CN106703883A - Method for determining floor water inrush danger level of coal mining working faces in personalized manner - Google Patents
Method for determining floor water inrush danger level of coal mining working faces in personalized manner Download PDFInfo
- Publication number
- CN106703883A CN106703883A CN201611243211.3A CN201611243211A CN106703883A CN 106703883 A CN106703883 A CN 106703883A CN 201611243211 A CN201611243211 A CN 201611243211A CN 106703883 A CN106703883 A CN 106703883A
- Authority
- CN
- China
- Prior art keywords
- water
- inrush
- danger classes
- water inrush
- independent variable
- 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.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000003245 coal Substances 0.000 title claims abstract description 21
- 238000005065 mining Methods 0.000 title abstract description 9
- 230000006870 function Effects 0.000 claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 239000011435 rock Substances 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 230000009172 bursting Effects 0.000 claims description 19
- 239000003673 groundwater Substances 0.000 claims description 9
- 230000000630 rising effect Effects 0.000 claims description 7
- 231100001261 hazardous Toxicity 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 2
- 230000008859 change Effects 0.000 abstract description 2
- 230000006378 damage Effects 0.000 abstract description 2
- 238000011161 development Methods 0.000 abstract description 2
- 238000009413 insulation Methods 0.000 abstract 3
- 239000007921 spray Substances 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000007634 remodeling Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK 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
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Mining & Mineral Resources (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Geology (AREA)
- Educational Administration (AREA)
- Geochemistry & Mineralogy (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a method for determining floor water inrush danger level of coal mining working faces in a personalized manner, and belongs to the field of coal safety mining. Factors such as water pressures of floors of the coal mining working faces, the thicknesses of water-insulation layers, destruction phenomena of floors of coal seams due to mine pressures, lithological combinations of rock strata of water-insulation sections and original guide rise and development phenomena of floor confined underground water are comprehensively considered, implicit functional dependency relationships between the influence factors and the water inrush danger level are established, and comprehensive evaluation index systems for evaluating the floor water inrush danger level can be established by means of interpolation analysis on sudden change points of implicit functions. The method has the advantages that the various factors which can affect coal mining floor water inrush thread are comprehensively considered, the functional dependency relationships between the various influence factors and water inrush coefficients are established, accordingly, the difficult problem that only water pressures and the thicknesses of water-insulation layers are considered in the traditional method or functional dependency relationships between influence factors and water inrush coefficients cannot be established is solved, and the novel method can be provided for computing the water inrush coefficients.
Description
Technical field
The invention belongs to safety of coal mines production technique field, and in particular to a kind of personalized determination coal-face base plate is dashed forward
The method of water danger classes.
Background technology
The dangerous method of safety of coal mines exploitation Water Inrush is evaluated at present mainly uses water inrush coefficient method.Water bursting coefficient meter
Calculate used for reference during formula T=p/M is China's hydrogeology decisive battle of Jiaozhuo in 1964 Hungary engineer Wei Gefulunsi to every
What water thickness (T=M/p) concept was proposed, p is seat earth aquifer water pressure in formula, and M is seat earth impermeable layer thickness.Should
After formula is proposed, with the inundation mine area Water Inrush case such as Jiaozhuo, peak-to-peak, Jingxing, Handan, Feicheng, Zibo and basic data
It is foundation, it is safety to calculate T≤0.06MPa/m, and 0.06MPa/m < T≤MPa/m is safer, and 0.1MPa/m < T are danger
Danger.Water bursting coefficient reflects the most basic rule of seepage action of ground water in hydrogeology.
Considerably long period of history afterwards, water bursting coefficient plays an important role for instructing safety of coal mines to exploit.
But with shallow-layer coal seam resource exploitation totally, coal mining progressively turns to deep, and the hydraulic pressure of Ordovician karst water is stepped up, in reality
Water bursting coefficient is far longer than in exploitation《Mine geological hazards specify》0.1MPa/m.Although later stage someone considers Seam Floor Failure
Degree, water proof section rock stratum lithology combination and other influence factors, it is proposed that the computing formula of various water bursting coefficients, but proposed
The adjacent value that adjacency coefficient was still proposed using 1964.Obviously, this is ill-considered.
There are the following problems for current water bursting coefficient computational methods:
1. the factor of influence Spray water way considers not comprehensive
Water bursting coefficient computing formula only accounts for hydraulic pressure and impermeable layer thickness, does not account for seat earth ore deposit and crushes bad journey
The relevant factors such as degree, water proof section rock stratum lithology combination, base plate artesian groundwater rising height, aquifer water well index.
2. the functional dependencies between Spray water way and influence factor are not set up using machine learning method
The water bursting coefficient computing formula Consideration of early stage is few, and computing formula is simple.The computing formula Consideration in later stage
It is many, in the case where collecting sample is less, it is impossible to fit the functional dependencies between water bursting coefficient and influence factor.
