CN111102006B - Dynamic early warning intelligent decision method for outburst mine extraction and mining deployment imbalance - Google Patents
Dynamic early warning intelligent decision method for outburst mine extraction and mining deployment imbalance Download PDFInfo
- Publication number
- CN111102006B CN111102006B CN201910963488.0A CN201910963488A CN111102006B CN 111102006 B CN111102006 B CN 111102006B CN 201910963488 A CN201910963488 A CN 201910963488A CN 111102006 B CN111102006 B CN 111102006B
- Authority
- CN
- China
- Prior art keywords
- extraction
- index
- tunneling
- deployment
- mining
- 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.)
- Active
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 143
- 238000005065 mining Methods 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000005641 tunneling Effects 0.000 claims abstract description 93
- 238000011156 evaluation Methods 0.000 claims abstract description 51
- 238000012544 monitoring process Methods 0.000 claims abstract description 43
- 238000009412 basement excavation Methods 0.000 claims abstract description 22
- 238000011161 development Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 239000003245 coal Substances 0.000 claims description 67
- 239000010410 layer Substances 0.000 claims description 50
- 239000011241 protective layer Substances 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 22
- 238000002360 preparation method Methods 0.000 claims description 17
- 238000011084 recovery Methods 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010206 sensitivity analysis Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000008030 elimination Effects 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 5
- 238000005553 drilling Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 125000002015 acyclic group Chemical group 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
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
- E21F17/18—Special adaptations of signalling or alarm devices
-
- 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
-
- 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
- E21F7/00—Methods or devices for drawing- off gases with or without subsequent use of the gas for any purpose
-
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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)
- Mining & Mineral Resources (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Marine Sciences & Fisheries (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a dynamic early warning intelligent decision method for outburst mine extraction and mining deployment disorder. The method comprises the steps of constructing a outburst mine extraction mining deployment rationality evaluation index system, constructing a correlation model between outburst mine safety monitoring big data and extraction mining deployment rationality evaluation identification indexes, constructing a dynamic early warning intelligent decision model for outburst mine extraction mining deployment based on a Bayesian network theory and the like. The method considers the tunneling advance index and the regional measure engineering effectiveness index and carries out dynamic calculation, thereby providing comprehensive, scientific and reliable theoretical guidance for the arrangement of the extraction and mining of the outburst mine. The method has the advantages that timely early warning is carried out on problems existing in the alternative deployment, reasonable and initiative excavation deployment is realized, the continuous development of the mine is guaranteed, the mine is guaranteed to safely and efficiently complete a production plan, and the method has important practical significance.
Description
Technical Field
The invention relates to the field of coal mine gas prevention and control, in particular to a dynamic early warning intelligent decision method for outburst mine excavation mining deployment maladjustment.
Background
Reasonable extraction mining deployment means that extraction mining can be connected in a balanced and continuous manner in time and space in the production process of a coal mine. Unreasonable extraction and mining deployment has long been one of the key issues governing safe and efficient operation of mines. Particularly, for outburst mines, along with the increase of the mining depth of the mines, the difficulty in controlling mine gas is increased, and the problem of unbalance of extraction, excavation and mining is more serious. At present, when the coal mine is extracted and deployed, extraction, mining and deployment are carried out by mine deployment personnel according to the stipulations about the division range of the exploitation coal quantity, the preparation coal quantity and the stope coal quantity of mines and open mines published by the department of coal industry in 1961, or on the premise of meeting related regulations and according to experience summary. The deployment mode is static calculation and evaluation, defines ambiguity, and cannot effectively warn problems in follow-up work and give improvement directions of effective measures.
Therefore, an intelligent dynamic early warning decision method for mining and deployment imbalance of the outburst mine is urgently needed, so that reasonable evaluation indexes of mining and deployment imbalance of the mine are redefined from a theoretical height, dynamic calculation is performed, and problems in alternative deployment are timely early warned.
Disclosure of Invention
The invention aims to provide a dynamic early warning intelligent decision method for mining and deployment maladjustment of an outburst mine, which aims to solve the problems in the prior art.
The technical scheme adopted for achieving the purpose of the invention is that the dynamic early warning intelligent decision method for the outburst mine extraction and mining deployment maladjustment comprises the following steps:
1) and constructing an outburst mine extraction mining deployment rationality evaluation index system. And (4) providing an evaluation and identification index of the extraction mining deployment rationality of the outburst mine, and quantifying the evaluation and identification index.
2) And constructing a correlation model between the extraction related safety monitoring big data of the outburst mine and the extraction related identification index variable. And constructing a correlation model between the relevant safety monitoring big data of the outburst mine excavation and the relevant excavation judging index variables. And constructing a correlation model between the safety monitoring big data related to the extraction of the outburst mine and the judgment index variable related to the extraction. The extraction related safety monitoring big data comprises extraction gas concentration, extraction gas flow and extraction drilling footage. And the excavation related safety monitoring big data comprise excavation roadway air exhaust gas concentration and excavation footage. And the large data of safety monitoring related to the recovery comprise the concentration of the wind-exhaust gas of the recovery working face and the coal yield.
3) And constructing a Bayesian network model for the intelligent decision of extraction, excavation and deployment of the outburst mine based on the evaluation index and the judgment index.
4) And when the outburst mine is unreasonably extracted and mined, early warning is carried out and an intelligent decision is made.
Further, the step 1) specifically comprises the following steps:
1.1) constructing a reasonable evaluation index system for extraction mining deployment of the outburst mine. The evaluation index system comprises a tunneling advance index and 2 first-level indexes of regional measure engineering effectiveness indexes. The tunneling advance index comprises 6 secondary indexes of development tunneling, preparation tunneling, regional measure engineering tunneling, protective layer tunneling and gas control roadway tunneling. The regional measure engineering effectiveness indexes comprise 5 secondary indexes of protective layer roadway strip effectiveness indexes, protective layer mining effectiveness indexes, protected layer roadway strip effectiveness indexes, protected layer mining effectiveness indexes and protective layer gas control effectiveness.
1.2) combining the quantitative indexes, and providing an identification index corresponding to the extraction mining deployment rationality evaluation index of the outburst mine. Wherein the quantitative index comprises the coal amount and the outburst elimination effective length. The judgment index corresponding to the development heading is the development coal amount. The judgment index corresponding to the preparation of tunneling is the preparation coal amount. And the judgment index corresponding to the regional measure engineering tunneling is the measure coal quantity. The judgment index corresponding to the protective layer tunneling is the protective layer tunneling coal amount. The judgment index corresponding to the protected layer tunneling is the amount of coal tunneled by the protected layer. The judgment index corresponding to the gas control roadway tunneling is the gas control coal quantity. The judgment index corresponding to the effective index of the protective layer roadway strip is the effective length of the protective layer heading face. The judgment index corresponding to the protective layer recovery effectiveness index is the effective length of the protective layer recovery surface. And the judgment index corresponding to the effectiveness index of the roadway strip of the protected layer is the effective tunneling length of the protected layer. And the judgment index corresponding to the recovery effectiveness index of the protected layer is the effective coal amount of the protected layer. The judgment index corresponding to the gas treatment effectiveness of the protective layer is the effective coal amount of the gas treatment.
1.3) combining the definition of the extracted mining deployment rationality evaluation index of the outburst mine, and providing a calculation rule and an evaluation criterion of the extracted mining deployment rationality evaluation index of the outburst mine.
Further, the step 2) specifically comprises the following steps:
and 2.1) acquiring safety monitoring big data related to extraction, tunneling and stoping, and preprocessing the safety monitoring big data.
And 2.2) randomly grouping the preprocessed safety monitoring big data samples related to extraction, tunneling and recovery into a training set and a testing set respectively. And training and testing the BP neural network, and establishing a correlation model between the outburst mine safety monitoring big data and the extraction mining deployment rationality evaluation identification index based on the deep belief network.
And 2.3) bringing real-time and dynamic extraction, tunneling and extraction big data into the established deep belief network to obtain real-time and dynamic extraction, mining and deployment rationality evaluation and identification indexes.
Further, in step 2.1), the preprocessing includes encoding and normalizing the raw data.
Further, the step 3) specifically comprises the following steps:
3.1) establishing a Bayesian network model for outburst mine extraction mining deployment intelligent decision by using a form of branching connection in Bayesian network theory.
And 3.2) carrying out forward reasoning on the Bayesian network model to obtain the probability P (A is Yes) of reasonable deployment of the outburst mine extraction mining. And dividing intervals according to the obtained probability P (A ═ Yes) to obtain a judgment criterion for evaluating the extraction mining deployment rationality of the outburst mine. Sensitivity analysis is carried out through Netica software, and the influence degree of different identification indexes on the extraction mining deployment rationality is obtained.
3.3) when P (A ═ Yes) ═ 0, judging the key identification index which causes unreasonable extraction and mining through the change trend of the index probability. And (4) evaluating the risk probability of the misextraction of the outburst mine caused by unreasonable reasons.
The technical effects of the invention are undoubted:
A. the advance tunneling index and the effective index of regional measure engineering are considered, and dynamic calculation is carried out, so that comprehensive, scientific and reliable theoretical guidance is provided for the arrangement of extraction and mining of the outburst mine;
B. the method has the advantages that timely early warning is carried out on problems existing in alternative deployment, reasonable initiative of excavation and deployment is realized, continuous development of a mine is guaranteed, the mine is guaranteed to safely and efficiently complete a production plan, and the method has important practical significance.
Drawings
FIG. 1 is a process flow diagram;
FIG. 2 is a drawing, excavating and deploying rationality evaluation index system framework;
FIG. 3 is a schematic diagram of a restricted Boltzmann machine;
FIG. 4 is a schematic of a deep belief network architecture;
FIG. 5 is a process of deep belief network training and testing;
FIG. 6 is a Bayesian network model framework.
Detailed Description
The present invention is further illustrated by the following examples, but it should not be construed that the scope of the above-described subject matter is limited to the following examples. Various alterations and modifications can be made without departing from the technical idea of the invention, and all changes and modifications made by the ordinary technical knowledge and the conventional means in the field are intended to be included in the scope of the invention.
Example 1:
referring to fig. 1, the embodiment discloses an intelligent decision method for dynamic early warning of mining and deployment imbalance of an outburst mine, which comprises the following steps:
1) and constructing an outburst mine extraction mining deployment rationality evaluation index system. And (4) providing an evaluation and identification index of the extraction mining deployment rationality of the outburst mine, and quantifying the evaluation and identification index.
1.1) constructing a reasonable evaluation index system for extraction mining deployment of the outburst mine. The evaluation index system comprises a tunneling advance index and 2 first-level indexes of regional measure engineering effectiveness indexes. The tunneling advance index comprises 6 secondary indexes of development tunneling, preparation tunneling, regional measure engineering tunneling, protective layer tunneling and gas control roadway tunneling. The regional measure engineering effectiveness indexes comprise 5 secondary indexes of protective layer roadway strip effectiveness indexes, protective layer mining effectiveness indexes, protected layer roadway strip effectiveness indexes, protected layer mining effectiveness indexes and protective layer gas control effectiveness.
1.2) combining the quantitative indexes, and providing an identification index corresponding to the extraction mining deployment rationality evaluation index of the outburst mine. Wherein the quantitative index comprises the coal amount and the outburst elimination effective length. The judgment index corresponding to the development heading is the development coal amount. The judgment index corresponding to the preparation of tunneling is the preparation coal amount. And the judgment index corresponding to the regional measure engineering tunneling is the measure coal quantity. The judgment index corresponding to the protective layer tunneling is the protective layer tunneling coal amount. The judgment index corresponding to the protected layer tunneling is the amount of coal tunneled by the protected layer. The judgment index corresponding to the gas control roadway tunneling is the gas control coal quantity. The judgment index corresponding to the effective index of the protective layer roadway strip is the effective length of the protective layer heading face. The judgment index corresponding to the protective layer recovery effectiveness index is the effective length of the protective layer recovery surface. And the judgment index corresponding to the effectiveness index of the roadway strip of the protected layer is the effective tunneling length of the protected layer. And the judgment index corresponding to the recovery effectiveness index of the protected layer is the effective coal amount of the protected layer. The judgment index corresponding to the gas treatment effectiveness of the protective layer is the effective coal amount of the gas treatment.
1.3) combining the definition of the extracted mining deployment rationality evaluation index of the outburst mine, and providing a calculation rule and an evaluation criterion of the extracted mining deployment rationality evaluation index of the outburst mine.
2) And constructing a correlation model between the extraction related safety monitoring big data of the outburst mine and the extraction related identification index variable. And constructing a correlation model between the relevant safety monitoring big data of the outburst mine excavation and the relevant excavation judging index variables. And constructing a correlation model between the safety monitoring big data related to the extraction of the outburst mine and the judgment index variable related to the extraction.
And 2.1) acquiring safety monitoring big data related to extraction, tunneling and stoping, and preprocessing the safety monitoring big data. The extraction related safety monitoring big data comprises extraction gas concentration, extraction gas flow and extraction drilling footage. And the tunneling related safety monitoring big data comprises the concentration of air and gas exhausted from the tunneling roadway and the tunneling footage. And the safety monitoring big data related to the stoping comprises the concentration of the wind-exhaust gas of the stoping working face and the coal yield.
And 2.2) randomly grouping the preprocessed safety monitoring big data samples related to extraction, tunneling and recovery into a training set and a testing set respectively. And training and testing the BP neural network, and establishing a correlation model between the outburst mine safety monitoring big data and the extraction mining deployment rationality evaluation identification index based on the deep belief network.
And 2.3) bringing real-time and dynamic extraction, tunneling and extraction big data into the established deep belief network to obtain real-time and dynamic extraction, mining and deployment rationality evaluation and identification indexes.
3) And constructing a Bayesian network model for the intelligent decision of extraction, excavation and deployment of the outburst mine based on the evaluation index and the judgment index.
3.1) establishing a Bayesian network model for outburst mine extraction mining deployment intelligent decision by using a form of branching connection in Bayesian network theory.
And 3.2) carrying out forward reasoning on the Bayesian network model to obtain the probability P (A is Yes) of reasonable deployment of the outburst mine extraction mining. And dividing intervals according to the obtained probability P (A ═ Yes) to obtain a judgment criterion for evaluating the extraction mining deployment rationality of the outburst mine. Sensitivity analysis is carried out through Netica software, and the influence degree of different identification indexes on the extraction mining deployment rationality is obtained.
3.3) when P (A ═ Yes) ═ 0, judging the key identification index which causes unreasonable extraction and mining through the change trend of the index probability. And (4) evaluating the risk probability of the misextraction of the outburst mine caused by unreasonable reasons.
4) And when the outburst mine is unreasonably extracted and mined, early warning is carried out and an intelligent decision is made.
Example 2:
the embodiment discloses a dynamic early warning intelligent decision method for outburst mine extraction and mining deployment maladjustment, which comprises the following steps:
1) constructing an outburst mine extraction and mining deployment rationality evaluation index system by exploring a time-space coordination relationship among extraction, tunneling and stoping of the outburst mine by adopting a field investigation method; providing an outburst mine extraction mining deployment rationality evaluation identification index based on analysis of a corresponding relation between the effective outburst elimination length and the coal quantity and the outburst mine extraction mining deployment rationality evaluation index; and quantifying the extraction mining deployment rationality evaluation identification index of the outburst mine through the calculation rule of the extraction mining deployment rationality evaluation identification index of the outburst mine and the clarification of the identification criterion.
2) Respectively constructing a correlation model between the relevant safety monitoring big data of the extraction, the tunneling and the stoping of the outburst mine and relevant judgment index variables of the extraction, the tunneling and the stoping by exploring the acquisition and processing method of the relevant safety monitoring big data of the extraction, the tunneling and the stoping of the outburst mine; through the construction of the correlation model, the change of the extraction mining deployment rationality evaluation identification index of the outburst mine is reflected by the monitoring big data, so that the real-time dynamic monitoring of the extraction mining deployment rationality evaluation identification index of the outburst mine is realized.
3) Constructing a directed acyclic outburst mine extraction mining deployment rationality evaluation hierarchical Bayesian network structure based on the proposed outburst mine extraction mining deployment evaluation index and identification index, obtaining the prior probability of a Bayesian network root node and the conditional probability of a subnode, and proposing an outburst mine extraction mining deployment rationality rating standard; and evaluating the sensitivity analysis of the Bayesian network target node to the node state through the extraction mining deployment rationality of the outburst mine, diagnosing the unreasonable reasons of extraction mining deployment of the outburst mine, and evaluating the risk probability of extraction mining disorder of the outburst mine under the unreasonable reason situation.
4) And when the outburst mine is unreasonably extracted and mined, early warning is carried out and an intelligent decision is made. The method realizes the orderly coordination of the extraction and excavation of the outburst mine and effectively controls the final aim of gas accidents of the outburst mine.
Example 3:
the embodiment discloses a dynamic early warning intelligent decision method for outburst mine extraction and mining deployment maladjustment, which comprises the following steps:
1) and constructing an outburst mine extraction mining deployment rationality evaluation index system.
1.1) adopting a field investigation method, taking extraction, tunneling and stoping as main lines, collecting data of extraction and mining deployment schemes, mine column charts, mine production system charts, gas extraction layout charts, tunneling outburst danger check tables and the like of the first five years and the third years of a typical outburst mine such as a Chongqing Songguan coal mine, a Huainan new-collected second mine, a Shanxi end coal mine and the like, summarizing and refining deployment conditions of extraction, tunneling and stoping of the outburst mine under different geological and coal seam occurrence conditions, and exploring a time-space coordination relationship among extraction, tunneling and stoping of the outburst mine.
Referring to fig. 2, the embodiment proposes extraction, excavation and deployment rationality evaluation indexes taking an advance tunneling index and a regional measure engineering validity index as a first level and taking development, excavation preparation, gas control roadway excavation, protective layer roadway strip validity index, protective layer mining back validity index, protective layer gas control validity index and the like as a second level. The indexes of development tunneling, preparation tunneling, gas control roadway tunneling and the like are used for controlling the tunneling advanced index, and the indexes of protective layer roadway strip effectiveness index, protective layer mining effectiveness index, protective layer gas control effectiveness and the like are used for controlling the effectiveness index of regional measure engineering.
1.2) according to the definition of the extraction mining deployment rationality evaluation index of the outburst mine, combining quantitative indexes such as coal quantity and outburst elimination effective length and the like, providing an identification index corresponding to the extraction mining deployment rationality evaluation index of the outburst mine, and defining the definition of the identification index. Referring to fig. 2, the judgment index corresponding to the preparation for tunneling is the preparation coal amount. And the judgment index corresponding to the regional measure engineering tunneling is the measure coal quantity. The judgment index corresponding to the protective layer tunneling is the protective layer tunneling coal amount. The judgment index corresponding to the protected layer tunneling is the amount of coal tunneled by the protected layer. The judgment index corresponding to the gas control roadway tunneling is the gas control coal quantity. And the judgment index corresponding to the effective index of the protective layer roadway strip is the effective length of the protective layer tunneling surface. The judgment index corresponding to the protective layer stoping effectiveness index is the effective length of the protective layer stoping surface. And the judgment index corresponding to the effectiveness index of the roadway strip of the protected layer is the effective tunneling length of the protected layer. And the judgment index corresponding to the recovery effectiveness index of the protected layer is the effective coal amount of the protected layer. The judgment index corresponding to the protective layer gas treatment effectiveness is the gas treatment effective coal quantity.
1.3) combining the definition of the extraction mining deployment rationality judgment index of the outburst mine, and providing a calculation rule and a judgment criterion of the extraction mining deployment rationality evaluation judgment index of the outburst mine. For example, the calculation rule for exploiting the coal amount may be described as: before the development roadway enters the opening positions of the upper and lower mountains of the mining area, the development coal amount of the mining area is zero. After entering the opening positions of the upper and lower mountains of the mining area, the total mining area development project amount of the mining area refers to the development roadway project amount from the opening position of the upper and lower mountains of the mining area to the opening position of the upper and lower mountains of the next mining area. The judgment criterion can be described as: the amount of developed coal should be greater than the time for completing development, preparation and recovery projects of a mining area, the annual yield of the mine and the surplus coefficient.
2) Constructing a correlation model between the outburst mine safety monitoring big data and the extraction mining deployment rationality evaluation identification indexes;
this exampleThe real-time dynamic capture and analysis of the coal mine extraction mining deployment identification index are realized through the real-time dynamic capture and analysis of the coal mine safety monitoring big data, and the adopted big data analysis method is a deep learning algorithm, namely a deep belief network. The deep learning simulates human brain from the perspective of bionics for analysis, is essentially a neural network containing a plurality of hidden layers, but is different from a traditional shallow model, the essence of the deep learning is to overcome the difficulty of the deep model in training by initializing layer by layer, and to learn useful information in data step by step through a plurality of hidden layers, so that the accuracy of prediction or classification is improved. The deep belief network is a generation model based on a deep learning technology, and the forming elements of the deep belief network are restricted Boltzmann machines, and each restricted Boltzmann machine can be independently used as a classifier. The restricted Boltzmann machine only has two layers of neurons, one layer is a visible layer and consists of dominant neurons, and the restricted Boltzmann machine is used for inputting training data; and the other layer is a hidden layer and consists of hidden neurons and is used for extracting the characteristics of the training data. The structure of the constrained boltzmann machine is shown in fig. 3, in which the visible layer has m nodes, the hidden layer has n nodes, w1 RIs the connection weight.
And a plurality of limited Boltzmann machines are sequentially stacked to form a deep belief network, and the output of the previous limited Boltzmann machine is used as the training input of the next limited Boltzmann machine. As a generation model, the learning process of the deep belief network can be divided into two stages, namely, all limited Boltzmann machines are subjected to unsupervised pre-training layer by layer, and then are subjected to fine tuning by a supervised algorithm, and the structure of the deep belief network is shown in FIG. 4. In the figure, l is the number of implicit layers, ySIs the desired output of the network. w ═ w (w)out,wl,wl-1,…,w2,win) Is the connection weight of the network, and can be determined by the initial weight w determined by unsupervised learningR＝(wl R,wl-1 R,…,w1 R) And carrying out supervised fine adjustment to obtain the product.
And 2.1) acquiring and preprocessing the extraction, tunneling and recovery big data. According to the typical mine practice, acquiring safety monitoring big data related to extraction, tunneling and stoping, wherein the extraction related safety monitoring big data comprises the following steps: the concentration and flow of the extracted gas, the footage of the extracted drill hole and the like, and the safety monitoring big data related to tunneling comprises the following steps: the air-exhaust gas concentration of the excavation roadway, the excavation footage and the like, and the safety monitoring big data related to the back mining comprises the following steps: the concentration of the gas discharged by the stope face, the coal yield and the like. Due to the diversity of data types and formats, the raw data needs to be encoded and normalized.
2.2) training and testing the deep belief network. The training and testing process of the deep belief network is realized by MATLAB programming. And respectively randomly grouping the preprocessed safety monitoring big data samples related to extraction, tunneling and recovery into a training set and a testing set, wherein the n-dimensional matrix r is used as an input sample of the training set and represents n extraction, tunneling or recovery state monitoring parameters. And taking the m-dimensional matrix u as a training set sample label to represent m identification index levels, wherein the matrix adopts binary numbering. And then establishing an n-dimensional matrix q as a test set, and establishing an m-dimensional matrix s as a test set sample label. In the training process, a training set r is input into a deep belief network for pre-training, and then a result obtained by training and a sample label u are brought into a BP neural network for reverse fine adjustment. And substituting the test set q into the trained deep belief network to obtain an identification index result, comparing the identification index result with s, and counting the accuracy. The training and testing process described above is illustrated in fig. 5.
In addition, basic parameters of the deep belief network, such as the number of cycles of each layer, the maximum number of cycles and the like, need to be set according to actual conditions. Based on the process, a correlation model between the outburst mine safety monitoring big data and the extraction mining deployment rationality evaluation identification index based on the deep belief network can be established.
2.3) applying the model. And (3) bringing real-time and dynamic extraction, tunneling and stoping big data into the established depth belief network, so as to obtain real-time and dynamic extraction, tunneling and deployment rationality evaluation and identification indexes.
3) Constructing a dynamic early warning intelligent decision model for extraction mining deployment of the outburst mine based on a Bayesian network theory; ", and"
3.1) establishing a Bayesian network model for the intelligent decision of the extraction and mining deployment of the outburst mine as shown in FIG. 6. In fig. 6, a is the deployment rationality of a gas outburst mine, B1 is a tunneling advancing index, B2 is an area measure engineering effectiveness index, C1 is a development coal amount, C2 is a preparation coal amount, C3 is a measure coal amount, C4 is a protective layer tunneling coal amount, C5 is a protected layer tunneling coal amount, C6 is a gas control coal amount, C7 is a protected layer tunneling face effective length, C8 is a protective layer stoping face effective length, C9 is a protected layer effective length, C10 is a protected layer effective coal amount, and C11 is a gas control effective coal amount.
In this embodiment, a bayesian network model is established in a form of split connection in a bayesian network theory through explicit variables such as "development coal amount C1", "effective length of protected heading face C7", "effective coal amount for gas control C11", and implicit variables such as "preparation coal amount C2", "gas control coal amount C6", "effective length of protected stope C8", "heading advance index B1", "effective index for regional measure engineering B2", and "rationality for gas outburst mine deployment a". The marginal probability of the explicit variables in FIG. 6 is determined primarily by investigating the deployment data of a plurality of mines in recent years and the opinion of a plurality of mine production deployment field experts EE 1-E3. The prior probability and the conditional probability of each node are obtained mainly by two methods: the first method is to obtain objective probability through historical data and statistical data, classify the objective probability according to needs, and calculate probability value occurring in a specific situation range in a probability mode. The second is subjective probability based on expert experience. This example combines the two methods and is done with the help of Netica software. The method comprises the following steps of firstly, taking the reasonable probability of the extraction mining deployment of the outburst mine as a target value to evaluate the deployment rationality of the outburst mine, and determining a conditional probability table of each node in the Bayesian network according to the logical relation among indexes of each layer. The second step updates the edge probabilities of the nodes by clustering expert opinions.
3.2) carrying out forward reasoning on the established Bayesian network model for the intelligent decision of the extraction mining deployment of the outburst mine to obtain the probability P (A ═ Yes) of the reasonable state of the extraction mining deployment of the outburst mine. And dividing the interval according to the obtained probability P (A ═ Yes), and obtaining a judgment criterion for evaluating the extraction mining deployment rationality of the outburst mine, wherein if the P (A ═ Yes) of the evaluated mine deployment state is less than 0.1, the safety level of the mine deployment state is 'unreasonable deployment'. If P (a ═ Yes) is between 0.1 and 0.3, then the security level of the mine deployment state is "generally reasonable to deploy". If P (a ═ Yes) is between 0.3 and 0.5, then the safety level of the mine deployment state is "deploy reasonable". If P (a ═ Yes) is greater than 0.5, then the safety level of the mine deployment state is "deploy initiative". In addition, in the bayesian network, the sensitivity analysis refers to the analysis of the influence of the states of a plurality of reason nodes on the result target node and the degree of the influence. Sensitivity analysis is carried out through Netica software, and the influence degree of different judgment indexes on the extraction mining deployment rationality is obtained.
3.3) when the mine deployment produces an unreasonable state, the probability of its state is P (a ═ Yes) ═ 0. At the moment, the probability change trends of certain indexes can be obtained through automatic probability updating, and key judgment indexes which cause unreasonable extraction and mining can be judged according to the change trends of the indexes. Meanwhile, a Bayesian network model for evaluating the extraction mining deployment rationality of the outburst mine under the condition of unreasonable indexes can be constructed, and the risk probability of the outburst mine extraction mining disorder caused by unreasonable reasons can be evaluated.
4) And when the outburst mine is unreasonably extracted and mined, early warning is carried out and an intelligent decision is made. And the method can timely and accurately give a countermeasure for improving the unreasonable situation of extraction mining deployment of the outburst mine, namely, timely and accurate early warning and intelligent decision making for the unreasonable extraction mining deployment of the outburst mine can be realized.
Claims (4)
1. A dynamic early warning intelligent decision method for mining and deployment imbalance of an outburst mine is characterized by comprising the following steps:
1) constructing a reasonable evaluation index system for extraction mining deployment of the outburst mine; proposing an identification index for the extraction mining deployment rationality of the outburst mine, and quantifying the identification index;
1.1) constructing a reasonable evaluation index system for extraction mining deployment of the outburst mine; wherein, the evaluation index system comprises 2 primary indexes of a tunneling advance index and a regional measure engineering effectiveness index; the tunneling advance index comprises 6 secondary indexes of development tunneling, preparation tunneling, regional measure engineering tunneling, protective layer tunneling and gas control roadway tunneling; the regional measure engineering effectiveness indexes comprise 5 secondary indexes of protective layer roadway strip effectiveness indexes, protective layer mining effectiveness indexes, protected layer roadway strip effectiveness indexes, protected layer mining effectiveness indexes and protective layer gas control effectiveness;
1.2) combining the quantitative indexes to provide identification indexes corresponding to the extraction mining deployment rationality evaluation indexes of the outburst mine; wherein the quantitative index comprises the coal amount and the outburst elimination effective length; the judgment index corresponding to the development tunneling is the development coal amount; the judgment index corresponding to the preparation of tunneling is the preparation coal amount; the judgment index corresponding to the regional measure engineering tunneling is the measure coal quantity; the identification index corresponding to the protective layer tunneling is the protective layer tunneling coal amount; the identification index corresponding to the protected layer tunneling is the amount of coal tunneled by the protected layer; the judgment index corresponding to the gas control roadway tunneling is the gas control coal quantity; the judgment index corresponding to the protective layer roadway strip effectiveness index is the effective length of the protective layer tunneling surface; the judgment index corresponding to the protective layer stoping effectiveness index is the effective length of the protective layer stoping surface; the judgment index corresponding to the effectiveness index of the roadway strip of the protected layer is the effective tunneling length of the protected layer; the judgment index corresponding to the recovery effectiveness index of the protected layer is the effective coal amount of the protected layer; the identification index corresponding to the gas treatment effectiveness of the protective layer is the effective coal amount of the gas treatment;
1.3) combining the definition of the extraction mining deployment rationality identification index of the outburst mine, providing a calculation rule and an identification criterion of the extraction mining deployment rationality identification index of the outburst mine;
2) constructing a correlation model between the extraction related safety monitoring big data of the outburst mine and the extraction related identification index variable; constructing a correlation model between the relevant safety monitoring big data of the outburst mine excavation and the relevant excavation judgment index variable; constructing a correlation model between relevant safety monitoring big data of the extraction of the outburst mine and relevant judgment index variables of the extraction; the extraction related safety monitoring big data comprises extraction gas concentration, flow and extraction drilling footage; the tunneling related safety monitoring big data comprises the concentration of air and gas exhausted from a tunneling roadway and a tunneling footage; the safety monitoring big data related to the stoping comprises the concentration of the wind-exhaust gas of the stoping face and the coal yield;
3) constructing a Bayesian network model for an intelligent decision of extraction, excavation and deployment of the outburst mine based on the evaluation index and the judgment index;
4) and when the outburst mine is unreasonably extracted and mined, early warning is carried out and an intelligent decision is made.
2. The dynamic early warning intelligent decision method for the outburst mine extraction and deployment maladjustment according to claim 1, wherein the step 2) specifically comprises the following steps:
2.1) acquiring safety monitoring big data related to extraction, tunneling and stoping, and preprocessing the data;
2.2) randomly grouping the preprocessed safety monitoring big data samples related to extraction, tunneling and recovery into a training set and a testing set respectively; training and testing a BP neural network, and establishing a correlation model between the outburst mine safety monitoring big data and the extraction mining deployment rationality identification index based on a deep belief network;
and 2.3) bringing real-time and dynamic extraction, tunneling and extraction big data into the established deep belief network to obtain real-time and dynamic extraction and mining deployment rationality judgment indexes.
3. The dynamic early warning intelligent decision method for the outburst mine extraction and deployment maladjustment, according to claim 2, is characterized in that: in step 2.1), the preprocessing includes encoding and normalizing the raw data.
4. The dynamic early warning intelligent decision method for the outburst mine extraction and deployment maladjustment according to claim 1, wherein the step 3) specifically comprises the following steps:
3.1) establishing a Bayesian network model for intelligent decision of outburst mine extraction mining deployment by utilizing a form of branching connection in Bayesian network theory;
3.2) carrying out forward reasoning on the Bayesian network model to obtain the probability P (A = Yes) of reasonable state of extraction mining deployment of the outburst mine; dividing the regions according to the obtained probability P (A = Yes) to obtain a judgment criterion for evaluating the extraction mining deployment rationality of the outburst mine; sensitivity analysis is carried out through Netica software to obtain the influence degree of different identification indexes on the extraction mining deployment rationality;
3.3) judging key judgment indexes which cause unreasonable extraction and mining through the change trend of the index probability when P (A = Yes) = 0; and (4) evaluating the risk probability of the misextraction of the outburst mine caused by unreasonable reasons.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910963488.0A CN111102006B (en) | 2019-10-11 | 2019-10-11 | Dynamic early warning intelligent decision method for outburst mine extraction and mining deployment imbalance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910963488.0A CN111102006B (en) | 2019-10-11 | 2019-10-11 | Dynamic early warning intelligent decision method for outburst mine extraction and mining deployment imbalance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111102006A CN111102006A (en) | 2020-05-05 |
| CN111102006B true CN111102006B (en) | 2020-11-10 |
Family
ID=70421297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910963488.0A Active CN111102006B (en) | 2019-10-11 | 2019-10-11 | Dynamic early warning intelligent decision method for outburst mine extraction and mining deployment imbalance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111102006B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033954B (en) * | 2021-02-18 | 2022-09-06 | 重庆大学 | Intelligent decision-making method for coordinated development of coal and coalbed methane |
| CN113011635B (en) * | 2021-02-18 | 2022-09-16 | 重庆大学 | Coal and coalbed methane coupling coordination development device and method |
| CN113807013B (en) * | 2021-09-17 | 2023-07-11 | 中国联合网络通信集团有限公司 | Method and device for processing top data, electronic equipment and readable storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013053977A1 (en) * | 2011-10-11 | 2013-04-18 | Sandvik Mining And Construction Oy | A method, system and a device for controlling a work machine |
| CN103244188A (en) * | 2013-05-14 | 2013-08-14 | 太原科技大学 | Coal mine underground integrated monitoring and controlling system based on internet of things technology |
| CN106194263B (en) * | 2016-08-29 | 2019-04-02 | 中煤科工集团重庆研究院有限公司 | Coal mine gas disaster monitoring early-warning system and method for early warning |
| CN106437853B (en) * | 2016-09-27 | 2019-02-15 | 西安科技大学 | A kind of coal petrography bump dynamic disaster method for early warning |
| CN106761928A (en) * | 2016-11-25 | 2017-05-31 | 中原工学院 | The collecting method and device of a kind of coal mine safety monitoring system |
| CN108301872B (en) * | 2018-02-28 | 2020-03-31 | 山东科技大学 | Visual mine real-time monitoring alarm system and method based on data filtering |
| CN109595036B (en) * | 2018-12-14 | 2020-06-12 | 北京矿冶科技集团有限公司 | Early warning method for mine ground pressure disaster |
| CN109739849B (en) * | 2019-01-02 | 2021-06-29 | 山东省科学院情报研究所 | Data-driven network sensitive information mining and early warning platform |
-
2019
- 2019-10-11 CN CN201910963488.0A patent/CN111102006B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 煤与瓦斯突出综合预警系统在严重突出矿井;唐远游;《煤矿安全》;20120831;第136-139页 * |
| 煤矿抽掘采平衡指标体系研究与应用;张永斌;《煤》;20170731;第22-23页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111102006A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111102006B (en) | Dynamic early warning intelligent decision method for outburst mine extraction and mining deployment imbalance | |
| CN112529341B (en) | Drilling well leakage probability prediction method based on naive Bayesian algorithm | |
| CN106296435B (en) | A kind of mine gas monitors disorder data recognition method | |
| CN112100727B (en) | Early warning prevention and control method for water burst of water-rich tunnel under influence of fault fracture zone | |
| US11360235B2 (en) | Modeling method and method for diagnosing lost circulation | |
| CN107122860B (en) | Rock burst danger level prediction method based on grid search and extreme learning machine | |
| CN110110740B (en) | Drilling process working condition identification method based on multi-time scale features and neural network | |
| CN109255134A (en) | A kind of acquisition methods of rod-pumped well fault condition | |
| Wang et al. | Prediction of axis attitude deviation and deviation correction method based on data driven during shield tunneling | |
| Dmitrievsky et al. | On increasing the productive time of drilling oil and gas wells using machine learning methods | |
| CN113570226A (en) | Method for evaluating occurrence probability grade of tunnel water inrush disaster in fault fracture zone | |
| CN113431635B (en) | Semi-supervised shield tunnel face geological type estimation method and system | |
| RU2745136C1 (en) | Automated system for identification and prediction of complications in the process of construction of oil and gas wells | |
| CN116341901B (en) | Integrated evaluation method for landslide surface domain-monomer hazard early warning | |
| CN112926839A (en) | Overflow risk cooperative monitoring method and system for oil and gas well drilling process | |
| CN112085242B (en) | Low-resistance layer accurate prediction method and device based on big data deep learning method | |
| CN106246226B (en) | A kind of abnormal recognition methods of Mine Gas Gushing | |
| CN115017206A (en) | Mine CO abnormal disturbance intelligent identification and coal spontaneous combustion early warning value determination method | |
| Yousef et al. | Predictive data analytics application for enhanced oil recovery in a mature field in the Middle East | |
| CN116777085B (en) | Coal mine water damage prediction system based on data analysis and machine learning technology | |
| CN115438823A (en) | Borehole wall instability mechanism analysis and prediction method and system | |
| CN115438090A (en) | Borehole wall instability type analysis and prediction method and system based on lost block image characteristics | |
| CN109033593B (en) | Big data analysis method for inverting working face salient risk factors by utilizing local salient risk prediction forecast data | |
| RU2745137C1 (en) | Automated system for identification and prediction of complications in the process of construction of oil and gas wells | |
| CN114971177A (en) | Surrounding rock grading and digitizing method and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |