CN108535195A - A kind of chemical industry fire fuel identification method based on combustion product - Google Patents
A kind of chemical industry fire fuel identification method based on combustion product Download PDFInfo
- Publication number
- CN108535195A CN108535195A CN201810302506.6A CN201810302506A CN108535195A CN 108535195 A CN108535195 A CN 108535195A CN 201810302506 A CN201810302506 A CN 201810302506A CN 108535195 A CN108535195 A CN 108535195A
- Authority
- CN
- China
- Prior art keywords
- light
- chemical industry
- data
- flue gas
- identification method
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The present invention relates to chemical industry fire protection technologies fields, refer specifically to a kind of chemical industry fire fuel identification method based on combustion product, its step are as follows:A, the incendivity object sample for choosing the higher chemical of purity, sample is put into smoke generating apptss and is burnt, and the flue gas that burning is generated inputs mixing arrangement;B, the flue gas of mixing in mixing arrangement is inputted several light rooms, the acquisition indoor direct light of light and scattering light by capillary is influenced generated change in radiation intensity data by flue gas;C, it enters data into the database of computer foundation, randomly selects the partial data in database as training set, be trained by Randomforest algorithms, then training set is tested to determine validity with remaining data;The influence for the flue gas centering long wave light that the present invention is generated by the different comburants of identification, collecting sample data establish large database concept, learnt by Randomforest machine algorithms, realize the quick analysis and response of scene of a fire comburant, reduces the risk and rescue difficulty of chemical industry fire.
Description
Technical field
The present invention relates to chemical industry fire protection technologies fields, refer specifically to a kind of chemical industry fire fuel knowledge based on combustion product
Other method.
Background technology
Due to the complexity that chemical industry place article is placed, once it is difficult quick identification fire source and fuel kind that fire, which occurs,
Class.Such as in the event of PORT OF TIANJIN, due to lacking the understanding for explosive category, fire fighter takes incorrect fire extinguishing side
Method results in the casualties and property loss of bigger.Therefore the quick determination for fire cause class, especially fuel type
It quickly determines for controlling fire behavior, it is most important to reduce loss.Since the burn incompletely of fuel inherently produces in fire process
Raw a large amount of flue gas, and numerous studies show flue gas caused by different types of fuel in color, temperature, grain size, surface shape
State and density etc. are all different, and therefore, it is necessary to a kind of technologies that fire fuel can be identified by flue gas, for fire
The quick emergency response at calamity scene.
Invention content
In view of the defects and deficiencies of the prior art, the present invention intends to provide one kind can recognizing different flue gases to difference
The direct projection and scattering of wavelength light influence, and establish large database concept and carry out Randomforest training, improve burning things which may cause a fire disaster resolution and sound
Speed is answered, the chemical industry fire fuel identification method based on combustion product of chemical industry fire risk is reduced.
To achieve the goals above, the present invention uses following technical scheme:
A kind of chemical industry fire fuel identification method based on combustion product of the present invention, its step are as follows:
A, the incendivity object sample for choosing the higher chemical of purity, sample is put into smoke generating apptss and is burnt, so
Start the flue gas that the first fan in smoke generating apptss generates burning afterwards and inputs mixing arrangement;
B, the first fan is closed, the flue gas of mixing in mixing arrangement is passed through capillary by the second fan started in mixing arrangement
Pipe inputs several light rooms, the acquisition indoor direct light of light and scattering light is influenced generated change in radiation intensity data by flue gas;
C, it enters data into the database of computer foundation, randomly selects the partial data in database as training
Collection, is trained, then tested training set with determination with remaining data in database by Randomforest algorithms
Validity.
According to above scheme, the mixing arrangement is separately connected 10 identical light rooms, and 10 by 10 capillaries
The middle long wave light of 10 kind different wave lengths of the wave-length coverage between 275nm-930nm is respectively adopted in light room.
According to above scheme, the light room includes straight line chamber, light source, scattered light sensor and direct projection optical sensor, light
It is equipped with lens on front side of source outgoing plane, scattered light sensor and direct projection optical sensor.
According to above scheme, any indoor direct light of light and scattering light convert the equal synchronous transfer of data to database
It is interior to keep the consistency of data.
According to above scheme, the air intake of the smoke generating apptss is equipped with HEPA filters.
The present invention has the beneficial effect that:The shadow for the flue gas centering long wave light that the present invention is generated by the different comburants of identification
It rings, collecting sample data are established large database concept, learnt by Randomforest machine algorithms, realize the quick of scene of a fire comburant
Analysis and response reduce the risk and rescue difficulty of chemical industry fire.
Description of the drawings
Fig. 1 is the overall flow schematic diagram of the present invention;
Fig. 2 is light room inside detailed structure schematic diagram in Fig. 1.
Specific implementation mode
Technical scheme of the present invention is illustrated with embodiment below in conjunction with the accompanying drawings.
As shown in Figs. 1-2, a kind of chemical industry fire fuel identification method based on combustion product of the present invention, step
It is as follows:
A, the incendivity object sample for choosing the higher chemical of purity, sample is put into smoke generating apptss and is burnt, so
Start the flue gas that the first fan in smoke generating apptss generates burning afterwards and inputs mixing arrangement;
B, the first fan is closed, the flue gas of mixing in mixing arrangement is passed through capillary by the second fan started in mixing arrangement
Pipe inputs several light rooms, the acquisition indoor direct light of light and scattering light is influenced generated change in radiation intensity data by flue gas;
C, it enters data into the database of computer foundation, randomly selects the partial data in database as training
Collection, is trained, then tested training set with determination with remaining data in database by Randomforest algorithms
Validity.
The mixing arrangement is separately connected 10 identical light rooms by 10 capillaries, and is respectively adopted in 10 light rooms
The middle long wave light of 10 kind different wave lengths of the wave-length coverage between 275nm-930nm;Light room includes straight line chamber, light source, dissipates
Optical sensor and direct projection optical sensor are penetrated, is equipped on front side of light source outgoing plane, scattered light sensor and direct projection optical sensor
Mirror;The indoor direct light of any light converts in the equal synchronous transfer of data to database with scattering light to keep the consistent of data
Property.
The air intake of the smoke generating apptss is equipped with HEPA filters, it is ensured that the accuracy of test data.
The above is only the better embodiment of the present invention, therefore all constructions according to described in present patent application range,
The equivalent change or modification that feature and principle are done, is included within the scope of present patent application.
Claims (5)
1. a kind of chemical industry fire fuel identification method based on combustion product, its step are as follows:
A, the incendivity object sample for choosing the higher chemical of purity, sample is put into smoke generating apptss and is burnt, is then opened
The flue gas that the first fan in dynamic smoke generating apptss generates burning inputs mixing arrangement;
B, the first fan is closed, the second fan started in mixing arrangement is defeated by capillary by the flue gas of mixing in mixing arrangement
Enter several light rooms, the acquisition indoor direct light of light and scattering light is influenced generated change in radiation intensity data by flue gas;
C, it enters data into the database of computer foundation, randomly selects the partial data in database as training set, lead to
It crosses Randomforest algorithms to be trained, then training set is tested to determine effectively with remaining data in database
Property.
2. the chemical industry fire fuel identification method according to claim 1 based on combustion product, it is characterised in that:It is described mixed
It attaches together to set and is separately connected 10 identical light rooms by 10 capillaries, and wave-length coverage is respectively adopted in 10 light rooms and exists
The middle long wave light of 10 kinds of different wave lengths between 275nm-930nm.
3. the chemical industry fire fuel identification method according to claim 1 based on combustion product, it is characterised in that:The light
Room includes straight line chamber, light source, scattered light sensor and direct projection optical sensor, light source outgoing plane, scattered light sensor and direct projection
Lens are equipped on front side of optical sensor.
4. the chemical industry fire fuel identification method according to claim 1 based on combustion product, it is characterised in that:Described
The indoor direct light of one light and scattering light convert in the equal synchronous transfer of data to database to keep the consistency of data.
5. the chemical industry fire fuel identification method according to claim 1 based on combustion product, it is characterised in that:The cigarette
The air intake of gas generating means is equipped with HEPA filters.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810302506.6A CN108535195A (en) | 2018-04-05 | 2018-04-05 | A kind of chemical industry fire fuel identification method based on combustion product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810302506.6A CN108535195A (en) | 2018-04-05 | 2018-04-05 | A kind of chemical industry fire fuel identification method based on combustion product |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108535195A true CN108535195A (en) | 2018-09-14 |
Family
ID=63482753
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810302506.6A Pending CN108535195A (en) | 2018-04-05 | 2018-04-05 | A kind of chemical industry fire fuel identification method based on combustion product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108535195A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113075137A (en) * | 2020-01-03 | 2021-07-06 | 应急管理部化学品登记中心 | Device and method for identifying nitrogen-containing substances in fire comburent |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102232183A (en) * | 2008-09-05 | 2011-11-02 | 爱克斯崔里斯科技有限公司 | Optical detection of particle characteristics |
CN202512700U (en) * | 2012-03-07 | 2012-10-31 | 科达士(澳大利亚)消防有限公司 | Air-breathing fire detection device |
US8627711B1 (en) * | 2010-05-14 | 2014-01-14 | Richard H. Hall | Sensor switch for chemical/composition detection |
CN104408864A (en) * | 2014-11-27 | 2015-03-11 | 中国科学技术大学先进技术研究院 | Air-suction-type plane cargo compartment fire disaster detector with dehumidifying and dedusting functions |
CN104458702A (en) * | 2014-12-11 | 2015-03-25 | 成都鼎智汇科技有限公司 | Portable gas explosive identification device based on Raman spectrum |
CN104735864A (en) * | 2015-01-16 | 2015-06-24 | 上海大学 | Self-learning fire-source simulating system and method |
CN204575496U (en) * | 2014-06-23 | 2015-08-19 | 重庆交通大学 | The gas diffusion test confined chamber of adjustable meteorologic parameter |
CN106501312A (en) * | 2016-12-24 | 2017-03-15 | 天津达元吉科技有限公司 | A kind of tunnel fire hazard burning HRR test system |
CN106682635A (en) * | 2016-12-31 | 2017-05-17 | 中国科学技术大学 | Smoke detecting method based on random forest characteristic selection |
CN107038334A (en) * | 2017-02-27 | 2017-08-11 | 浙江大学 | Circulating fluid bed domestic garbage burning boiler CO emitted smoke system and methods |
CN206638482U (en) * | 2017-04-19 | 2017-11-14 | 江苏方天电力技术有限公司 | A kind of condenser system of flue gas analysis pretreatment |
CN107561015A (en) * | 2017-07-04 | 2018-01-09 | 华北电力大学 | Solid fuel category identification method based on spectrum analysis |
-
2018
- 2018-04-05 CN CN201810302506.6A patent/CN108535195A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102232183A (en) * | 2008-09-05 | 2011-11-02 | 爱克斯崔里斯科技有限公司 | Optical detection of particle characteristics |
US8627711B1 (en) * | 2010-05-14 | 2014-01-14 | Richard H. Hall | Sensor switch for chemical/composition detection |
CN202512700U (en) * | 2012-03-07 | 2012-10-31 | 科达士(澳大利亚)消防有限公司 | Air-breathing fire detection device |
CN204575496U (en) * | 2014-06-23 | 2015-08-19 | 重庆交通大学 | The gas diffusion test confined chamber of adjustable meteorologic parameter |
CN104408864A (en) * | 2014-11-27 | 2015-03-11 | 中国科学技术大学先进技术研究院 | Air-suction-type plane cargo compartment fire disaster detector with dehumidifying and dedusting functions |
CN104458702A (en) * | 2014-12-11 | 2015-03-25 | 成都鼎智汇科技有限公司 | Portable gas explosive identification device based on Raman spectrum |
CN104735864A (en) * | 2015-01-16 | 2015-06-24 | 上海大学 | Self-learning fire-source simulating system and method |
CN106501312A (en) * | 2016-12-24 | 2017-03-15 | 天津达元吉科技有限公司 | A kind of tunnel fire hazard burning HRR test system |
CN106682635A (en) * | 2016-12-31 | 2017-05-17 | 中国科学技术大学 | Smoke detecting method based on random forest characteristic selection |
CN107038334A (en) * | 2017-02-27 | 2017-08-11 | 浙江大学 | Circulating fluid bed domestic garbage burning boiler CO emitted smoke system and methods |
CN206638482U (en) * | 2017-04-19 | 2017-11-14 | 江苏方天电力技术有限公司 | A kind of condenser system of flue gas analysis pretreatment |
CN107561015A (en) * | 2017-07-04 | 2018-01-09 | 华北电力大学 | Solid fuel category identification method based on spectrum analysis |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113075137A (en) * | 2020-01-03 | 2021-07-06 | 应急管理部化学品登记中心 | Device and method for identifying nitrogen-containing substances in fire comburent |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chen et al. | An early fire-detection method based on image processing | |
JP2008008911A (en) | Chamber constitution for detecting particle, particle detector, smoke detector, and method of making fluid flow in detection zone of particle detector | |
US7696501B2 (en) | Apparatus for monitoring engine exhaust | |
CN106442858B (en) | Combustible Spread Characteristics experimental method under the conditions of different humitures, oxygen concentration | |
CN109712367A (en) | Smoke detector and smoke detection method | |
CN107782463A (en) | The device and method of synchro measure flame forms and temperature | |
CN104677876B (en) | A kind of gaseous material detection device based on transparent capillary structure and fluorescence | |
US3231748A (en) | Smoke detector | |
CN109991228A (en) | A kind of visual pressurization discrete particle kinetics experimental system | |
CN109724981A (en) | Soot apparatus for quantitatively and method in a kind of flame using radiant light | |
CN108535195A (en) | A kind of chemical industry fire fuel identification method based on combustion product | |
GB1135416A (en) | Method of and device for analysing dispersive systems | |
CN104880448B (en) | Pulverized coal flame combustion diagnosis experimental rig | |
Makmool et al. | Structures and performances of laminar impinging multiple premixed LPG–air flames | |
CN209708281U (en) | Smoke detector | |
Samantaray et al. | Analysis of industrial flame characteristics and constancy study using image processing technique | |
CN109239257A (en) | Multi-functional cabin interior material combustion characteristic experiment porch | |
CN216524101U (en) | System for simultaneously measuring temperature and volume fraction of soot particulate matter | |
CN207502480U (en) | Single pellet reaction measuring device | |
CN115290521A (en) | Experimental system and detection method for detecting physical properties of oscillating flame | |
CN103728249A (en) | System for detecting carbon monoxide by acousto-optic technology | |
Kirkbright et al. | Spectroscopy in separated flames—I: The use of the separated air-acetylene flame in thermal emission spectroscopy | |
Turner et al. | Laminar Flame Speed Measurements from Chemiluminescence of OH* and CH* in CH4-Air Flames | |
CN104963790B (en) | Laser ignition device | |
CN114216509B (en) | System and method for measuring temperature and volume fraction of soot particles based on LED light source |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180914 |