3. what water bursting coefficient was given is only the danger of gushing water, and unrelated with water inrush quantity
Current water bursting coefficient is can be seen that from its computing formula T=p/M only consider seat earth aquifer water pressure, coal
The factors such as layer water-resisting floor thickness, it doesn't matter with actual water inrush quantity.If floor water-bearing rock is rich in actual recovery process
It is aqueous poor, even gushing water, because water inrush quantity is smaller, larger harm will not be also brought to coal mining working face.
The content of the invention
In view of the above-mentioned problems existing in the prior art, the present invention proposes a kind of personalized determination coal-face base plate and dashes forward
The method of water danger classes.
The adopted technical solution is that:
A kind of personalized method for determining Water Inrush From Working-faces danger classes, is carried out according to the following steps:
Step one:Coal-face integrated data during coal production is collected, maximal water*.inrush quality and various influences are analyzed
The correlation of factor, selects corresponding species influence factor as the independent variable of influence Water Inrush danger classes;
Step 2:According to specific mine comprehensive draining ability and maximal water*.inrush quality data, personalization divides Water Inrush danger
Dangerous grade;
Step 3:The vector combination of independent variable is denoted as x, Water Inrush danger classes is denoted as y, sets up independent variable and base plate
The Implicitly function dependence of gushing water danger classes;
Step 4:The vector combination x of the independent variable that will newly collect substitutes into the Implicitly function dependence set up in step 3 and closes
System, is calculated Water Inrush danger classes y, then determines Water Inrush danger classes according to step 2.
The above method is further comprising the steps of:
Step 5:The Implicitly function dependence set up using step 3, it is prominent in each base plate to each independent variable subdivision interpolation
In the range of water danger classes, very big, the minimum of each independent variable are asked in reversely calculation, set up each independent variable dangerous with Water Inrush
The System of Comprehensive Evaluation of grade;
Step 6:Each independent variable and the System of Comprehensive Evaluation of Water Inrush danger classes set up according to step 5,
Field personnel is to the argument data that newly collects, you can determine that Water Inrush is endangered by inquiring about System of Comprehensive Evaluation
Dangerous grade.
Preferably, in step one:The coal-face integrated data includes maximal water*.inrush quality, water bursting coefficient, coal seam bottom
Plate ore deposit pressure destructiveness, water proof section rock stratum lithology combination, base plate artesian groundwater rising height and aquifer water well index etc.;
Analysis maximal water*.inrush quality presses destructiveness, water proof section rock stratum lithology combination, base plate pressure-bearing with water bursting coefficient, seat earth ore deposit respectively
The correlation of the various factors such as underground water rising height and aquifer water well index, and phase is selected according to correlation size
Species influence factor such as seat earth ore deposit pressure destructiveness, base plate artesian groundwater rising height etc. are answered as influence Water Inrush
The independent variable of danger classes.
Preferably, in step 2:Water Inrush dangerous grade classification is safe, relatively hazardous, dangerous Three Estate;Maximum is prominent
Water is set to safe class 1 less than or equal to specific mine comprehensive draining ability 2/3rds;Maximal water*.inrush quality is more than specific ore deposit
Mountain comprehensive draining ability 2/3rds and it is set to relatively hazardous grade 2 less than or equal to specific mine comprehensive draining ability;Maximum is prominent
Water is set to danger classes 3 more than specific mine comprehensive draining ability.
Preferably, in step 3:The n observation sample (x according to known to specific mine1,y1),(x2,y2)……(xn,yn)
Optimal function f (x, a ω are asked in some functions { f (x, ω) }0), unknown dependence is estimated, make formula R (ω)=∫
Expected risk shown in L (y, f (x, ω)) dF (x, y) is minimum.
In above-mentioned steps three, the independent variable of foundation and the Implicitly function dependence of Water Inrush danger classes, by machine
The realization of the device theories of learning, specifically:
(1) { f (x, ω) } is anticipation function collection, and ω is referred to as Generalized Parameters, and L (y, f (x, ω)) is loss function;
(2) loss function uses L (y, f (x, ω))=(y-f (x, ω))2;
(3) utilizable information only has sample data in the training process, it is therefore desirable for risk
R (ω)=∫ L (y, f (x, ω)) dF (x, y) cannot be calculated, and be usedTo it
Estimated;
(4) in calculating process, training is successive value using the danger classes of regression forecasting, the method using rounding up
Round.
Preferably, in step 4:The vector combination x of independent variable is actually obtained during construction exploration, coal work;It is right
In the location for not carrying out physical prospecting, interpolative prediction is carried out by three-dimensional mine mathematical model, first prediction, rear adjustment.
