For life characteristic parameter, value 0 or 1；
Output signal are as follows:
Wherein, w0Refer to the offset of radial base neural net output；Represent the activation primitive of hidden layer；ωiFor connection weight
Weight；ciFor the center of j-th of middle layer activation primitive function.
Under normal conditions, Gaussian function (Gaussian) is selected as the activation primitive of radial base neural net, calculating process
It is shown below:
Wherein, cjWhat is indicated is the center for j-th of the middle layer activation primitive function chosen, and center is a vector, and
And with input signal XTDimension having the same；||XT-cj| | expression is input signal XTWith center cjDifference XT-cjTwo models
Number indicates input vector XTWith center vector cjEuclidean distance, when the Euclidean between input signal and activation primitive center away from
From | | XT-cj| | when increase, the output of activation primitive is reduced rapidly, and when input signal is consistent with center, network output becomes
“1”。
For convenience of the transmission of data and the parsing of data, the format of data transmission uses JSON data lattice in the present embodiment
Formula, and some symbols are defined, convenient for transmission:
Re: indicating the direction of data transmission, and 1 expression data are transferred to fire control platform from client host, and 2 indicate data
Client host is transferred to from fire control platform.
Action: expression movement, what is defined at present has 1 expression client host information；2 indicate client device information；
3 indicate equipment numerical information；4 indicate starting fire extinguisher.
Location: position；
Name: title；
Code: device coding, for distinguishing equipment；
MainBoardCode: host code, for distinguishing client host；
Status: equipment state, 0 indicates normal, and 1 indicates abnormal, and when there is abnormal conditions, platform can be sent out automatically
It send short massage notice relevant persons in charge to check to scene, sees whether be network problem, equipment fault problem etc..
Temperature: the temperature of infrared camera detection；
IsAlarm: 0 normal 1 alarm of whether alarming；
IsAlive: whether life detectors detection has life mark, and 0 indicates, 1 indicates do not have；
The cigarette sense at scene, infrared photography, suspended type ultrafine dry powder fire extinguisher, the various kinds of equipment such as vital signs detector are logical
Cross the client host at the scene of being typically wire connected to.
Client host establishes long connection with fire control platform by socket.
(1) listening thread for starting fire control platform, monitors specified port numbers；
(2) client host creates socket, is connected to specified services end；
(3) client host sends data: and " re ": 1, " action ": 1, " entity ": { " location ": " is brilliant big
Tall building 602 ", " mainBoardCode ": " 001 ", " name ": " 602 host of brilliant mansion " }；
To fire control platform, for differentiating different clients host identities, such as above-mentioned host table shows address in brilliant mansion
602, for title 602 host of brilliant mansion, host number is 001.
(4) client host data are deposited into database by fire control platform.Compare for data analysis later.
After long connection is established, the facility information of oneself is sent fire control platform by client host:
{"re":1,"action":2,"mainBoardCode":001,"entity":{"deviceDTOList":[{"
Code ": 0 0101, " name ": " smoke alarm 1 ", " location ": " hall " }, " code ": 00102, " name ": "
Infrared camera ", " location ": " hall " }, " code ": 00103, " name ": " fire extinguisher * 2 ", " location ": "
Hall " }, and " code ": 00104, " name ": " life detectors ", " location ": " hall " }]
If above-mentioned tables of data shows there is a cigarette sense under No. 001 host, an infrared photography, 2 fire extinguishers, a life
Detector.These equipment are saved in database by fire control platform, are compared for data analysis later.
Client host acquisition primary equipment data per second, and once per second transmits data to fire control platform.By more
Fire-fighting data fusion is tieed up, comprehensive analysis judges whether the place of monitoring has fire alarm, and carries out respective handling.It is following to lift
Example:
(1) normal data:
{"re":1,"action":3,"mainBoardCode":001,"entity":{[{"code":00101,"
status":0,"is Alarm":0},{"code":00102,"status":0,"temperature":20.5,”
thresholdValue”:60,"isAlarm": 0},{"code":00103,"status":0,"isAlive":0}]}}
Above-mentioned data indicate that 00101 cigarette sense of number is normal, do not alert；The infrared photography of number 00102 is normal, detection
Temperature be 20.5 DEG C；The life detectors that number is 00103, which detect current region, sign of life；Neural network at this time
The occurrence index of model output is 0.At this point, not early warning, does not also alarm.
