CN107403234A - Tunnel Coal and Gas Outbursts Prediction method based on neutral net - Google Patents
Tunnel Coal and Gas Outbursts Prediction method based on neutral net Download PDFInfo
- Publication number
- CN107403234A CN107403234A CN201710489806.5A CN201710489806A CN107403234A CN 107403234 A CN107403234 A CN 107403234A CN 201710489806 A CN201710489806 A CN 201710489806A CN 107403234 A CN107403234 A CN 107403234A
- Authority
- CN
- China
- Prior art keywords
- coal
- gas
- tunnel
- method based
- prediction 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
- 239000003245 coal Substances 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000007935 neutral effect Effects 0.000 title claims abstract description 10
- 238000009792 diffusion process Methods 0.000 claims abstract description 10
- 241001269238 Data Species 0.000 claims abstract description 3
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 3
- 238000012360 testing method Methods 0.000 claims abstract description 3
- 230000006870 function Effects 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000006378 damage Effects 0.000 claims description 5
- 238000003325 tomography Methods 0.000 claims description 5
- 230000005284 excitation Effects 0.000 claims description 4
- 230000000052 comparative effect Effects 0.000 claims description 2
- 238000011161 development Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000011156 evaluation Methods 0.000 description 10
- 238000010276 construction Methods 0.000 description 9
- 210000002569 neuron Anatomy 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 3
- 238000005553 drilling Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000002817 coal dust Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06N3/08—Learning methods
-
- 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
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Animal Husbandry (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Agronomy & Crop Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Tunnel Coal and Gas Outbursts Prediction method based on neutral net, is related to civil engineering technology and computer technology.The present invention comprises the steps：1) input data is determined：Determine 6 input datas, respectively gas pressure, gas diffusion initial speed, the Failure type of coal, coal body firmness coefficient, geological structure and vertical buried depth, 6 nodes of corresponding input layer；2) algorithm parameter is set；3) train；4) return and sentence；5) live application：After checking, testing data is inputted, obtains prediction result.The accuracy of the invention for further improving coal and gas prominent judged result.
Description
Technical field
The present invention relates to civil engineering technology and computer technology.
Background technology
Coal and gas prominent is that a kind of extremely complex coal geology that gas entrainment coal dust is drastically largely gushed moves
Force phenomenon, serious injury loss is had resulted in the coal and gas prominent construction production of colliery industry at home and abroad.In China
Also existing more tunnels have that coal and gas prominent is dangerous in the construction of gas tunnel, as Jiazuqing Tunnel, purple tiling tunnel and
Xin Zhai tunnels etc..
At present, the prediction to tunnel coal and gas prominent mainly uses the Regular contact Forecasting Methodology of coal industry, such as
The method of aggregative indicator, method of drilling index etc..Though tunnel has points of resemblance compared with coal mine roadway, also there are many different ground
Side.For example, in terms of cross dimensions：Coal mine roadway section is smaller, typically less than 10m2, maximum drift section size is typically
No more than 30m2；And the section in tunnel is determined by driving and track clearance, much bigger than coal mine roadway of cross dimensions, typically
Railway single tunnel is 60m2Left and right, the section of Line for Passenger Transportation is then bigger, can reach 150m2.In terms of construction supporting：Apply in tunnel
Supporting quality is strict with work, is wearing coal section generally according to short drilling depth, soon weak blast, spray anchor, strong supporting, diligent monitoring and reinforcement
The principle of ventilation is constructed so as to ensure construction safety and construction quality, requires to reduce landslide in working face, once landslide will shadow
Project progress is rung, increases substantial amounts of project inputs；And coal mine roadway be in order to mine, so roadway support standard is relatively low, even if
Sump remedy is also very fast, can be taken sometimes or even also in order to avoid bigger dangerous generation and increase dose Vibration shot to induce
The generation of small-sized coal and gas prominent.Therefore, the Coal and Gas Outbursts Prediction method for indiscriminately imitating coal industry completely might not energy
Achieve the desired result, the result obtained using colliery routine Forecasting Methodology is sometimes with realizing that situation is not inconsistent, even if some coal seams
Indivedual indexs are not reaching to threshold values and coal and gas prominent also occur, even and if index that some coal seams are judged all has reached valve
Value does not also occur coal and gas prominent.
In recent years, the method that mathematical statistics is analyzed has been incorporated into disaster analysis by Many researchers, and disaster is carried out
Predict and simultaneously provide instruction to prophylactico-therapeutic measures, step analysis, fuzzy mathematics and neutral net are most widely used.
The content of the invention
The technical problem to be solved by the invention is to provide one kind accurately and efficiently to predict that tunnel coal is dashed forward with gas
The method of artificial situation.
It is the tunnel coal and gas prominent based on neutral net that the present invention, which solves the technical scheme that the technical problem uses,
Forecasting Methodology, it is characterised in that comprise the steps：
1) input data is determined：Determine 6 input datas, the respectively destruction of gas pressure, gas diffusion initial speed, coal
Type, coal body firmness coefficient, geological structure and vertical buried depth, 6 nodes of corresponding input layer；
2) algorithm parameter is set：BP neural network structure is 3 layers, wherein, 6 nodes of input layer, 11 nodes of hidden layer,
Transmission function is tansig, 2 nodes of output layer, transmission function logsig, trains function trainlm；Maximum train epochs
5000, target error 0.0001, learning rate is 0.01~0.8；Excitation function selects Sigmoid functions, initial value and threshold values
Between [0,1]；
3) train：Make the input data of BP neural network after sample is normalized, train small to sample error
After desired value, training is completed；Desired value is preset value, such as 0.0001 or smaller.Setting value is smaller, and iterations is more.
4) return and sentence：Training sample is calculated in the network trained using " sim " program in MATLAB,
Contrasted with expected result, that is, return and sentence checking.
If not meeting, continue to make interative computation, until reaching iterations or meeting precision.
5) live application：After checking, testing data is inputted, obtains prediction result.
Further, in the step 2), learning rate 0.2.
In step 1), the assignment mode of each input data is：
Gas pressure：Measured value
Gas diffusion initial speed：Measured value
Coal body Failure type：Different numerical value is entered as by type
Coal body firmness coefficient：Measured value
Geological structure：Different numerical value is entered as by type
Vertical buried depth：Measured value.
The present invention is realized using MATLAB.Each function in MATLAB is all preset, and each function has different functions,
For example, excitation function, transmission function are used for neuron calculates output by input, and it is to be based on to train function and learning function
Error changes weights and threshold value, completes and once trains, then proceed to iteration, until reaching iterations or meeting essence
Degree.No matter which kind of function, is all some mathematical functions, it is of course possible to for other programs, as linear function, power function, refer to
Number function is the same.
Beneficial effects of the present invention are：
A certain or some indexs, which reach threshold values, in conventional Forecasting Methodology will judge that coal and gas prominent occurs in the coal seam
Phenomenon, but this is often with realizing that situation is not inconsistent, some coal seams even if indivedual indexs are not reaching to threshold values and coal also occur dashes forward with gas
Go out, and some coal seams have all reached threshold values even if the index judged and have not also occurred coal and gas prominent.The offer of the present invention
Coal and Gas Outbursts Prediction method based on neutral net is by inputting the autonomous training of typical sample, the energy with comprehensive descision
Power, moreover, gradually increase increase with evaluation index number range with training samples number, can further improve coal with watt
This protrudes the accuracy of judged result；In addition, Forecasting Methodology provided by the invention, selected evaluation index easily obtains, and
It can be upgraded in time according to measured value, quickly get prominent judged result.
Embodiment
BP neural network is incorporated into tunnel coal and gas prominent by the present invention according to coal and gas prominent comprehensive function hypothesis
In prediction, by choosing rational prominent evaluation index, using BP neural network training and return to sentence tunnel coal dashed forward with gas
The danger gone out is predicted.
Coal and Gas Outbursts Prediction method in tunnel provided by the invention, comprises the following steps：
Step 1：Select coal and gas prominent evaluation index：
According to the comprehensive function hypothesis of coal and gas prominent, according to main property principle, property principle simple and easy to get, quantitative original
Then and data popularity principle, determine that tunnel coal and gas prominent evaluation index includes gas pressure, gas diffusion initial speed, coal
Failure type, coal body firmness coefficient, geological structure and vertical buried depth.
(1) gas pressure：Gas is the material base of coal and gas prominent, and gas pressure is bigger, when coal properties are identical
Its permeated in hole it is faster, it is also more favourable to the development of the crack of coal, therefore gas is the prominent principal element of reflection.In tunnel
Gas pressure data are easier to determine in construction, and gas monitor data are also relatively comprehensive in work progress, and the degree of accuracy is also higher,
So selection gas pressure is as one of network design index.
(2) gas diffusion initial speed：Gas diffusion initial speed is also coal bed gas diffusion initial speed, and what it reflected is that coal body is put
A property of gas is dissipated, but also the size of gas pressure and content can be reflected, its desired value size and outburst hazard
There is certain positive correlation, also preferably its numerical value is accurately determined in Practical Project.
(3) Failure type of coal：Coal texture type refers to form, degree of crushing, gloss and the coal of each part of coal body
Particle size situation, structure type reflects the coal mass strength, Coal Pore Structure and be squeezed destruction situation in the coal seam, can be with
The size for danger of having outstanding performance.During calculating the size of desired value according to coal body Failure type value.
(4) coal body firmness coefficient：The reflection of coal body firmness coefficient is coal mass strength, represents the destroyed difficulty or ease journey of coal body
Degree, its value is smaller to illustrate that the coal body is easier is crushed by pressure break, the destruction of coal in the case of identical crustal stress or geological structure
It is more serious.Certain thickness construction coal seam (soft layering), precisely due to low intensity is only prominent recurrent place, Er Qieqi
Intensity of outburst is generally large.
(5) geological structure：Geological structure is mainly tomography and fold to prominent influence, in practice it has proved that many prominent generations
In shear-zone, and shear-zone intensity of outburst is larger compared with its elsewhere intensity of outburst.In order to calculate analysis, geological structure is broken
It is simple that bad degree is divided into geological structure, and geological structure is normal, a small amount of tomography and fold, tomography fold are relatively developed and geological structure hair
5 grades are educated, respectively assignment 1~5.So qualitatively geological structure can participate in quantitative calculating, consider BP network calculations more
Influence factor.
(6) vertical buried depth：The bigger gas pressure of general buried depth and content are also bigger in the case of identical geological structure, vertically bury
Press deeply it is also bigger, its for protrusion provide certain energy., can be with according to geological mapping in gas tunnel construction
Probably determine to wear coal section vertical depth, can be further confirmed that in construction, so value is easier, and buried depth data essence
Exactness is also higher.
The assignment of each index is as shown in table 1.
The tunnel coal and gas prominent evaluation index assignment table of table 1
Step 2：Build BP neural network model：
Based on MATLAB platforms, the design of network structure and calculating are realized by calling BP tool boxes function.In order that
Network structure simplifies as far as possible, and the present invention uses single hidden layer neural network structure, and tunnel Coal and Gas Outbursts Prediction is constructed with this
Network structure model.Input layer is 6 evaluation indexes choosing, i.e. first layer totally 6 neurons；Output layer need to only differentiate
No protrusion, therefore third layer sets 2 neuron nodes；In the present invention, hidden layer neuron number passes through a large amount of tentative calculations
Analysis is defined as 11.
Learning rate and training function decide the stability and net training time of network, the excessive network knot of speed together
Structure computational stability can be deteriorated.Between generally learning rate takes 0.01~0.8, if computer conditions permit, is partial to
Take less learning rate.The determination of anticipation error also directly affects training time and precision, and anticipation error is excessive to cause essence
Degree reduces, and anticipation error is too small that repetition training number can be caused very big, and the anticipation error through the tentative calculation present invention is set to
0.0001 can make network have preferably calculating and Generalization Ability.Excitation function selects Sigmoid functions, and initial value and threshold values exist
Between [0,1].
Step 3：Input typical coal and gas prominent sample and be trained and return and sentence：
Because the numerical value difference between each evaluation index for selecting is larger, and between neuron transmission function span for [0,
1], it is to accelerate network calculations convergence rate and precision of prediction, it is necessary to which first data are normalized with pretreatment.For example, one group
Data Xj, influence index value is respectively x1、x2、x3、x4、x5And x6, then obtaining output valve after normalizing is：
In formula, xmin- this group data minimum value；
xmax- this group data maximums, i=1,2,3 ... .6.
Then the sample data after normalization is inputted the BP neural network established to be trained, sample error, which is less than, it is expected
Training is completed after error.
Training sample is calculated in the network trained using " sim " program in MATLAB, with expectation
Comparative result, that is, return and sentence checking.
Step 4：The prediction of coal and gas prominent is carried out to target gas tunnel：
6 evaluation indexes of the gas tunnel that needs are predicted input the god after having trained after being normalized
Calculated through network, you can complete to carry out target gas tunnel the prediction of coal and gas prominent.Prediction result also can be with it
The reliability of his Forecasting Methodology comparison test method provided by the present invention.
Below by embodiment, the present invention is described further.
The first step：Determine tunnel coal and gas prominent evaluation index include gas pressure, gas diffusion initial speed, coal it is broken
Bad type, coal body firmness coefficient, geological structure and vertical buried depth, selection coal and gas prominent data sample is as shown in table 2, sample
Data derive from Practical Project.
The coal and gas prominent data sample of table 2
Second step：BP neural network model is built, network structure is 3 layers, wherein, 6 nodes of input layer, hidden layer 11
Node, transmission function tansig, 2 nodes of output layer, transmission function logsig, training function trainlm；Maximum training step
Number 5000, target error 0.0001, learning rate 0.2.Specific procedure is：
Net=newff (minmax (X), [11,2], ' tansig''logsig'}, ' trainlm')；
Net.trainparam.show=25；
Net.trainparam.epochs=5000；
Net.trainparam.goal=0.0001；
Net.trainparam.lr=0.2.
3rd step：The matrix data file that sample data text editor 30 rows 6 of formation of table 2 are arranged, is imported
MATLAB softwares are normalized, and input net=train (net, X, T) and start training network, and the network is calculating 7
Sample error can reaches 1.9 × 10 after step-5, less than anticipation error 0.0001.
Training sample is calculated in the network trained using " sim " program, contrasted with expected result, i.e.,
Return and sentence checking.Specific procedure is Y=sim (net, X), returns that to sentence result as shown in table 3.
Table 3, which returns, sentences the result table
Sentence checking through returning, 30 groups of training samples correctly identify, identical with actual conditions, illustrate the network design ratio
Relatively rationally, training result is good.
4th step：The prediction of coal and gas prominent is carried out to target gas tunnel.In order to verify the network trained
Estimated performance, it is as shown in table 4 to have chosen the 10 groups of gas tunnel built data samples.
The gas tunnel data sample of table 4
The data for defining 10 groups of gas tunnels are Matrix C, are then differentiated using " sim " program function.Differentiation process
As returning and sentencing process, program is Y2=sim (net, C), actual to differentiate that output result and expected result are as shown in table 5.
The gas tunnel of table 5 differentiates result table
| Sequence number | Prominent situation | Desired output | Differentiate output | As a result it is whether identical |
| 1 | It is | (1,0) | (1.0000,0.0007) | It is |
| 2 | It is no | (0,1) | (0.0004,0.9993) | It is |
| 3 | It is | (1,0) | (1.0000,0.0010) | It is |
| 4 | It is | (1,0) | (0.9999,0.0040) | It is |
| 5 | It is | (1,0) | (0.7670,0.3408) | It is |
| 6 | It is | (1,0) | (1.0000,0.0011) | It is |
| 7 | It is no | (0,1) | (0.0004,0.9995) | It is |
| 8 | It is no | (0,1) | (0.0036,0.9976) | It is |
| 9 | It is no | (0,1) | (0.0202,0.9993) | It is |
| 10 | It is no | (0,1) | (0.0932,0.9980) | It is |
As shown in Table 5, the differentiation result of 10 groups of built gas tunnels is consistent with actual conditions.With training samples number
With the growth of influence factor number range, the differentiation accuracy of the network structure can further increase.
Specification is clear and completely illustrates the thinking of the present invention and necessary details, and those of ordinary skill can be according to
Implement the present invention according to specification, therefore the technology contents of more details repeat no more (such as the program statement realized).
Claims (4)
1. the tunnel Coal and Gas Outbursts Prediction method based on neutral net, it is characterised in that comprise the steps：
1) input data is determined：Determine 6 input datas, respectively gas pressure, gas diffusion initial speed, the destruction class of coal
Type, coal body firmness coefficient, geological structure and vertical buried depth, 6 nodes of corresponding input layer；
2) algorithm parameter is set：BP neural network structure is 3 layers, wherein, 6 nodes of input layer, 11 nodes of hidden layer, transmit
Function is tansig, 2 nodes of output layer, transmission function logsig, trains function trainlm；Maximum train epochs 5000, mesh
Error 0.0001 is marked, learning rate is 0.01~0.8；Excitation function is from Sigmoid functions, initial value and threshold values in [0,1]
Between；
3) train：Make the input data of BP neural network after sample is normalized, train to sample error and be less than the phase
After prestige value, training is completed；
4) return and sentence：Training sample is calculated in the network trained using " sim " program in MATLAB, with the phase
Comparative result is hoped, that is, returns and sentences checking；
5) live application：After checking, testing data is inputted, obtains prediction result.
2. the tunnel Coal and Gas Outbursts Prediction method based on neutral net as claimed in claim 1, it is characterised in that described
In step 2), learning rate 0.2.
3. the tunnel Coal and Gas Outbursts Prediction method based on neutral net as claimed in claim 1, it is characterised in that described
In step 1), the assignment mode of each input data is：
Gas pressure：Measured value
Gas diffusion initial speed：Measured value
Coal body Failure type：Different numerical value is entered as by type
Coal body firmness coefficient：Measured value
Geological structure：Different numerical value is entered as by type
Vertical buried depth：Measured value.
4. the tunnel Coal and Gas Outbursts Prediction method based on neutral net as claimed in claim 3, it is characterised in that described
In step 1),
The assignment of coal body Failure type corresponds to its series, respectively 1,2,3,4,5 grade；
Geological structure is according to following corresponding relation assignment：
0.2 geological structure is simple, and 0.4 geological structure is general, 0.6 a small amount of tomography and fold；0.8 tomography fold is relatively developed；1 geology
Construct pole development.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710489806.5A CN107403234A (en) | 2017-06-24 | 2017-06-24 | Tunnel Coal and Gas Outbursts Prediction method based on neutral net |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710489806.5A CN107403234A (en) | 2017-06-24 | 2017-06-24 | Tunnel Coal and Gas Outbursts Prediction method based on neutral net |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107403234A true CN107403234A (en) | 2017-11-28 |
Family
ID=60404709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710489806.5A Pending CN107403234A (en) | 2017-06-24 | 2017-06-24 | Tunnel Coal and Gas Outbursts Prediction method based on neutral net |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107403234A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492816A (en) * | 2018-11-16 | 2019-03-19 | 辽宁工程技术大学 | A kind of coal and gas prominent dynamic prediction method based on hybrid intelligent |
| CN109934398A (en) * | 2019-03-05 | 2019-06-25 | 山东大学 | A kind of drill bursting construction tunnel gas danger classes prediction technique and device |
| CN110397472A (en) * | 2019-06-20 | 2019-11-01 | 平安煤矿瓦斯治理国家工程研究中心有限责任公司 | The prediction technique of coal and gas prominent, apparatus and system |
| CN111079978A (en) * | 2019-11-20 | 2020-04-28 | 辽宁工程技术大学 | Coal and gas outburst prediction method based on logistic regression and reinforcement learning |
| CN111222238A (en) * | 2020-01-03 | 2020-06-02 | 辽宁工程技术大学 | Rapid prediction method for gas explosion shock wave propagation state for emergency rescue |
| 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 |
| CN112183901A (en) * | 2020-11-06 | 2021-01-05 | 贵州工程应用技术学院 | Coal and gas outburst strength prediction method based on deep learning |
| CN112308306A (en) * | 2020-10-27 | 2021-02-02 | 贵州工程应用技术学院 | Multi-mode input coal and gas outburst risk prediction method |
| CN114046179A (en) * | 2021-09-15 | 2022-02-15 | 山东省计算中心（国家超级计算济南中心） | Method for intelligently identifying and predicting underground safety accident based on CO monitoring data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09218192A (en) * | 1996-02-14 | 1997-08-19 | Snow Brand Milk Prod Co Ltd | Method for predicting taste of yoghurt |
| CN101344389A (en) * | 2008-08-20 | 2009-01-14 | 中国建筑第八工程局有限公司 | Method for estimating tunnel surrounding rock displacement by neural network |
| CN101436264A (en) * | 2008-11-28 | 2009-05-20 | 北京交通大学 | Mine downhole debris flow prediction method based on subsection fuzzy BP neural network |
| 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 |
| CN104850897A (en) * | 2015-02-25 | 2015-08-19 | 中国矿业大学 | Prediction method for coal and gas outburst based on seismic information |
| CN105550769A (en) * | 2015-12-09 | 2016-05-04 | 贵州省矿山安全科学研究院 | Dynamic prediction method for residual gas content distribution after coal seam pre-pumping |
| CN105976025A (en) * | 2016-03-18 | 2016-09-28 | 孙胜伟 | BP neural network gas prediction method based on genetic algorithm optimization |
-
2017
- 2017-06-24 CN CN201710489806.5A patent/CN107403234A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09218192A (en) * | 1996-02-14 | 1997-08-19 | Snow Brand Milk Prod Co Ltd | Method for predicting taste of yoghurt |
| CN101344389A (en) * | 2008-08-20 | 2009-01-14 | 中国建筑第八工程局有限公司 | Method for estimating tunnel surrounding rock displacement by neural network |
| CN101436264A (en) * | 2008-11-28 | 2009-05-20 | 北京交通大学 | Mine downhole debris flow prediction method based on subsection fuzzy BP neural network |
| 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 |
| CN104850897A (en) * | 2015-02-25 | 2015-08-19 | 中国矿业大学 | Prediction method for coal and gas outburst based on seismic information |
| CN105550769A (en) * | 2015-12-09 | 2016-05-04 | 贵州省矿山安全科学研究院 | Dynamic prediction method for residual gas content distribution after coal seam pre-pumping |
| CN105976025A (en) * | 2016-03-18 | 2016-09-28 | 孙胜伟 | BP neural network gas prediction method based on genetic algorithm optimization |
Non-Patent Citations (1)
| Title |
|---|
| 张振强: "铁路瓦斯隧道分类及煤与瓦斯突出预测方法研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492816A (en) * | 2018-11-16 | 2019-03-19 | 辽宁工程技术大学 | A kind of coal and gas prominent dynamic prediction method based on hybrid intelligent |
| CN109492816B (en) * | 2018-11-16 | 2021-11-09 | 辽宁工程技术大学 | Coal and gas outburst dynamic prediction method based on hybrid intelligence |
| CN109934398A (en) * | 2019-03-05 | 2019-06-25 | 山东大学 | A kind of drill bursting construction tunnel gas danger classes prediction technique and device |
| CN110397472A (en) * | 2019-06-20 | 2019-11-01 | 平安煤矿瓦斯治理国家工程研究中心有限责任公司 | The prediction technique of coal and gas prominent, apparatus and system |
| CN111079978B (en) * | 2019-11-20 | 2023-07-25 | 辽宁工程技术大学 | Coal and gas outburst prediction method based on logistic regression and reinforcement learning |
| CN111079978A (en) * | 2019-11-20 | 2020-04-28 | 辽宁工程技术大学 | Coal and gas outburst prediction method based on logistic regression and reinforcement learning |
| CN111222238A (en) * | 2020-01-03 | 2020-06-02 | 辽宁工程技术大学 | Rapid prediction method for gas explosion shock wave propagation state for emergency rescue |
| 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 |
| CN112308306A (en) * | 2020-10-27 | 2021-02-02 | 贵州工程应用技术学院 | Multi-mode input coal and gas outburst risk prediction method |
| CN112183901A (en) * | 2020-11-06 | 2021-01-05 | 贵州工程应用技术学院 | Coal and gas outburst strength prediction method based on deep learning |
| CN114046179A (en) * | 2021-09-15 | 2022-02-15 | 山东省计算中心（国家超级计算济南中心） | Method for intelligently identifying and predicting underground safety accident based on CO monitoring data |
| CN114046179B (en) * | 2021-09-15 | 2023-09-22 | 山东省计算中心（国家超级计算济南中心） | Method for intelligently identifying and predicting underground safety accidents based on CO monitoring data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107403234A (en) | Tunnel Coal and Gas Outbursts Prediction method based on neutral net | |
| CN104533400B (en) | Method for reconstructing logging curve | |
| CN104727798B (en) | A kind of low permeability gas reservoir turns to refracturing process | |
| AU2020102747A4 (en) | A decision-making method for in-situ remediation of petroleum-contaminated groundwater | |
| CN109034582A (en) | Tunnel Passing inrush through faults based on cloud model and combination weighting are dashed forward mud risk evaluating method | |
| CN105626009A (en) | Fracture-cavern type carbonate oil reservoir single well water injection oil substituting effect quantitative evaluation method | |
| CN102455438B (en) | Method for predicting volume of carbonate rock fractured cave type reservoir | |
| CN103268420A (en) | Method for evaluating risks of high rock slope | |
| CN106407493A (en) | Multi-dimensional Gaussian cloud model-based rock burst grade evaluation method | |
| CN104616350A (en) | Fracture-cavity type carbonate oil reservoir three-dimensional physical model establishing method | |
| CN104133985A (en) | Evaluation method of geological disaster risk attribute interval of tunnel and underground construction | |
| CN106250984A (en) | The determination methods of the oil water relation pattern of oil well and device | |
| CN109214026A (en) | A kind of shale gas horizontal well initial productivity prediction technique | |
| CN110298107B (en) | Working face impact risk evaluation method based on incremental stacking | |
| Lee et al. | Selection and evaluation of enhanced oil recovery method using artificial neural network | |
| CN106326624A (en) | Method for predicating stratum fracture pressure | |
| CN104091069A (en) | Method for determining oil driving efficiency and sweep coefficient of all layers and positions of heterogeneous reservoir stratum | |
| CN104179514A (en) | Method for water inrush prediction and seepage control for underwater-tunnel broken surrounding rocks | |
| CN103530818A (en) | Water supply pipe network modeling method based on BRB (belief-rule-base) system | |
| CN104200292A (en) | Forecasting method for height of water-flowing fractured zone | |
| CN107239845A (en) | The construction method of effect of reservoir development forecast model | |
| CN112541571A (en) | Injection-production connectivity determination method based on machine learning of double parallel neural networks | |
| Qiu et al. | TBM tunnel surrounding rock classification method and real-time identification model based on tunneling performance | |
| CN117786794A (en) | Shield tunneling existing tunnel deformation optimization control method and system | |
| Yao et al. | Evaluation of enhanced oil recovery methods for mature continental heavy oil fields in China based on geology, technology and sustainability criteria |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171128 |
|
| WD01 | Invention patent application deemed withdrawn after publication |