Preferably, in step 5 specifically:
(1) very big, the minimum of each component of the vector combination x of analysis independent variable;
(2) subtracted by maximum minimum difference 1 percent in units of, subdivision interpolation;
(3) the Water Inrush danger classes of each interpolation point is asked for, danger classes now does not carry out the treatment that rounds up;
(4) ask gushing water danger classes it is interval [0,1.5), [1.5,2.5), [2.5,3.5) when, each independent variable it is very big,
Minimum, sets up the System of Comprehensive Evaluation of each independent variable and Water Inrush danger classes.
The method have the benefit that:
Compared with prior art, the present invention considers specific mine drainage ability, the various factors of influence water inrush quantity, builds
Implicitly function dependence between the dangerous grading of vertical gushing water and influence factor, using parameter region interpolation agriculture products framework, solution
The technical barriers such as gushing water data of having determined Small samples modeling, Implicitly function application difficult so that gushing water danger classes evaluates more section
Learn reasonable, meet mining production reality.
Brief description of the drawings
Fig. 1 is a kind of personalized flow chart for determining Water Inrush From Working-faces danger classes method of the present invention.
Specific embodiment
The invention provides a kind of personalized method for determining Water Inrush From Working-faces danger classes.The method synthesis
Consider coal-face base plate hydraulic pressure, impermeable layer thickness, seat earth ore deposit pressure breakoff phenomenon, water proof section rock stratum lithology combination, bottom
Plate artesian groundwater is original to lead the factors such as liter development phenomenon, set up the Implicitly function of these influence factors and gushing water danger classes according to
The relation of relying, by the catastrophe point of the interpolation analysis Implicitly function, sets up the comprehensive evaluation index for evaluating Water Inrush danger classes
System.The method considers the various factors for influenceing coal mining Water Inrush to threaten comprehensively, sets up each influence factor and gushing water system
Several functional dependencies, solve conventional method and only consider water pressure and impermeable layer thickness or cannot set up influence factor and dash forward
The problem of water coefficient functional dependencies, new method is provided for water bursting coefficient is calculated.
Below in conjunction with the accompanying drawings and specific embodiment is described in further detail to the present invention:
As shown in figure 1, a kind of method that Water Inrush From Working-faces danger classes is determined for personalization, according to as follows
Step is carried out:
Step one:Coal-face maximal water*.inrush quality, water bursting coefficient, seat earth ore deposit are crushed during collection coal production
The integrated datas such as bad degree, water proof section rock stratum lithology combination, base plate artesian groundwater rising height, aquifer water well index,
Analysis maximal water*.inrush quality presses the correlation of other influence factors such as destructiveness with water bursting coefficient, seat earth ore deposit, and selection is related
Property influence factor higher as influence maximal water*.inrush quality independent variable.
Step 2:According to specific mine comprehensive draining ability and maximal water*.inrush quality data, personalization divides each group of data
Water Inrush danger classes.Generally it is divided into safe, relatively hazardous, dangerous Three Estate.Maximal water*.inrush quality is less than or waits
It is set to safe class 1 in specific mine comprehensive draining ability 2/3rds;Maximal water*.inrush quality is more than specific mine comprehensive draining energy
Power 2/3rds and it is set to relatively hazardous grade 2 less than specific mine comprehensive draining ability;Maximal water*.inrush quality is more than or equal to specific
Mine comprehensive draining ability is set to danger classes 3.
Step 3:The vector combination of independent variable is denoted as x, Water Inrush danger classes is denoted as y.According to known to specific mine
N observation sample (x1,y1),(x2,y2)……(xn,yn) asked in some functions { f (x, ω) } an optimal function f (x,
ω0), unknown dependence is estimated, make expected risk shown in formula R (ω)=∫ L (y, f (x, ω)) dF (x, y) most
It is small.
The functional dependencies of each influence factor and Water Inrush danger classes that step 3 is set up be implicit function according to
The relation of relying, can realize by machine Learning Theories such as SVMs theories.
Specifically:
(1) { f (x, ω) } is anticipation function collection, and ω is referred to as Generalized Parameters, and L (y, f (x, ω)) is loss function.
(2) loss function uses L (y, f (x, ω))=(y-f (x, ω))2。
(3) utilizable information only has sample data in the training process, it is therefore desirable for risk R (ω)=∫ L (y, f
(x, ω)) dF (x, y) cannot calculate, usesIt is estimated.
(4) in calculating process, training is successive value using the danger classes of regression forecasting, the method using rounding up
Round.
Step 4:According to the Implicitly function dependence that step 3 is set up, the data vector to newly collecting influence factor
That is the vector combination x of independent variable, you can substitute into Implicitly function and calculate its Water Inrush danger classes.Water Inrush danger classes shadow
The factor of sound can actually be obtained during construction exploration, coal work.For the location for not carrying out physical prospecting, can be by three
Dimension mine mathematical model carries out interpolative prediction, first prediction, rear adjustment.
Step 5:For convenience of live practical application, the Implicitly function dependence set up using step 3, to each independent variable
Subdivision interpolation, in the range of each Water Inrush danger classes, very big, the minimum of each independent variable are asked in reversely calculation, set up each
The System of Comprehensive Evaluation of independent variable and Water Inrush danger classes.