(2) equipment fault data:
{"re":1,"action":3,"mainBoardCode":001,"entity":{[{"code":00101,"
status":1,"is Alarm":0},{"code":00102,"status":0,"temperature":20.5,"
isAlarm":0},{"code":00103, "status":0,"isAlive":0}]}}
The cigarette sense that above-mentioned number is 00101 is broken down, and platform can give relevant persons in charge's push note automatically, allow negative
Duty personnel go whether scene investigation is network problem, equipment fault problem.
(3) alert data 1:
{"re":1,"action":3,"mainBoardCode":001,"entity":{[{"code":00101,"
status":0,"is Alarm":1},{"code":00102,"status":0,"temperature":20.5,”
thresholdValue”:60,"isAlarm": 0},{"code":00103,"status":0,"isAlive":0}]}}
The occurrence index that above-mentioned data are exported through neural network model is 0.5.The alarm that can determine cigarette sense is wrong report,
Early warning is then issued, is not alarmed, responsible person is allowed to go whether scene investigation is network problem, equipment fault problem.
Cigarette sense if above-mentioned data number is 00101 is alerted, but other than normal smog alarm, dust,
Steam etc. also result in cigarette sense alarm, formed wrong report, so the result obtained by neural network model be actually consistent.
(4) alert data 2:
{"re":1,"action":3,"mainBoardCode":001,"entity":{[{"code":00101,"
status":0,"is Alarm":1},{"code":00102,"status":0,"temperature":91.5,”
thresholdValue”:60,"isAlarm": 1},{"code":00103,"status":0,"isAlive":0}]}}
The occurrence index that above-mentioned data are exported through neural network model is 1.It can determine that the alarm of cigarette sense is drawn for fire
It rises, issues fire alarm.
The automatic telephone of platform meeting at this time notifies relevant persons in charge to rush to the scene, and phonic warning occurs, platform monitoring people
After member's discovery phonic warning, the data cases of video and life detectors can be checked.
If any vital movement sign, then relevant persons in charge is needed to arrive live dredging in time, after personnel withdraw, can passed through
Client host starts fire extinguisher, can also remotely start fire extinguisher by fire control platform.
Such as without vital movement sign, then direct long-range starting fire extinguisher, reaches fire behavior and quickly, accurately handles.
Claims (8)
1. a kind of multidimensional fire-fighting data fusion analysis method neural network based, which comprises the steps of:
Step 1 is established with the state parameter of live cigarette sense, the temperature parameter at scene, live temperature warning threshold parameter and is showed
The vital signs parameter of field is input, take occurrence index as the neural network model of output, and to the neural network mould of foundation
Type is trained, according to the implicit layer number of training result and the error transfer factor neural network model of actual alarm result, until
Accuracy rate is not less than desired value；
Step 2, with trained neural network model, the state parameter of the live cigarette sense obtained in real time, the temperature at scene are joined
The vital signs parameter of number, the temperature warning threshold parameter at scene and scene carries out the condition of a disaster analysis.
2. according to a kind of multidimensional fire-fighting data fusion analysis method neural network based described in claim 1, which is characterized in that
The device data obtains by the following method:
Field device is connected to the client host at scene；
Client host is connected to fire control platform, and the facility information of oneself is sent fire control platform by client host.
3. according to a kind of multidimensional fire-fighting data fusion analysis system neural network based as claimed in claim 2, which is characterized in that
The field device includes cigarette propagated sensation sensor, infrared photography sensor, suspended type ultrafine dry powder fire extinguisher and vital signs detection
Device；Wherein cigarette propagated sensation sensor is used to detect the state parameter of live cigarette sense；Infrared photography sensor is used to detect the temperature at scene
Parameter；Vital signs detector is used to detect the vital signs parameter at scene；Suspended type ultrafine dry powder fire extinguisher with going out on site
Fire.
4. multidimensional fire-fighting data fusion analysis method neural network based according to claim 1, which is characterized in that every
Second acquisition primary equipment data simultaneously carry out the condition of a disaster conjunction analysis, judge whether the place of monitoring has fire, send out if analyzing and having fire
It alarms out.
5. multidimensional fire-fighting data fusion analysis method neural network based according to claim 1, which is characterized in that visitor
Long connection is established between family end main frame and fire control platform, the listening thread including starting fire control platform monitors specified port numbers；
Client host creates socket, is connected to specified services end;Client host sends data；Fire control platform is by client host
Data are deposited into database.
6. multidimensional fire-fighting data fusion analysis method neural network based according to claim 2, which is characterized in that institute
Stating facility information includes: cigarette sense title, position, state；Infrared camera title, position, state, temperature, temperature threshold；Life
Detector title, position, state；Suspended automatic dry powder extinguisher title, position, quantity.
7. multidimensional fire-fighting data fusion analysis method neural network based according to claim 1, which is characterized in that institute
The output occurrence index for stating neural network is that 0-1 is judged as early warning as 0.5≤occurrence index < 0.85, when fire is sent out
When raw rate >=0.85, it is judged as alarm.
8. multidimensional fire-fighting data fusion analysis method neural network based according to claim 1, which is characterized in that institute
Stating desired value is 95%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910342957.7A CN110135016A (en) | 2019-04-26 | 2019-04-26 | A kind of multidimensional fire-fighting data fusion analysis method neural network based |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910342957.7A CN110135016A (en) | 2019-04-26 | 2019-04-26 | A kind of multidimensional fire-fighting data fusion analysis method neural network based |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110135016A true CN110135016A (en) | 2019-08-16 |
Family
ID=67575228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910342957.7A Pending CN110135016A (en) | 2019-04-26 | 2019-04-26 | A kind of multidimensional fire-fighting data fusion analysis method neural network based |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135016A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079855A (en) * | 2019-12-27 | 2020-04-28 | 三一重能有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting console |
| CN111310347A (en) * | 2020-02-25 | 2020-06-19 | 深圳市瑞立视多媒体科技有限公司 | Method, device and equipment for loosening dry powder of simulated fire extinguisher and storage medium |
| CN111882810A (en) * | 2020-07-31 | 2020-11-03 | 广州市微智联科技有限公司 | Fire identification and early warning method and system |
| CN113126050A (en) * | 2021-03-05 | 2021-07-16 | 沃尔夫曼消防装备有限公司 | Life detection method based on neural network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017122995A (en) * | 2016-01-06 | 2017-07-13 | ホーチキ株式会社 | Disaster prevention information management system |
| US9888371B1 (en) * | 2015-11-13 | 2018-02-06 | State Farm Mutual Automobile Insurance Company | Portable home and hotel security system |
| CN109139115A (en) * | 2018-10-16 | 2019-01-04 | 煤炭科学技术研究院有限公司 | A kind of downhole data acquisition terminal, processing system and processing method |
| CN109191357A (en) * | 2018-10-15 | 2019-01-11 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire-fighting method for early warning, device and terminal device |
| CN109356652A (en) * | 2018-10-12 | 2019-02-19 | 深圳市翌日科技有限公司 | Adaptive fire grading forewarning system method and system under a kind of mine |
-
2019
- 2019-04-26 CN CN201910342957.7A patent/CN110135016A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9888371B1 (en) * | 2015-11-13 | 2018-02-06 | State Farm Mutual Automobile Insurance Company | Portable home and hotel security system |
| JP2017122995A (en) * | 2016-01-06 | 2017-07-13 | ホーチキ株式会社 | Disaster prevention information management system |
| CN109356652A (en) * | 2018-10-12 | 2019-02-19 | 深圳市翌日科技有限公司 | Adaptive fire grading forewarning system method and system under a kind of mine |
| CN109191357A (en) * | 2018-10-15 | 2019-01-11 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire-fighting method for early warning, device and terminal device |
| CN109139115A (en) * | 2018-10-16 | 2019-01-04 | 煤炭科学技术研究院有限公司 | A kind of downhole data acquisition terminal, processing system and processing method |
Non-Patent Citations (1)
| Title |
|---|
| 樊强等: "基于RBF神经网络的火灾探测器模型研究", 《微计算机信息》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079855A (en) * | 2019-12-27 | 2020-04-28 | 三一重能有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting console |
| CN111079855B (en) * | 2019-12-27 | 2023-08-11 | 三一重能股份有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting control console |
| CN111310347A (en) * | 2020-02-25 | 2020-06-19 | 深圳市瑞立视多媒体科技有限公司 | Method, device and equipment for loosening dry powder of simulated fire extinguisher and storage medium |
| CN111310347B (en) * | 2020-02-25 | 2022-05-31 | 深圳市瑞立视多媒体科技有限公司 | Method, device and equipment for loosening dry powder of simulated fire extinguisher and storage medium |
| CN111882810A (en) * | 2020-07-31 | 2020-11-03 | 广州市微智联科技有限公司 | Fire identification and early warning method and system |
| CN111882810B (en) * | 2020-07-31 | 2022-07-01 | 广州市微智联科技有限公司 | Fire identification and early warning method and system |
| CN113126050A (en) * | 2021-03-05 | 2021-07-16 | 沃尔夫曼消防装备有限公司 | Life detection method based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110135016A (en) | A kind of multidimensional fire-fighting data fusion analysis method neural network based | |
| CN112862153B (en) | BIM-based fire rescue method, device, storage medium and device | |
| TW201838687A (en) | Risk warning and managing system and method | |
| CN115392708A (en) | Fire risk assessment and early warning method and system for building fire protection | |
| CN108805398A (en) | A kind of method, device and mobile terminal of structural fire protection security evaluation | |
| CN107240216A (en) | Based on 3DGIS+BIM technologies and artificial intelligence O＆M emergent alarm and fast response method | |
| CN107403158A (en) | A kind of personnel video frequency identifying method on duty and intelligent subscriber information carrying means | |
| CN110009738B (en) | Indoor three-dimensional expression model for fire emergency evacuation | |
| CN112363443A (en) | Automatic monitoring method and system for data center | |
| CN111935219B (en) | Community Internet of things management system | |
| KR102480449B1 (en) | Disaster prediction method using multiple sensors | |
| KR20220071880A (en) | Digital twin disaster management system customized for underground public areas | |
| CN111553305B (en) | System and method for identifying illegal videos | |
| CN104574729B (en) | Alarm method, device and system | |
| KR101551716B1 (en) | Fire fight safety system for architecture using alalog address type sensor | |
| CN106789481B (en) | Data visualization integral monitoring system for smart home | |
| CN114187728A (en) | Fire monitoring method and system based on artificial intelligence and digital twin technology | |
| CN113554364A (en) | Disaster emergency management method, device, equipment and computer storage medium | |
| CN205563899U (en) | Fire alarm detection device | |
| CN115346170B (en) | Intelligent monitoring method and device for gas facility area | |
| CN111508182A (en) | Novel monitoring alarm system for community fire fighting through Internet of things | |
| CN116777707A (en) | Intelligent community management system and method | |
| CN115115117A (en) | Intelligent processing and analyzing system based on block chain | |
| JP6585319B1 (en) | System, bot, and method for information sharing | |
| CN115346303A (en) | Visual campus management system based on internet of things node and GIS |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190816 |
|
| RJ01 | Rejection of invention patent application after publication |