CN101661114B - Prediction method of small-scale structures in front of tunneled mine coal-shift based on ANN - Google Patents
Prediction method of small-scale structures in front of tunneled mine coal-shift based on ANN Download PDFInfo
- Publication number
- CN101661114B CN101661114B CN2009100161500A CN200910016150A CN101661114B CN 101661114 B CN101661114 B CN 101661114B CN 2009100161500 A CN2009100161500 A CN 2009100161500A CN 200910016150 A CN200910016150 A CN 200910016150A CN 101661114 B CN101661114 B CN 101661114B
- Authority
- CN
- China
- Prior art keywords
- coal
- little structure
- ann
- information
- collection
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The invention discloses a prediction method comprising the following steps: based on the analysis and the understanding of geological conditions, the growth characteristics and the law of the fracture structure and the like in a researched area, firstly analyzing and determining influencing factors closely related to the researched area as well as the distribution and the growth of a coal-bed small-scale structure; establishing an ANN forecasting and prediction model based on the looping principle; and finally developing a mine small-scale structure forecasting and prediction information system. The invention provides a set of complete theory system and working methods for the forecasting and the prediction of mine small-scale structures; the method introduces the looping theory and the ANN coupling technique into the forecasting and the prediction of the small-scale structures in front of the tunneled mine coal-shift for the first time; the artificial neural network used for the quantitative evaluation and prediction provides a comprehensive evaluation model which is close to the human thinking model and combines the qualitative evaluation and the quantitative evaluation, and therefore, the method has enough precision; and by utilizing the information of the abundant and cheap coal bed which is exposed in the coal-shift tunneling process and closely related to the distribution and the growth of the small-scale structures, the method needs low cost and well reflects the characteristics and the information of the distribution and the growth of the small-scale structures.
Description
Affiliated technical field
The present invention relates to the tectonic structure method in a kind of prediction construction of coal mine and the production run, particularly a kind ofly generally be difficult for the little structure forecast forecasting procedure in coal roads driving the place ahead that is detected at what have the disguised and scale of growth finiteness characteristics of law of development.
Background technology
Little structure is meant minor fault or some growth scales less crack and the solution crack of turn-off less than 5m.In [underground or production run, these little structures have great influence and security threat to tunnelling and working face extraction etc., they not only influence the recoverability in coal seam, increase the tunnelling amount, but also destroyed the integrality and the stability of top, coal seam, base plate, form comparatively hidden gushing (dashing forward) aquaporin.These passages gently then make construction or mine main water yield obviously increase, and have increased the effluent cost of mine, have improved cost of ton coal; Heavy then cause part tunnel, part workplace or whole mine gushing water to be flooded, bring about great losses for the country and people's lives and properties.Prediction to tunnelling and little structure space, back production the place ahead, coal seam law of development has important theory directive significance and practical value.
Because the finiteness of the disguise of the little structure development rule of mine and the scale of growth generally is difficult for being detected, the prediction difficulty is very big.When each institution of higher learning of coal system compiled in collaboration with " mine shaft geology and mine hydrogeology " teaching material in 1975, the term of " mine structure forecast " has just formally been proposed, and systematically sum up by China then in progress obtained aspect the structure forecast, pointed out thinking and method that root pick geometric construction, geomechanics and three aspects of mathematical statistics are predicted.The thinking and the method for mine structure forecast once systematically introduced in the whole nation that Wang Gui beam in 1976 is held in Dalian first geomechanics experience exchangement conference, caused the extensive attention of academia and production unit.People sum up the whole bag of tricks and predict tectonic structure in long term production, have accumulated the experience of some tectonic structure predictions gradually.Structure forecast forecasting procedure commonly used at present mainly comprises: geophysical prospection; The geologic rule analytic approach; Mathematical methods; Geometrograph etc.
Though these classic methods have played positive effect to a prediction difficult problem that solves mine geological structure, but since the too high and decipher problem that separate of acquisition cost is difficult to solve more or precision is limited or the structure of forecast too macroscopic view can't solve the prediction etc. of little structure, so classic method is failed the little structure of prediction mine, fail to solve the little structure forecast forecast difficult problem of digging laneway in the coal mine excavation process or coal face the place ahead small spatial scale especially.
Summary of the invention
One of the object of the invention is, satisfies the demand of coal industry production and safety, and a complete theoretical system of cover and a method of work of the little structure forecast forecast of a kind of mine is provided.
Further aim of the present invention is, satisfies the demand of coal industry production and safety, and a kind of prediction methods that can tunnel the little structure in the place ahead at the coal roads that generally are difficult for being detected with law of development disguise and the scale of growth finiteness characteristics is provided.
Further aim of the present invention also is, satisfies the demand of coal industry production and safety, provides a kind of expense cheap but have the little building method of prediction mine of enough accuracy.
To achieve these goals, the present invention is according to the ultimate principle and artificial neural network (the ArtificialNeural Network of " multiple ring set theory ", ANN) quantitative Analysis of the technology method that combines has proposed the theoretical system of the little structure forecast forecast in coal road driving the place ahead and a complete cover method of work.Analyze on the understanding basis in study area geologic condition and rift structure development characteristics and rule etc., the little structure forecast forecasting procedure in coal road driving the place ahead based on ANN, adopted following technical scheme:
1. analyze and determine study area and the closely-related influence factor of coal seam little structure distribution growth;
2. make up ANN prediction model based on the ring set principle;
3. research and develop the little structure forecast prediction information system of mine.
Owing to adopted above-mentioned technical scheme, the beneficial effect that the present invention has is:
1. use " multiple ring set theory ",, proposed a complete theoretical system of cover and a method of work of the little structure forecast forecast of mine, realized first purpose of the present invention based on nonlinear artificial neural network (ANN) technology.
2. first ring set theory and ANN coupling technique are incorporated in the little structure forecast forecast in mine coal roadway driving the place ahead, have carried out and utilized the applied research that ring set is theoretical and the neural network coupling technique forecasts the little structure forecast of mine.Artificial neural network is used for the comprehensive evaluation model that qualitative and quantitative that quantitative evaluation prediction is expected to approach human thinking's pattern combines, and has enough accuracy, has realized second purpose of the present invention.
3. the present invention utilizes a large amount of and cheap the distributing with little structure that is exposed in the coal road tunneling process to grow closely-related coal seam information, expense is cheap but reflected study area little structure distribution development characteristics and information admirably, has realized the 3rd purpose of the present invention.
Description of drawings
Accompanying drawing 1: workflow diagram of the present invention.
Accompanying drawing 2: the ring set principle among the present invention is determined little constitutive logic inference graph.
Specific embodiment
Below in conjunction with accompanying drawing the present invention is described in detail.
The present invention is based on the little structure forecast forecasting technique in coal road driving the place ahead of ANN method, concrete technical application scheme may further comprise the steps:
1. analyze and determine study area and the closely-related influence factor of coal seam little structure distribution growth
Described study area is grown closely related factor analysis with the little structure distribution in coal seam and is comprised the study area coal seam information analysis relevant with little structure and " ring set principle " reasoning from logic in little structure forecast.
Described study area and the distribution of little structure are grown closely related factor analysis and are comprised:
(1) variation of crack occurrence in the coal seam;
(2) variation of seam inclination;
(3) variation of thickness of coal seam;
(4) variation of coal-bed gas aggregate amount;
(5) variation of coal seam water cut;
(6) coal seam variation of temperature;
(7) variation of coal seam degree of crushing.
Described " ring set principle " reasoning from logic in little structure forecast is meant, in the coal road tunneling process, if it is the A collection that tectonic information is looked in the coal seam water yield variation of our current entry, it is the B collection that tectonic information is looked in the seam inclination variation that records, it is the C collection that Coal Seam Thickness Change is looked for tectonic information, it is the D collection that tectonic information is looked in the gas variation that the gas emission value of time recording calculates, it is the E collection that tectonic information is looked in the variation of coal seam water cut, it is the F collection that the coal seam variation of temperature is looked for tectonic information, and it is the G collection that tectonic information is looked in the variation of coal seam degree of crushing.By the reaction of A collection information acquisition structural anormaly, think that then may there be certain little structure in the coal road driving, from the qualitative information that can not have little structure before the back production that reflected of macroscopic view; The existence of structure also can be embodied in the variation of seam inclination, occurs in A collection structural anormaly information area during as if B collection information of same, has then strengthened the possibility that has little structure in A collection and the B collection overlap-add region; C, D, E, F, G collection information are in like manner.Its reasoning from logic circuit as shown in Figure 2.
2. make up ANN prediction model based on the ring set principle;
Described structure is based on the ANN prediction model of ring set principle, comprise analysis of Influential Factors, each influence factor that collection is relevant with the little structure development in coal seam sample set, set up artificial nerve network model, learning training sample and interpretation of result and check forecast.
Described analysis of Influential Factors is meant, according to each information set in the ring set principle, considers concrete mine actual conditions again, chooses seam inclination, thickness of coal seam, coal seam water yield, coal-bed gas outburst amount etc. as the artificial neural network input layer factor.
The sample set of each influence factor that described collection is relevant with the little structure development in coal seam is meant, coal road geologic sketch map according to record formation in the coal road tunneling process, be collected in the delta data and the curve of destruction band, influence band and normal each factor of being with of different little structures, form the sample set of ANN learning training.
The described artificial nerve network model of setting up is meant, utilizes above-mentioned factor of influence to set up the input layer of neural network, by the neural network learning training, sets up artificial nerve network model.
Described artificial nerve network model adopts the effective especially BP artificial neural network of complex relationship variable analysis.
3. research and develop the little structure forecast prediction information system of mine.
The research and development of described little structure forecast prediction information system are meant, at the ANN model of above-mentioned little structure, utilize the little structure forecast prediction information system of C/C++ language development.
Claims (6)
1. based on the little structure forecasting procedure in mine coal roadway driving the place ahead of ANN, on study area geologic condition and rift structure development characteristics and law-analysing understanding basis, it is characterized in that: technical scheme may further comprise the steps:
(1) analyzes the little structure distribution in definite study area and coal seam and grow closely-related influence factor;
Described study area is grown closely-related analysis of Influential Factors with the little structure distribution in coal seam and is comprised the study area coal seam information analysis relevant with little structure and " ring set principle " reasoning from logic in little structure forecast;
The coal seam information analysis that described study area is relevant with little structure comprises:
1. the variation of crack occurrence in the coal seam;
2. the variation of seam inclination;
3. the variation of thickness of coal seam;
4. the variation of coal-bed gas aggregate amount;
5. the variation of coal seam water cut;
6. coal seam variation of temperature;
7. the variation of coal seam degree of crushing;
Described " ring set principle " reasoning from logic in little structure forecast is meant, in the coal road tunneling process, if it is the A collection that tectonic information is looked in the coal seam water yield variation of our current entry, it is the B collection that tectonic information is looked in the seam inclination variation that records, it is the C collection that Coal Seam Thickness Change is looked for tectonic information, and it is the D collection that tectonic information is looked in the gas variation that the gas emission value of time recording calculates.By the reaction of A collection information acquisition structural anormaly, think that then may there be certain little structure in the coal road driving, from the qualitative information that can not have little structure before the back production that reflected of macroscopic view; The existence of structure also can be embodied in the variation of seam inclination, occurs in A collection structural anormaly information area during as if B collection information of same, has then strengthened the possibility that has little structure in A collection and the B collection overlap-add region; C, D collection information are in like manner;
(2) structure is based on the ANN prediction model of ring set principle;
Described structure is based on the ANN prediction model of ring set principle, comprise analysis of Influential Factors, each influence factor that collection is relevant with the little structure development in coal seam sample set, set up artificial nerve network model, learning training sample and interpretation of result and check forecast;
(3) the little structure forecast prediction information system of research and development mine.
2. the little structure forecasting procedure in mine coal roadway driving the place ahead based on ANN according to claim 1, it is characterized in that: described analysis of Influential Factors is meant, according to each information set in the ring set principle, consider concrete mine actual conditions again, choose seam inclination, thickness of coal seam, coal seam water yield, coal-bed gas outburst amount as the artificial neural network input layer factor.
3. according to the described little structure forecasting procedure in mine coal roadway driving the place ahead of claim 1 based on ANN, it is characterized in that: the sample set of each influence factor that described collection is relevant with the little structure development in coal seam is meant, coal road geologic sketch map according to record formation in the coal road tunneling process, be collected in the delta data and the curve of destruction band, influence band and normal each factor of being with of different little structures, form the sample set of ANN learning training.
4. the little structure forecasting procedure in mine coal roadway driving the place ahead based on ANN according to claim 1, it is characterized in that: the described artificial nerve network model of setting up is meant, utilize above-mentioned factor of influence to set up the input layer of neural network, by the neural network learning training, set up artificial nerve network model.
5. the little structure forecasting procedure in mine coal roadway driving the place ahead based on ANN according to claim 4 is characterized in that: described artificial nerve network model adopts the effective especially BP artificial neural network of complex relationship variable analysis.
6. the little structure forecasting procedure in mine coal roadway driving the place ahead based on ANN according to claim 1, it is characterized in that: the research and development of described little structure forecast prediction information system are meant, at the ANN model of above-mentioned little structure, utilize the little structure forecast prediction information system of C/C++ language development.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100161500A CN101661114B (en) | 2009-06-12 | 2009-06-12 | Prediction method of small-scale structures in front of tunneled mine coal-shift based on ANN |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100161500A CN101661114B (en) | 2009-06-12 | 2009-06-12 | Prediction method of small-scale structures in front of tunneled mine coal-shift based on ANN |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101661114A CN101661114A (en) | 2010-03-03 |
| CN101661114B true CN101661114B (en) | 2010-10-13 |
Family
ID=41789247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009100161500A Expired - Fee Related CN101661114B (en) | 2009-06-12 | 2009-06-12 | Prediction method of small-scale structures in front of tunneled mine coal-shift based on ANN |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101661114B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810524A (en) * | 2014-03-08 | 2014-05-21 | 辽宁工程技术大学 | Method for predicting ground subsidence in underground metro construction process |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103105630B (en) * | 2013-01-08 | 2014-01-15 | 中国矿业大学(北京) | Ration determination method of mine hydrogeology inside and outside border hydraulic power nature artificial neural network (ANN) technology |
| CN104537566B (en) * | 2014-12-22 | 2018-08-31 | 山西煤炭职业技术学院 | A kind of prediction technique of hexagon coal road surface displacement amount |
| CN107169616B (en) * | 2017-07-21 | 2020-11-13 | 西安科技大学 | Relative entropy prediction method for relative complexity of mine non-mining area structure |
| CN110286207A (en) * | 2019-06-28 | 2019-09-27 | 山西晋城无烟煤矿业集团有限责任公司 | A kind of cacoplastic judgment method of coal body |
| CN110688690B (en) * | 2019-08-02 | 2023-06-06 | 天地科技股份有限公司 | Roadway support parameter determination method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5692107A (en) * | 1994-03-15 | 1997-11-25 | Lockheed Missiles & Space Company, Inc. | Method for generating predictive models in a computer system |
| JP2002259940A (en) * | 2001-03-06 | 2002-09-13 | Kddi Corp | Parallel neural network processing system equipped with output condition determination function |
| CN1975462A (en) * | 2006-09-05 | 2007-06-06 | 孟召平 | Coal seam thickness analyzing method based on earthquake attribute |
-
2009
- 2009-06-12 CN CN2009100161500A patent/CN101661114B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5692107A (en) * | 1994-03-15 | 1997-11-25 | Lockheed Missiles & Space Company, Inc. | Method for generating predictive models in a computer system |
| JP2002259940A (en) * | 2001-03-06 | 2002-09-13 | Kddi Corp | Parallel neural network processing system equipped with output condition determination function |
| CN1975462A (en) * | 2006-09-05 | 2007-06-06 | 孟召平 | Coal seam thickness analyzing method based on earthquake attribute |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810524A (en) * | 2014-03-08 | 2014-05-21 | 辽宁工程技术大学 | Method for predicting ground subsidence in underground metro construction process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101661114A (en) | 2010-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Slope stability prediction using ensemble learning techniques: A case study in Yunyang County, Chongqing, China | |
| CN108119142B (en) | - three-two subregion water-protection coal-mining methods of band of five figures | |
| Li et al. | Evolution characteristics and displacement forecasting model of landslides with stair-step sliding surface along the Xiangxi River, three Gorges Reservoir region, China | |
| Schultz et al. | Newly emerging cases of hydraulic fracturing induced seismicity in the Duvernay East Shale Basin | |
| CN101661114B (en) | Prediction method of small-scale structures in front of tunneled mine coal-shift based on ANN | |
| Weaver | Geological factors significant in the assessment of rippability | |
| Bai et al. | Negative externalities of high-intensity mining and disaster prevention technology in China | |
| CN102998718A (en) | Coal-mine gas geology four-dimensional analysis method | |
| Wu et al. | Assessment of groundwater inrush from underlying aquifers in Tunbai coal mine, Shanxi province, China | |
| Li et al. | Innovation for sustainable mining: Integrated planning of underground coal mining and mine reclamation | |
| Howladar | Environmental impacts of subsidence around the Barapukuria Coal Mining area in Bangladesh | |
| Dong et al. | Quantitative evaluation and case study of risk degree for underground goafs with multiple indexes considering uncertain factors in mines | |
| CN107526098A (en) | A kind of construction method for carrying out advance geologic prediction | |
| CN102852524B (en) | Method for utilizing hydraulic support to improve bauxite recovery rate | |
| CN115758671B (en) | Surrounding rock roadway reinforcement anchor grouting support full life cycle management method, system and application | |
| Shi et al. | Failure mechanism analysis for tunnel construction crossing the water-rich dense fracture zones: A case study | |
| Yin et al. | Point and interval estimation of rock mass boreability for tunnel boring machine using an improved attribute-weighted deep belief network | |
| Zeng | Research on risk evaluation methods of groundwater bursting from aquifers underlying coal seams and applications to coalfields of North China | |
| Guo et al. | Overburden response to longwall mining | |
| Tang et al. | Research development and critical problems existing in strata movement and its control | |
| Wang et al. | Application of displacement direction angle theory on excavation methods conversion opportunity of Zi-Zhi Tunnel | |
| Cao et al. | Construction and Application of “Active Prediction-Passive Warning” Joint Impact Ground Pressure Resilience Prevention System: Take the Kuan Gou Coal Mine as an Example | |
| Githenya et al. | Integration of remote sensing and geophysical investigation in geological mapping of the Yatta/Kwa Vonza phonolite lavas | |
| Anis et al. | Utilizing coal remaining resources and post-mining land use planning based on GIS-based optimization method: study case at PT Adaro coal mine in South Kalimantan | |
| Cao et al. | Study on the Safety Thickness of Rock Strata for Outburst Prevention in Deep Tunnel Based on Numerical Modeling and Backpropagation Neural Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20101013 Termination date: 20110612 |