Specifically:
(1) very big, the pole of each component of analysis Water Inrush danger classes influence factor (the vector combination x of independent variable)
Small value.
(2) subtracted by maximum minimum difference 1 percent in units of, subdivision interpolation.
(3) the Water Inrush danger classes of each interpolation point is asked for, danger classes now does not carry out the treatment that rounds up.
(4) ask gushing water danger classes it is interval [0,1.5), [1.5,2.5), [2.5,3.5) when, each independent variable it is very big,
Minimum, sets up the System of Comprehensive Evaluation of each independent variable and Water Inrush danger classes.
Step 6:Each independent variable and the System of Comprehensive Evaluation of Water Inrush danger classes set up according to step 5, it is existing
Staff is to newly collecting the data of influence factor, you can determine that Water Inrush is endangered by inquiring about System of Comprehensive Evaluation
Dangerous grade.
What the present invention proposed Spray water way in step one it is critical only that water inrush quantity, and not exclusively water inrush coefficient with
The ratio of impermeable layer thickness.And considered in step one the influence water bursting coefficient of water inrush quantity, seat earth ore deposit crush it is bad
The factors such as degree, water proof section rock stratum lithology combination, base plate artesian groundwater rising height, aquifer water well index.
According to the personalized division mine coal-face gushing water danger classes of specific mine drainage ability in step 2, and
It is not all mine sudden flooding danger classes of universal formulation.
Under conditions of it cannot provide gushing water influence factor and maximal water*.inrush quality explicit function dependence, in step 3
The functional dependencies of maximal water*.inrush quality and each influence factor are described using Implicitly function dependence, the functional dependencies will
Ask:For data sample (x1,y1),(x2,y2),(x3,y3)……(xn,yn), ask one most in some functions { f (x, ω) }
Major function f (x, ω0), unknown dependence is estimated so that the expected risk shown in following formula is minimum.
R (ω)=∫ L (y, f (x, ω)) dF (x, y)
To each influence factor subdivision interpolation in step 5, in the range of each Water Inrush danger classes, reversely calculation is asked
Very big, the minimum of each independent variable are taken, the System of Comprehensive Evaluation of each independent variable and Water Inrush danger classes is set up.
The present invention proposes a kind of method that Water Inrush From Working-faces danger classes is determined for personalization, and existing
Technology is compared, and the present invention considers specific mine drainage ability, the various factors of influence water inrush quantity, sets up the dangerous grading of gushing water
Implicitly function dependence between influence factor, using parameter region interpolation agriculture products framework, solve gushing water data small
The technical barriers such as sample, Implicitly function application difficult so that gushing water danger classes evaluates more scientific and reasonable, meets mine
Produce reality.
Take or use for reference prior art to be capable of achieving in the part do not addressed in aforesaid way.
Described above is not limitation of the present invention, and the present invention is also not limited to the example above, the art
Change, remodeling, addition or replacement that technical staff is made in essential scope of the invention, should also belong to protection of the invention
Scope.
Claims (8)
1. a kind of method that personalization determines Water Inrush From Working-faces danger classes, it is characterised in that enter according to the following steps
OK:
Step one:Coal-face integrated data during coal production is collected, maximal water*.inrush quality and various factors are analyzed
Correlation, select corresponding species influence factor as the independent variable of influence Water Inrush danger classes;
Step 2:According to specific mine comprehensive draining ability and maximal water*.inrush quality data, personalization divides Water Inrush danger etc.
Level;
Step 3:The vector combination of independent variable is denoted as x, Water Inrush danger classes is denoted as y, sets up independent variable and Water Inrush
The Implicitly function dependence of danger classes;
Step 4:The vector combination x of the independent variable that will newly collect substitutes into the Implicitly function dependence set up in step 3, meter
Calculation obtains Water Inrush danger classes y, then determines Water Inrush danger classes according to step 2.
2. the method that a kind of personalization according to claim 1 determines Water Inrush From Working-faces danger classes, it is special
It is further comprising the steps of to levy:
Step 5:The Implicitly function dependence set up using step 3, to each independent variable subdivision interpolation, in each Water Inrush danger
In dangerous rate range, very big, the minimum of each independent variable are asked in reversely calculation, set up each independent variable and Water Inrush danger classes
System of Comprehensive Evaluation;
Step 6:Each independent variable and the System of Comprehensive Evaluation of Water Inrush danger classes set up according to step 5, scene
Staff is to the argument data that newly collects, you can determine Water Inrush danger etc. by inquiring about System of Comprehensive Evaluation
Level.
3. the method that a kind of personalization according to claim 1 determines Water Inrush From Working-faces danger classes, it is special
Levy and be, in step one:The coal-face integrated data includes that maximal water*.inrush quality, water bursting coefficient, seat earth ore deposit are crushed
Bad degree, water proof section rock stratum lithology combination, base plate artesian groundwater rising height and aquifer water well index;Analysis is maximum prominent
Water leads liter with water bursting coefficient, seat earth ore deposit pressure destructiveness, water proof section rock stratum lithology combination, base plate artesian groundwater respectively
The correlation of height and aquifer water well index, and corresponding species influence factor is selected as influence bottom according to correlation size
The independent variable of plate gushing water danger classes.
4. the method that a kind of personalization according to claim 1 determines Water Inrush From Working-faces danger classes, it is special
Levy and be, in step 2:Water Inrush dangerous grade classification is safe, relatively hazardous, dangerous Three Estate;Maximal water*.inrush quality is less than
Or it is set to safe class 1 equal to specific mine comprehensive draining ability 2/3rds;Maximal water*.inrush quality is comprehensively arranged more than specific mine
Outlet capacity 2/3rds and it is set to relatively hazardous grade 2 less than or equal to specific mine comprehensive draining ability;Maximal water*.inrush quality is more than
Specific mine comprehensive draining ability is set to danger classes 3.
5. the method that a kind of personalization according to claim 1 determines Water Inrush From Working-faces danger classes, it is special
Levy and be, in step 3:The n observation sample (x according to known to specific mine1,y1),(x2,y2)……(xn,yn) in some functions
Optimal function f (x, a ω are asked in { f (x, ω) }0), unknown dependence is estimated, make formula R (ω)=∫ L (y, f (x,
ω)) expected risk shown in dF (x, y) is minimum.
6. the method that a kind of personalization according to claim 5 determines Water Inrush From Working-faces danger classes, it is special
Levy and be:The independent variable of foundation and the Implicitly function dependence of Water Inrush danger classes, realize by machine Learning Theory,
Specifically:
(1) { f (x, ω) } is anticipation function collection, and ω is referred to as Generalized Parameters, and L (y, f (x, ω)) is loss function;
(2) loss function uses L (y, f (x, ω))=(y-f (x, ω))2;
(3) utilizable information only has sample data in the training process, it is therefore desirable for risk R (ω)=∫ L (y, f (x,
ω)) dF (x, y) cannot be calculated, and be usedIt is estimated;
(4) in calculating process, training is successive value using the danger classes of regression forecasting, is taken using the method for rounding up
It is whole.
7. the method that a kind of personalization according to claim 1 determines Water Inrush From Working-faces danger classes, it is special
Levy and be, in step 4:The vector combination x of independent variable is actually obtained during construction exploration, coal work;For do not carry out
The location of physical prospecting, interpolative prediction is carried out by three-dimensional mine mathematical model, first prediction, rear adjustment.
8. the method that a kind of personalization according to claim 1 determines Water Inrush From Working-faces danger classes, it is special
Levy in being step 5, specifically:
(1) very big, the minimum of each component of the vector combination x of analysis independent variable;
(2) subtracted by maximum minimum difference 1 percent in units of, subdivision interpolation;
(3) the Water Inrush danger classes of each interpolation point is asked for, danger classes now does not carry out the treatment that rounds up;
(4) ask gushing water danger classes it is interval [0,1.5), [1.5,2.5), [2.5,3.5) when, each independent variable it is very big, minimum
Value, sets up the System of Comprehensive Evaluation of each independent variable and Water Inrush danger classes.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611243211.3A CN106703883B (en) | 2016-12-29 | 2016-12-29 | A kind of personalized method for determining Water Inrush From Working-faces danger classes |
PCT/CN2017/108619 WO2018121035A1 (en) | 2016-12-29 | 2017-10-31 | Customized method for determining coal mining face floor water inrush risk level |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611243211.3A CN106703883B (en) | 2016-12-29 | 2016-12-29 | A kind of personalized method for determining Water Inrush From Working-faces danger classes |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106703883A true CN106703883A (en) | 2017-05-24 |
CN106703883B CN106703883B (en) | 2018-03-13 |
Family
ID=58906146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611243211.3A Active CN106703883B (en) | 2016-12-29 | 2016-12-29 | A kind of personalized method for determining Water Inrush From Working-faces danger classes |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106703883B (en) |
WO (1) | WO2018121035A1 (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107165626A (en) * | 2017-06-30 | 2017-09-15 | 徐州市耐力高分子科技有限公司 | A kind of coal-face floods prevention method with cranny development country rock top plate |
CN107237644A (en) * | 2017-06-30 | 2017-10-10 | 湖南科技大学 | The determination method of the three-dimensional gushing water destruction critical hydraulic pressure of tunnel inverted arch and critical thickness |
CN107784437A (en) * | 2017-10-16 | 2018-03-09 | 重庆大学 | A kind of Driving Face in Coal Tunnel outburst danger discrimination method based on stress concentration |
WO2018121035A1 (en) * | 2016-12-29 | 2018-07-05 | 山东科技大学 | Customized method for determining coal mining face floor water inrush risk level |
CN109598102A (en) * | 2019-02-01 | 2019-04-09 | 内蒙古科技大学 | Prediction technique, device, equipment and the medium of coal mine rock burst degree of danger |
CN109948268A (en) * | 2019-01-21 | 2019-06-28 | 安迈智能(北京)矿山科技股份有限公司 | A kind of working face integrated risk automatic identifying method |
CN110533224A (en) * | 2019-08-06 | 2019-12-03 | 山东科技大学 | A kind of oil shale connecting exploratory bore-hole position preferred method |
CN110552741A (en) * | 2019-09-09 | 2019-12-10 | 中煤科工集团西安研究院有限公司 | coal face bottom plate water inrush comprehensive monitoring and early warning system and method |
CN111239840A (en) * | 2020-02-25 | 2020-06-05 | 华北科技学院 | Baseplate water inrush early warning method based on high-density electrical method |
CN111652490A (en) * | 2020-05-28 | 2020-09-11 | 山东科技大学 | New deep mine tectonic type water inrush prediction method based on fracture mechanics theory |
CN114087022A (en) * | 2021-10-28 | 2022-02-25 | 山东科技大学 | Coal seam floor variable parameter water inrush channel early warning system and water inrush danger judgment method |
CN118154046A (en) * | 2024-05-10 | 2024-06-07 | 太原向明智控科技有限公司 | Top plate pressure grade dividing method |
Families Citing this family (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109359374A (en) * | 2018-10-10 | 2019-02-19 | 山东科技大学 | The Secondary Fuzzy Comprehensive Evaluation method of evaluating coal seam bottom water bursting |
CN109800955A (en) * | 2018-12-24 | 2019-05-24 | 永城煤电控股集团有限公司 | Coal seam bottom water bursting hazard assessment calculation method |
CN110532872A (en) * | 2019-07-24 | 2019-12-03 | 宁德市公路局 | A kind of landslide hierarchy system and method based on convolution supporting vector neural network |
CN111127234B (en) * | 2019-10-11 | 2024-01-19 | 重庆大学 | Method and device for determining first mining layer of outburst coal seam group mining |
CN111260216B (en) * | 2020-01-15 | 2023-06-30 | 山东大学 | Comprehensive evaluation and control method for seepage field of underground water seal oil storage in operation period |
CN111222254A (en) * | 2020-01-22 | 2020-06-02 | 西安科技大学 | Working face rock burst danger grade dividing method and system based on stress superposition method |
CN111563653A (en) * | 2020-04-03 | 2020-08-21 | 山东大学 | Early warning construction method for water-rich broken stratum of underground engineering |
CN111562285A (en) * | 2020-06-03 | 2020-08-21 | 安徽大学 | Mine water inrush source identification method and system based on big data and deep learning |
CN111652509B (en) * | 2020-06-03 | 2024-02-13 | 华北科技学院 | Method for classifying and distinguishing water inrush risk of Taiyuan limestone aquifer based on multiple variables |
CN111814322B (en) * | 2020-06-24 | 2023-11-10 | 应急管理部信息研究院 | Working face overlying strata damage height determining method based on half-plane theory |
CN114329680B (en) * | 2020-10-09 | 2024-04-16 | 神华神东煤炭集团有限责任公司 | Mining area underground reservoir pillar dam body stability evaluation method and application thereof |
CN112668873B (en) * | 2020-12-25 | 2024-03-05 | 中国矿业大学 | Mine safety situation analysis and prediction early warning method |
CN112906280A (en) * | 2021-03-11 | 2021-06-04 | 宁夏安普安全技术咨询有限公司 | Mathematical model establishing method for safety evaluation and risk prediction |
CN112966949B (en) * | 2021-03-15 | 2022-06-10 | 北京市市政工程研究院 | Tunnel construction risk assessment method and device and storage medium |
CN113294143B (en) * | 2021-04-16 | 2023-09-26 | 中煤能源研究院有限责任公司 | Method for evaluating investigation treatment effect of advanced ground area of limestone water damage of coal seam floor |
CN113449415B (en) * | 2021-06-07 | 2023-02-24 | 西安科技大学 | Double-layer structure-based bottom plate slippage failure depth calculation method |
CN113449414B (en) * | 2021-06-07 | 2023-03-28 | 西安科技大学 | Three-layer structure-based bottom plate slippage failure depth calculation method |
CN113516414A (en) * | 2021-08-09 | 2021-10-19 | 江苏徐矿能源股份有限公司 | Method for determining rock burst danger level |
CN113565490B (en) * | 2021-08-31 | 2023-08-08 | 中煤科工集团重庆研究院有限公司 | Water damage microseism early warning method |
CN113623004B (en) * | 2021-08-31 | 2024-02-13 | 中煤科工集团重庆研究院有限公司 | Judgment method for water damage early warning |
CN113914928B (en) * | 2021-09-06 | 2024-06-25 | 中煤科工开采研究院有限公司 | Method for dividing support areas of fully mechanized coal mining face support and accurately supporting coal mine fully mechanized coal mining face support |
CN114412567B (en) * | 2021-12-08 | 2023-03-14 | 中国矿业大学 | Early warning method for in-situ water-retention coal mining on water with bearing pressure of bottom plate limestone |
CN115114476B (en) * | 2022-07-26 | 2022-11-15 | 汶上义桥煤矿有限责任公司 | Image processing-based monitoring video storage method for coal washing transmission equipment |
CN116797020A (en) * | 2023-05-24 | 2023-09-22 | 中国矿业大学 | Coal mine roof separation layer water bursting micro-earthquake early warning method considering rock stratum structure evolution |
CN117057601B (en) * | 2023-08-02 | 2024-01-30 | 中国安全生产科学研究院 | Non-coal mine safety monitoring and early warning system based on Internet of things |
CN118191967B (en) * | 2024-05-14 | 2024-08-06 | 中煤科工西安研究院(集团)有限公司 | Intelligent early warning system and method for full-space three-dimensional monitoring of water damage risk of coal seam roof |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103049645A (en) * | 2012-11-28 | 2013-04-17 | 山东科技大学 | Coal seam floor water-inrush risk evaluation method |
CN103279809A (en) * | 2013-06-09 | 2013-09-04 | 山东科技大学 | Method for predicting and evaluating water-inrush from seam floor based on bidirectional impact of indexes |
CN104502995A (en) * | 2014-12-15 | 2015-04-08 | 中国矿业大学 | Ts-q method for evaluating floor water inrush dangerousness in coal mining of deep mine |
CN104766242A (en) * | 2015-03-25 | 2015-07-08 | 山东科技大学 | Method for evaluating dangerousness of water inrush from coal floor |
CN105069689A (en) * | 2015-08-21 | 2015-11-18 | 山东科技大学 | Coal seam floor water-inrush risk evaluation method based on combination of grey correlation and FDAHP |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SU1719635A1 (en) * | 1988-12-19 | 1992-03-15 | Н.И.Никифоров, А.М.Оллыкайнен и И.Г.Новиков | Method to protect mine workings against influx of surface water |
CN101699451A (en) * | 2009-05-08 | 2010-04-28 | 中国矿业大学(北京) | Novel practical method frangibility index method for evaluating seam floor water inrush |
CN101894189B (en) * | 2010-07-14 | 2011-04-20 | 中国矿业大学(北京) | New method for evaluating coal seam bottom water bursting |
CN102194056B (en) * | 2011-05-05 | 2012-03-21 | 中国矿业大学(北京) | BN-GIS (Bayesian Network-Geographic Information System) method for evaluating and predicting water inrush danger of coal-seam roof and floor |
CN104156560A (en) * | 2014-07-12 | 2014-11-19 | 中国矿业大学 | Multi-level coal mine water inrush prediction method based on SaE-ELM (self-adaptive evolutionary extreme learning machine) |
CN106703883B (en) * | 2016-12-29 | 2018-03-13 | 山东科技大学 | A kind of personalized method for determining Water Inrush From Working-faces danger classes |
-
2016
- 2016-12-29 CN CN201611243211.3A patent/CN106703883B/en active Active
-
2017
- 2017-10-31 WO PCT/CN2017/108619 patent/WO2018121035A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103049645A (en) * | 2012-11-28 | 2013-04-17 | 山东科技大学 | Coal seam floor water-inrush risk evaluation method |
CN103279809A (en) * | 2013-06-09 | 2013-09-04 | 山东科技大学 | Method for predicting and evaluating water-inrush from seam floor based on bidirectional impact of indexes |
CN104502995A (en) * | 2014-12-15 | 2015-04-08 | 中国矿业大学 | Ts-q method for evaluating floor water inrush dangerousness in coal mining of deep mine |
CN104766242A (en) * | 2015-03-25 | 2015-07-08 | 山东科技大学 | Method for evaluating dangerousness of water inrush from coal floor |
CN105069689A (en) * | 2015-08-21 | 2015-11-18 | 山东科技大学 | Coal seam floor water-inrush risk evaluation method based on combination of grey correlation and FDAHP |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018121035A1 (en) * | 2016-12-29 | 2018-07-05 | 山东科技大学 | Customized method for determining coal mining face floor water inrush risk level |
CN107237644A (en) * | 2017-06-30 | 2017-10-10 | 湖南科技大学 | The determination method of the three-dimensional gushing water destruction critical hydraulic pressure of tunnel inverted arch and critical thickness |
CN107165626A (en) * | 2017-06-30 | 2017-09-15 | 徐州市耐力高分子科技有限公司 | A kind of coal-face floods prevention method with cranny development country rock top plate |
CN107784437B (en) * | 2017-10-16 | 2021-09-28 | 重庆大学 | Stress concentration-based coal roadway driving face outburst danger identification method |
CN107784437A (en) * | 2017-10-16 | 2018-03-09 | 重庆大学 | A kind of Driving Face in Coal Tunnel outburst danger discrimination method based on stress concentration |
CN109948268A (en) * | 2019-01-21 | 2019-06-28 | 安迈智能(北京)矿山科技股份有限公司 | A kind of working face integrated risk automatic identifying method |
CN109948268B (en) * | 2019-01-21 | 2023-10-17 | 安迈智能(北京)矿山科技股份有限公司 | Automatic recognition method for comprehensive risk of working face |
CN109598102A (en) * | 2019-02-01 | 2019-04-09 | 内蒙古科技大学 | Prediction technique, device, equipment and the medium of coal mine rock burst degree of danger |
CN110533224A (en) * | 2019-08-06 | 2019-12-03 | 山东科技大学 | A kind of oil shale connecting exploratory bore-hole position preferred method |
CN110552741A (en) * | 2019-09-09 | 2019-12-10 | 中煤科工集团西安研究院有限公司 | coal face bottom plate water inrush comprehensive monitoring and early warning system and method |
CN111239840A (en) * | 2020-02-25 | 2020-06-05 | 华北科技学院 | Baseplate water inrush early warning method based on high-density electrical method |
CN111652490A (en) * | 2020-05-28 | 2020-09-11 | 山东科技大学 | New deep mine tectonic type water inrush prediction method based on fracture mechanics theory |
CN114087022A (en) * | 2021-10-28 | 2022-02-25 | 山东科技大学 | Coal seam floor variable parameter water inrush channel early warning system and water inrush danger judgment method |
CN114087022B (en) * | 2021-10-28 | 2023-11-28 | 山东科技大学 | Coal seam floor variable parameter water inrush channel early warning system and water inrush risk judging method |
CN118154046A (en) * | 2024-05-10 | 2024-06-07 | 太原向明智控科技有限公司 | Top plate pressure grade dividing method |
CN118154046B (en) * | 2024-05-10 | 2024-07-23 | 太原向明智控科技有限公司 | Top plate pressure grade dividing method |
Also Published As
Publication number | Publication date |
---|---|
CN106703883B (en) | 2018-03-13 |
WO2018121035A1 (en) | 2018-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106703883B (en) | A kind of personalized method for determining Water Inrush From Working-faces danger classes | |
CN106337426B (en) | It is a kind of to increase the anti-prominent precipitation method for gushing stability of artesian water stratum foundation pit | |
CN105785471A (en) | Impact danger evaluation method of mine pre-exploiting coal seam | |
CN104100245B (en) | Method for screening and evaluating artificial edge water drive fault block oil reservoir | |
CN105005712B (en) | Limestone aquifer watery evaluation methodology | |
CN105114068A (en) | Method of predicting high-water-yield area in coalbed methane area via logging information | |
CN106372297A (en) | Method for determining safe vertical distance between shield and karst cave in sand karst stratum | |
CN105550773A (en) | Method and device for predicting oil-water interface position | |
Zhao et al. | The evaluation methods for CO2 storage in coal beds, in China | |
CN104899358A (en) | Prediction method for lateral distribution of ordovician limestone karst crack water network | |
Jia et al. | Propagation of pressure drop in coalbed methane reservoir during drainage stage | |
CN108197421B (en) | Quantitative evaluation method for beneficial zone of joint development of dense gas and coal bed gas | |
CN111379562B (en) | Water-controlled coal mining method and device under composite water body | |
CN113792499B (en) | Loose confined aquifer water-rich dynamic determination method based on deposition characteristics | |
Marandi et al. | Simulation of the hydrogeologic effects of oil-shale mining on the neighbouring wetland water balance: case study in north-eastern Estonia | |
Guzy et al. | Spatio-temporal distribution of land subsidence and water drop caused by underground exploitation of mineral resources | |
Fenik et al. | Criteria for ranking realizations in the investigation of SAGD reservoir performance | |
CN116227710A (en) | Method and system for predicting degree of ecological water level variation under mining of coal seam in ecological fragile area | |
Martinez et al. | Use of numerical groundwater modelling for mine dewatering assessment | |
Liu et al. | Response characteristics and mechanisms of dynamic fluid field for well interference of coal bed methane group wells in production block | |
CN112270061A (en) | Method for evaluating drainage yield-increasing potential of water outlet well of fracture-cavity carbonate oil-gas reservoir | |
Dafny et al. | Identifying watershed-scale groundwater flow barriers: the Yoqne'am Fault in Israel | |
CN110308488A (en) | Determine the method and system of cavern filling degree | |
CN103984042B (en) | Limestone of mid Ordovician paleocrust of weathering water isolating Forecasting Methodology | |
CN109598049A (en) | Method for drilling rock fracture development degree and regional rock fracture development rule |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |