CN107313808A - Inflammable gas concentration monitor and the method for early warning - Google Patents
Inflammable gas concentration monitor and the method for early warning Download PDFInfo
- Publication number
- CN107313808A CN107313808A CN201610409694.3A CN201610409694A CN107313808A CN 107313808 A CN107313808 A CN 107313808A CN 201610409694 A CN201610409694 A CN 201610409694A CN 107313808 A CN107313808 A CN 107313808A
- Authority
- CN
- China
- Prior art keywords
- gas concentration
- inflammable gas
- layer
- early warning
- model
- 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
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The present invention relates to a kind of inflammable gas concentration monitor and the method for early warning, the problem of security is poor in the prior art is mainly solved.The present invention is by using a kind of inflammable gas concentration monitor and the method for early warning, inflammable gas concentration data is stored in database, and the data are handled as time series progress and obtain inflammable gas concentration-time sequence data, then exported by neutral net, concentration boundary value is preset, the boundary value is reached, the technical scheme that system carries out automatic alarm preferably solves above mentioned problem, available in inflammable gas concentration monitor and early warning.
Description
Technical field
The present invention relates to a kind of inflammable gas concentration monitor and the method for early warning.
Background technology
With continuing to develop for society, the raising of quality of life, the mankind propose higher requirement to inherently safe.Gas station, coal
Pernicious gas in the dangerous work place such as ore deposit, chemical plant threatens the safety of life always, and this will directly affect the matter of life
Amount.
At present, the acoustic-optic alarm progress sound and light alarm that gas exceeding limit alarm mainly uses methane transducer occurs for underground.
Because the acoustic-optic alarm alarm sound level intensities of methane transducer are smaller, audible signal sound level about 80dB (A), optical signal is only
Can be visible at a distance in 20m, when gas accident occurs for some place of underground, operation people in place only near methane transducer
Member can perceive warning message, and away from the personnel in methane transducer other tunnels in place and underground farther out in the tunnel
But Gas Disaster warning information can not be obtained in time, cause most of personnel in the pit to keep away calamity action delay.
Based on above-mentioned situation, the exploratory development for carrying out coal mine gas calamity forecast system just seems particularly necessary.Due to colliery peace
Full change of the monitoring system to each place gas density in underground is persistently monitored, and builds watt based on coal mine safety monitoring system
This disaster early warning system has feasibility.
The content of the invention
The technical problems to be solved by the invention are that there is provided one for the problem of alarm can not realize comprehensive early warning in the prior art
The new inflammable gas concentration monitor of kind and the method for early warning.
To solve the above problems, the technical solution adopted by the present invention is as follows:A kind of inflammable gas concentration monitor and the method for early warning,
Comprise the following steps:
1) the inflammable gas concentration data of multiple spot is obtained, database is stored in;
2) data in database are handled as time series progress and obtains inflammable gas time series data, wherein, the time is
Collect the real-time time of inflammable gas concentration data, inflammable gas concentration as the time dependent variable;
3) BP neural network forecast model and learning method model, training forecast model are built, is examined and forecast output;
4) inflammable gas concentration boundary value is set, early warning is realized.
Build BP neural network forecast model the step of be:Projected depth is limited Boltzmann machine model, to collect when
Between and inflammable gas concentration data carry out pre-training, obtain best initial weights matrix and optimal bias, be used as depth convolutional Neural
The weight initial value and bias initial value of network model;Using at the beginning of obtained best initial weights matrix and optimal bias as weight
Initial value and bias initial value, set up four layer depth convolutional neural networks models, and using the model to inflammable gas concentration shape
Condition is monitored.
In above-mentioned technical proposal, it is preferable that four layer depth convolutional neural networks models include input layer, hidden layer and output layer;
The signal that input layer is inputted is time and gas density, and the signal that output layer is exported is gas concentration monitoring situation, often
Individual hidden layer is constituted by convolution and down-sampling function.
In above-mentioned technical proposal, it is preferable that four layer depth convolutional neural networks models are entered using least square method of recursion algorithm
Row training, output layer and corresponding input layer is contrasted, until the mean square error of network training reaches requirement, it is determined that respectively
The weights and threshold value of layer.
Inflammable gas concentration data is stored in database by the present invention, and the data are handled as time series progress obtains easily
Combustion gas bulk concentration time series data, is then exported by neutral net, has preset concentration boundary value, reaches the border
Value, system carries out automatic alarm, can realize that system detects and sent in real time early warning, achieve preferable technique effect.
The present invention using modern Spatial Data Mining Technique from these inflammable gas Monitoring Datas it is automatic, quickly and accurately
The spatial information related to the generation of inflammable gas disaster accident is extracted, the Evolution of inflammable gas disaster is disclosed, sets up gas
Hazard prediction forecasting model.
Below by embodiment, the invention will be further elaborated, but is not limited only to the present embodiment.
Embodiment
【Embodiment 1】
A kind of method of gas monitor and early warning, it comprises the following steps:
1) the gas density data of multiple spot are obtained, database is stored in;
2) data in database are handled as time series progress and obtains gas density time series data, wherein, when
Between be to collect the real-time times of gas data, gas density as the time dependent variable;
3) projected depth is limited Boltzmann machine model, carries out pre-training to the time collected and gas density data, obtains
Best initial weights matrix and optimal bias are obtained, it is initial as the weight initial value and bias of depth convolutional neural networks model
Value;Using obtained best initial weights matrix and optimal bias as weight initial value and bias initial value, four layer depths are set up
Convolutional neural networks model, and gas density situation is monitored using the model;Four layer depth convolutional neural networks models
Include input layer, hidden layer and output layer;The signal that input layer is inputted is time and gas density, the letter that output layer is exported
Number it is gas concentration monitoring situation, each hidden layer is constituted by convolution and down-sampling function;Using least square method of recursion
Algorithm is trained to BP neural network, and output layer and corresponding input layer are contrasted, square until network training
Error reaches requirement, determines the weights and threshold value of each layer
4) gas density boundary value is set, early warning is realized.
Gas density data are stored in database by the present invention, and the data handle to obtain gas dense as time series progress
Time series data is spent, is then exported by neutral net, has preset concentration boundary value, reach the boundary value, system
Automatic alarm is carried out, can realize that system detects and sent in real time early warning, security is preferable.
Claims (4)
1. a kind of inflammable gas concentration monitor and the method for early warning, comprise the following steps:
1) the inflammable gas concentration data of multiple spot is obtained, database is stored in;
2) data in database are handled as time series progress and obtains inflammable gas time series data, wherein, the time is
Collect the real-time time of inflammable gas concentration data, inflammable gas concentration as the time dependent variable;
3) BP neural network forecast model and learning method model, training forecast model are built, is examined and forecast output;
4) inflammable gas concentration boundary value is set, early warning is realized.
2. a kind of inflammable gas concentration monitor as claimed in claim 1 and the method for early warning, it is characterised in that:Build BP god
The step of through Network Prediction Model is:Projected depth is limited Boltzmann machine model, dense to the time and inflammable gas that collect
Degrees of data carries out pre-training, obtains best initial weights matrix and optimal bias, is used as the weight of depth convolutional neural networks model
Initial value and bias initial value;Using at the beginning of obtained best initial weights matrix and optimal bias as weight initial value and bias
Initial value, sets up four layer depth convolutional neural networks models, and inflammable gas concentration profile is monitored using the model.
3. a kind of inflammable gas concentration monitor as claimed in claim 2 and the method for early warning, it is characterised in that:Four layer depths are rolled up
Product neural network model includes input layer, hidden layer and output layer;The signal that input layer is inputted be time and gas density,
The signal that output layer is exported is gas concentration monitoring situation, and each hidden layer is constituted by convolution and down-sampling function.
4. a kind of inflammable gas concentration monitor as claimed in claim 2 and the method for early warning, it is characterised in that:Using recursion most
Young waiter in a wineshop or an inn's multiplication algorithm is trained to four layer depth convolutional neural networks models, by output layer and the progress pair of corresponding input layer
Than until the mean square error of network training reaches requirement, determining the weights and threshold value of each layer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610409694.3A CN107313808A (en) | 2016-06-12 | 2016-06-12 | Inflammable gas concentration monitor and the method for early warning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610409694.3A CN107313808A (en) | 2016-06-12 | 2016-06-12 | Inflammable gas concentration monitor and the method for early warning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107313808A true CN107313808A (en) | 2017-11-03 |
Family
ID=60185742
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610409694.3A Pending CN107313808A (en) | 2016-06-12 | 2016-06-12 | Inflammable gas concentration monitor and the method for early warning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107313808A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108646149A (en) * | 2018-04-28 | 2018-10-12 | 国网江苏省电力有限公司苏州供电分公司 | Fault electric arc recognition methods based on current characteristic extraction |
CN109858576A (en) * | 2019-03-22 | 2019-06-07 | 盾钰(上海)互联网科技有限公司 | The gradual self feed back concentration Entropy Changes prediction technique of gas, system and storage medium |
CN111080976A (en) * | 2019-12-24 | 2020-04-28 | 北京优航机电技术有限公司 | Method and device for monitoring natural gas leakage in real time under temperature change scene |
CN111324988A (en) * | 2020-03-03 | 2020-06-23 | 山西西山煤电股份有限公司 | Gas overrun early warning model construction method based on machine learning and early warning method |
CN113358600A (en) * | 2020-03-06 | 2021-09-07 | 山东大学 | Gas detection chamber, laser spectrum gas detection system based on artificial neural network and laser spectrum gas detection method based on artificial neural network |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201531276U (en) * | 2009-10-09 | 2010-07-21 | 西安西科测控设备有限责任公司 | Device for tracking and early warning outburst hazard of mine coal and gas in real time |
CN103122772A (en) * | 2013-01-29 | 2013-05-29 | 山东科技大学 | Method for judging burst accident in early burst happening period rapidly and predicting gas discharge scale |
CN103711523A (en) * | 2013-12-24 | 2014-04-09 | 华北科技学院 | Method for predicating gas concentration in real time based on local decomposition-evolution neural network |
CN104156422A (en) * | 2014-08-06 | 2014-11-19 | 辽宁工程技术大学 | Gas concentration real-time prediction method based on dynamic neural network |
CN105089703A (en) * | 2015-09-15 | 2015-11-25 | 江苏三恒科技股份有限公司 | Mine safety system and control method |
CN105546352A (en) * | 2015-12-21 | 2016-05-04 | 重庆科技学院 | Natural gas pipeline tiny leakage detection method based on sound signals |
-
2016
- 2016-06-12 CN CN201610409694.3A patent/CN107313808A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201531276U (en) * | 2009-10-09 | 2010-07-21 | 西安西科测控设备有限责任公司 | Device for tracking and early warning outburst hazard of mine coal and gas in real time |
CN103122772A (en) * | 2013-01-29 | 2013-05-29 | 山东科技大学 | Method for judging burst accident in early burst happening period rapidly and predicting gas discharge scale |
CN103711523A (en) * | 2013-12-24 | 2014-04-09 | 华北科技学院 | Method for predicating gas concentration in real time based on local decomposition-evolution neural network |
CN104156422A (en) * | 2014-08-06 | 2014-11-19 | 辽宁工程技术大学 | Gas concentration real-time prediction method based on dynamic neural network |
CN105089703A (en) * | 2015-09-15 | 2015-11-25 | 江苏三恒科技股份有限公司 | Mine safety system and control method |
CN105546352A (en) * | 2015-12-21 | 2016-05-04 | 重庆科技学院 | Natural gas pipeline tiny leakage detection method based on sound signals |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108646149A (en) * | 2018-04-28 | 2018-10-12 | 国网江苏省电力有限公司苏州供电分公司 | Fault electric arc recognition methods based on current characteristic extraction |
CN109858576A (en) * | 2019-03-22 | 2019-06-07 | 盾钰(上海)互联网科技有限公司 | The gradual self feed back concentration Entropy Changes prediction technique of gas, system and storage medium |
CN109858576B (en) * | 2019-03-22 | 2020-12-22 | 盾钰(上海)互联网科技有限公司 | Progressive self-feedback concentration entropy change prediction method and system for gas and storage medium |
CN111080976A (en) * | 2019-12-24 | 2020-04-28 | 北京优航机电技术有限公司 | Method and device for monitoring natural gas leakage in real time under temperature change scene |
CN111324988A (en) * | 2020-03-03 | 2020-06-23 | 山西西山煤电股份有限公司 | Gas overrun early warning model construction method based on machine learning and early warning method |
CN111324988B (en) * | 2020-03-03 | 2023-08-08 | 山西西山煤电股份有限公司 | Gas overrun early warning model construction method and early warning method based on machine learning |
CN113358600A (en) * | 2020-03-06 | 2021-09-07 | 山东大学 | Gas detection chamber, laser spectrum gas detection system based on artificial neural network and laser spectrum gas detection method based on artificial neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107313808A (en) | Inflammable gas concentration monitor and the method for early warning | |
Alonso-Betanzos et al. | An intelligent system for forest fire risk prediction and fire fighting management in Galicia | |
CN104346538B (en) | Earthquake hazard assessment method based on three kinds of the condition of a disaster factor control | |
CN110264672A (en) | A kind of early warning system of geological disaster | |
CN108154265A (en) | A kind of cellular automata optimization of mine fire best-effort path and bootstrap technique | |
CN114021487B (en) | Early warning method, device and equipment for landslide collapse and readable storage medium | |
CN104881546A (en) | Method for improving prediction efficiency of atmospheric pollution model | |
CN115063963B (en) | Landslide monitoring system and method based on digital twin technology | |
CN115526422B (en) | Coal mine gas explosion risk prediction method | |
CN103810741A (en) | Underground emergency evacuation virtual crowd simulation method based on multiple intelligent agents | |
CN103711523A (en) | Method for predicating gas concentration in real time based on local decomposition-evolution neural network | |
CN113139322B (en) | Nuclear power plant fire response and drilling capability evaluation system and method | |
CN109448487B (en) | Coal mine gas explosion disaster virtual emergency drilling method and system | |
CN107240216A (en) | Based on 3DGIS+BIM technologies and artificial intelligence O&M emergent alarm and fast response method | |
CN109064050A (en) | Multiple linear regression Fire risk assessment method based on big data | |
CN107680680A (en) | Cardiovascular and cerebrovascular disease method for prewarning risk and system based on accurate health control | |
CN106251860A (en) | Unsupervised novelty audio event detection method and system towards safety-security area | |
CN107808237A (en) | A kind of parallel reservoir group Real time Flood risk Analytic Calculation Method | |
Nikulin et al. | Smart personal protective equipment in the coal mining industry | |
CN105976025A (en) | BP neural network gas prediction method based on genetic algorithm optimization | |
CN114048952A (en) | Iron works safety situation perception method based on edge internet of things technology and neural network | |
CN111724561A (en) | Sulfide ore spontaneous combustion monitoring method and system | |
CN106022663A (en) | Risk assessment system for mountain fires approaching to transmission lines | |
CN107704951A (en) | A kind of Forecasting Methodology of gas emission | |
CN109033561A (en) | Mine ventilation system anti-disaster ability evaluation method and device |
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: 20171103 |
|
RJ01 | Rejection of invention patent application after publication |