CN110363237A - A kind of coal discharge outlet operation decision-making technique based on Hidden Markov random field models - Google Patents
A kind of coal discharge outlet operation decision-making technique based on Hidden Markov random field models Download PDFInfo
- Publication number
- CN110363237A CN110363237A CN201910588103.7A CN201910588103A CN110363237A CN 110363237 A CN110363237 A CN 110363237A CN 201910588103 A CN201910588103 A CN 201910588103A CN 110363237 A CN110363237 A CN 110363237A
- Authority
- CN
- China
- Prior art keywords
- discharge outlet
- coal
- coal discharge
- hidden markov
- random field
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004590 computer program Methods 0.000 claims description 7
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 abstract description 3
- 238000005065 mining Methods 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
- G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Animal Husbandry (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Agronomy & Crop Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Disintegrating Or Milling (AREA)
- Machine Translation (AREA)
Abstract
A kind of coal discharge outlet operation decision-making technique based on Hidden Markov random field models, the motion space including establishing coal discharge outlet；Establish the state space of coal discharge outlet；The input random field of coal discharge outlet group；Establish coal discharge outlet decision output markov random file；Establish Hidden Markov random field models;According to maximum a posteriori probability principle, decision optimal value is exported.The invention patent proposes a kind of Hidden Markov random field models of coal discharge outlet operation decision first, on the basis of the system model of Hidden Markov random field, the intelligent decision of coal discharge outlet movement is realized by maximum a posteriori probability, it improves top coals' recovery ratio, reduce the percentage of shale content that produces coal, realize safe and efficient, the accurate exploitation of coal resources.
Description
Technical field
The invention belongs to fully mechanized coal face caving Mining Technology field, more particularly to one kind are random based on Hidden Markov
The coal discharge outlet of field model operates decision-making technique.
Background technique
Hydraulic support is the core equipment of fully mechanized coal face safety support and top coal recycling.One fully mechanized coal face usually has
Up to a hundred hydraulic support arrangements, constitute hydraulic support group.Behind coal seam under the shielding of coalcutter digging hydraulic support, hydraulic support
It is pushed forward, top coal can spontaneous caving.Hydraulic support packs up tail boom, and coal discharge outlet is opened, and the top coal fallen can smoothly fall into rear portion scraper plate
Transporter；When top coal let-down finishes, stretching, extension tail boom, coal discharge outlet closes, prevents spoil and enter rear portion scratch board conveyor.
During longwall top coal caving, the coal caving ratio of top coal is low and the percentage of shale content height that produces coal is the great difficult problem generally faced.
Currently, the coal caving ratio of longwall top-coal caving is only 75%~80% or so, a large amount of top coal can not be produced effectively, be caused huge
The wasting of resources.Meanwhile the percentage of shale content to produce coal is high, and transportation cost and post-processing expense greatly improved.
The coal process of putting of hydraulic support group is directly related to the coal caving ratio of top coal and the percentage of shale content to produce coal.In longwall top coal caving,
Top coal migration is broken, directly push up inbreak, a series of base object model multiple dynamic processes such as steady are directly opened with hydraulic support coal discharge outlet
Pass quantity, order of operation, and operation step pitch are related.Due to being limited by complex geological condition, coal process is put at present still with artificial
Operation and single rack operation based on, can not global planning consider top plate geological conditions, top coal occurrence status, hydraulic support group motion make etc.
Incidence relation between various information, this causes during longwall top coal caving, and top coals' recovery ratio is low, the percentage of shale content of mining of producing coal is high
One of the major reasons.
Currently, the operation of fully mechanized coal face Sub-Level Caving, mainly based on manual hand manipulation.Manual operation can not be from comprehensive
It puts working face systemic hierarchial to take in the state of top coal, the cooperation being unable to complete between coal discharge outlet, so that top coal can not be made
Recycling be optimal.
Summary of the invention
To solve the above problems, a kind of coal discharge outlet operation decision-making technique based on Hidden Markov random field models is provided,.
The object of the present invention is achieved in the following manner:
A kind of coal discharge outlet operation decision-making technique based on Hidden Markov random field models, which comprises
S1: establish the motion space of coal discharge outlet: the motion space of coal discharge outlet is expressed as A={ a1,a2, wherein movement is chosen
a1Expression is opened, and a is chosen2It indicates to close, sets a1=1, a2=2；
S2: establish the state space of coal discharge outlet: the state-space representation of coal discharge outlet is S={ s1,s2,...,s12, it is each
The state value of a coal discharge outlet is the coal content near coal discharge outlet；
S3: the input random field of coal discharge outlet group: setting a working face and share N number of coal discharge outlet, then the stochastic variable X inputted
={ X1,X2,...,XN, wherein Xi∈S；
S4: coal discharge outlet decision output markov random file Y={ Y is established1,Y2,...,YN, wherein Yi∈A；
S5: Hidden Markov random field models are established:
The stochastic variable X of input be it is observable, value be X=x={ x1,x2,...,xN}；The output Y of system is not
Observable, value is Y=y={ y1,y2,...,yN}；Wherein x, y are respectively observable random variable values and hidden random
Variate-value；
Hidden Markov random field models are the items about observable random variable X and Hidden Markov stochastic variable neighborhood
Part probability-distribution function:
Wherein,Indicate that the conditional probability with parameter, conditional probability are indicated in neighborhood NyiUnder the conditions of xiIt is general
Rate value, wherein parameter beAndNyiIndicate yiNeighborhood, because of yiOnly two, switch values, thenValue
For
According to maximum a posteriori probability principle, exports decision optimal value and is given by:
WhereinFor prior probability,It is Hidden Markov random field models；
By formula (3) it is found that the execution of N number of coal discharge outlet is acted by Hidden Markov random field modelsIt is general with priori
Rate p (yi|Nyi) determine together；System inputs the current state x={ x of each coal discharge outlet first1,x2,...,xN, xi∈ S, i.e., often
The state of a coal discharge outlet takes some value of state space；Then the optimizing decision y of coal discharge outlet movement can be obtained according to formula (3)*
={ y1 *,y2 *,...,yN *, yi *∈A。
S in the state space of coal discharge outlet1,s2,…..s12, respectively indicate coal content difference 0, (0,0.1], (0.1,
0.2]、(0.2,0.3]、(0.3,0.4]、(0.4,0.5]、(0.5,0.6]、(0.6,0.7]、(0.7,0.8]、(0.8,0.9]、
(0.9,1)、1。
The parameterIt is provided using EM algorithm；
(1) it givesInitial value
(2) E is walked: according to initial valueCalculate Θi(yi)
(3) M is walked: according to following formula undated parameter
(4) it is iterated between E step and M step, iteration terminates to judge that parameter is
Wherein, t indicates the number of iterations；Iteration stopping condition is set are as follows:
△<0.0001。
A kind of computer readable storage medium is stored in the computer readable storage medium and may be adapted to processor execution
Computer program, and implement such as claim 1-2 any the method when the computer program is executed by the processor
The step of.
Beneficial effects of the present invention: the invention patent proposes that a kind of Hidden Markov of coal discharge outlet operation decision is random first
Field model realizes the intelligence of coal discharge outlet movement by maximum a posteriori probability on the basis of the system model of Hidden Markov random field
Energy decision improves top coals' recovery ratio, reduces the percentage of shale content that produces coal, realizes safe and efficient, the accurate exploitation of coal resources.
Detailed description of the invention
Fig. 1 is inventive algorithm logical relation and flow chart.
Specific embodiment
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
The present invention provides a kind of coal discharge outlet operation decision-making technique based on Hidden Markov random field models, and this method is hidden
On the basis of the system model of markov random file, the intelligent decision of coal discharge outlet movement is realized by maximum a posteriori probability.
The method of the present invention includes the following steps:
S1: the motion space of coal discharge outlet is established:
There are two coal discharge outlet movements: on and off, the motion space of coal discharge outlet is expressed as A={ a1,a2, wherein acting
Choose a1Expression is opened, and a is chosen2It indicates to close, sets a1=1, a2=2；
S2: the state space of coal discharge outlet is established:
The state value of each coal discharge outlet is the coal content put near coal, and the value range of the value is [0,1], and discretization
For 12 grades, state space is constituted, the state-space representation of coal discharge outlet is S={ s1,s2,...,s12, wherein s1,
S2 ... ..s12, respectively indicate coal content difference 0, (0,0.1], (0.1,0.2], (0.2,0.3], (0.3,0.4], (0.4,
0.5], (0.5,0.6], (0.6,0.7], (0.7,0.8], (0.8,0.9], (0.9,1), 12 kinds of situations such as 1；S3: coal discharge outlet group
The input random field of group:
If a working face shares N number of coal discharge outlet, then the stochastic variable X={ X of the input of system1,X2,...,XN, wherein
Xi∈ S, the i.e. state value of each coal discharge outlet are some value of state space；
S4: coal discharge outlet decision output markov random file Y={ Y is established1,Y2,...,YN, wherein Yi∈A；It is i.e. each
The state of coal discharge outlet all goes the value of motion space.Coal discharge outlet movement decision process in, under normal circumstances, decision process only in accordance with
The current state value of model；And these current state values are the results for executing last decision.This is that is, coal discharge outlet is current
Decision process it is only related with last decision, this is typical markov decision process.Therefore YiAction sequence it is full
The condition of sufficient markov decision process.
S5: Hidden Markov random field models are established:
The stochastic variable X of input be it is observable, value be X=x={ x1,x2,...,xN}；The output Y of system is not
Observable, value is Y=y={ y1,y2,...,yN}；Wherein x, y are respectively observable random variable values and hidden random
Variate-value；
Hidden Markov random field models are the items about observable random variable X and Hidden Markov stochastic variable neighborhood
Part probability-distribution function:
Wherein,Indicate that the conditional probability with parameter, conditional probability are indicated in neighborhood NyiUnder the conditions of xiIt is general
Rate value, wherein parameter beAndNyiIndicate yiNeighborhood, because of yiOnly two, switch values, thenValue
For
According to maximum a posteriori probability principle, exports decision optimal value and is given by:
Wherein p (yi|Nyi) it is prior probability, it is provided by experience and is converted into Probability Forms.By formula (3) it is found that N number of coal discharge outlet
Execution act by Hidden Markov random field modelsWith prior probability p (yi|Nyi) determine together.Hidden Markov
Parameter in random field modelsIt is obtained by the training of EM algorithm, prior probability is obtained by field experience, and typical priori is general
Rate is as shown in table 1.
After the parameter training of markov random file, system inputs the current state x=of each coal discharge outlet first
{x1,x2,...,xN, xiThe state of ∈ S, i.e., each coal discharge outlet take some value of state space；Then it can be obtained according to formula (3)
The optimizing decision y acted to coal discharge outlet*={ y1 *,y2 *,...,yN *, yi *∈A。
Table 1
When the numerical value of upper table indicates that coal discharge outlet is in some state, movement is the probability value of on or off.These values
It can rule of thumb provide roughly.
ParameterIt is provided using EM (expectation-maximization) algorithm；
1) it givesInitial value
(2) E is walked: according to initial valueCalculate Θi(yi)
(3) M is walked: according to following formula undated parameter
(4) it is iterated between E step and M step, iteration terminates to judge that parameter is
Wherein, t indicates the number of iterations.General setting iteration stopping condition are as follows: the number of iterations is more than some value or △ small
In some value.The value expression parameter that wherein △ is less than some very little has restrained.Rule of thumb, it is typically chosen following condition
△<0.0001。
The invention also includes a kind of computer readable storage medium, being stored in the computer readable storage medium can be fitted
In the computer program that processor executes, and when the computer program is executed by the processor implementation above method step
Suddenly.
Above-mentioned computer readable storage medium may include any entity or dress that can carry the computer program
It sets, recording medium, USB flash disk, mobile hard disk, CD, disk, computer storage etc..
The invention patent proposes a kind of Hidden Markov random field models of coal discharge outlet operation decision first, in hidden Ma Erke
On the basis of the system model of husband's random field, the intelligent decision of coal discharge outlet movement is realized by maximum a posteriori probability, improves top coal
Coal caving ratio reduces the percentage of shale content that produces coal, and realizes safe and efficient, the accurate exploitation of coal resources.
What has been described above is only a preferred embodiment of the present invention, it is noted that for those skilled in the art,
Without depart from that overall concept of the invention, several changes and improvements can also be made, these also should be considered as of the invention
Protection scope.
Claims (4)
1. a kind of coal discharge outlet based on Hidden Markov random field models operates decision-making technique, it is characterised in that: the method packet
It includes:
S1: establish the motion space of coal discharge outlet: the motion space of coal discharge outlet is expressed as A={ a1,a2, wherein a is chosen in movement1Table
Show out, chooses a2It indicates to close, sets a1=1, a2=2；
S2: establish the state space of coal discharge outlet: the state-space representation of coal discharge outlet is S={ s1,s2,...,s12, each puts coal
The state value of mouth is the coal content near coal discharge outlet；
S3: the input random field of coal discharge outlet group: setting a working face and share N number of coal discharge outlet, then the stochastic variable X=inputted
{X1,X2,...,XN, wherein Xi∈S；
S4: coal discharge outlet decision output markov random file Y={ Y is established1,Y2,...,YN, wherein Yi∈A；
S5: Hidden Markov random field models are established:
The stochastic variable X of input be it is observable, value be X=x={ x1,x2,...,xN}；The output Y of system is inconsiderable
It surveys, value is Y=y={ y1,y2,...,yN}；Wherein x, y are respectively observable random variable values and hidden stochastic variable
Value；
Hidden Markov random field models are general about observable random variable X and the condition of Hidden Markov stochastic variable neighborhood
Rate distribution function:
Wherein,Indicate that the conditional probability with parameter, conditional probability are indicated in neighborhood NyiUnder the conditions of xiProbability value,
Wherein parameter isAndNyiIndicate yiNeighborhood, because of yiOnly two, switch values, thenValue is
According to maximum a posteriori probability principle, exports decision optimal value and is given by:
Wherein p (yi|Nyi) it is prior probability,It is Hidden Markov random field models；
By formula (3) it is found that the execution of N number of coal discharge outlet is acted by Hidden Markov random field modelsWith prior probability p (yi
|Nyi) determine together；System inputs the current state x={ x of each coal discharge outlet first1,x2,...,xN, xi∈ S, i.e., each put coal
The state of mouth takes some value of state space；Then the optimizing decision y of coal discharge outlet movement can be obtained according to formula (3)*={ y1 *,
y2 *,...,yN *, yi *∈A。
2. the coal discharge outlet as described in claim 1 based on Hidden Markov field model immediately operates decision-making technique, feature exists
In s1, s2 in the state space of coal discharge outlet ... ..s12, respectively indicate coal content difference 0, (0,0.1], (0.1,0.2],
(0.2,0.3]、(0.3,0.4]、(0.4,0.5]、(0.5,0.6]、(0.6,0.7]、(0.7,0.8]、(0.8,0.9]、(0.9,
1)、1。
3. the coal discharge outlet based on Hidden Markov random field models operates decision-making technique as described in claim 1, feature exists
In: the parameterIt is provided using EM algorithm；
(1) it givesInitial value
(2) E is walked: according to initial valueCalculate Θi(yi)
(3) M is walked: according to following formula undated parameter
(4) it is iterated between E step and M step, iteration terminates to judge that parameter is
Wherein, t indicates the number of iterations；Iteration stopping condition is set are as follows:
△<0.0001。
4. a kind of computer readable storage medium, it is characterised in that: being stored in the computer readable storage medium may be adapted to
The computer program that processor executes, and implement such as claim 1-2 when the computer program is executed by the processor
The step of one the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910588103.7A CN110363237B (en) | 2019-07-01 | 2019-07-01 | Coal caving port operation decision method based on hidden Markov random field model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910588103.7A CN110363237B (en) | 2019-07-01 | 2019-07-01 | Coal caving port operation decision method based on hidden Markov random field model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110363237A true CN110363237A (en) | 2019-10-22 |
| CN110363237B CN110363237B (en) | 2021-09-07 |
Family
ID=68217669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910588103.7A Active CN110363237B (en) | 2019-07-01 | 2019-07-01 | Coal caving port operation decision method based on hidden Markov random field model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363237B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325093A (en) * | 2013-05-20 | 2013-09-25 | 中国科学院电子学研究所 | Method and system for phase position unwrapping based on MRF |
| CN104008374A (en) * | 2014-06-04 | 2014-08-27 | 中国矿业大学(北京) | Method for conducting miner detection in mine images on the basis of conditional random field |
| CN104732117A (en) * | 2015-04-02 | 2015-06-24 | 苏州科技学院 | G protein-coupled receptor topology calculation prediction method based on feedback type conditional random field |
| CN105824886A (en) * | 2016-03-10 | 2016-08-03 | 西安电子科技大学 | Rapid food recognition method based on Markov random field |
| CN109063269A (en) * | 2018-07-07 | 2018-12-21 | 河南理工大学 | Hydraulic support group's top plate supporting control method based on graph model, storage medium |
-
2019
- 2019-07-01 CN CN201910588103.7A patent/CN110363237B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325093A (en) * | 2013-05-20 | 2013-09-25 | 中国科学院电子学研究所 | Method and system for phase position unwrapping based on MRF |
| CN104008374A (en) * | 2014-06-04 | 2014-08-27 | 中国矿业大学(北京) | Method for conducting miner detection in mine images on the basis of conditional random field |
| CN104732117A (en) * | 2015-04-02 | 2015-06-24 | 苏州科技学院 | G protein-coupled receptor topology calculation prediction method based on feedback type conditional random field |
| CN105824886A (en) * | 2016-03-10 | 2016-08-03 | 西安电子科技大学 | Rapid food recognition method based on Markov random field |
| CN109063269A (en) * | 2018-07-07 | 2018-12-21 | 河南理工大学 | Hydraulic support group's top plate supporting control method based on graph model, storage medium |
Non-Patent Citations (3)
| Title |
|---|
| CUI LIZHEN 等: "Positioning algorithms of underground coal mines based on virtual Radio-map and Markov chain", 《JOURNAL OF PLA UNIVERSITY OF SCIENCE AND TECHNOLOGY》 * |
| 刘旭辉: "龙宫煤业煤矿掘进巷道顶板灾害防治技术研究", 《煤炭与化工》 * |
| 张喆 等: "基于证据马尔可夫随机场模型的图像分割", 《控制与决策》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110363237B (en) | 2021-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102693317B (en) | Method and device for data mining process generating | |
| CN113326244B (en) | Abnormality detection method based on log event graph and association relation mining | |
| Biere | Lingeling and Friends at the SAT Competition 2011 | |
| CN104123591A (en) | Smart grid classification and fuzzy neural network based natural gas load prediction method | |
| CN105912588A (en) | Visualization processing method and system for big data based on memory calculations | |
| CN104408127A (en) | Maximal pattern mining method for uncertain data based on depth-first | |
| CN105740521B (en) | Small grid elimination method and device during reservoir numerical simulation system solution | |
| CN108280289B (en) | Rock burst danger level prediction method based on local weighted C4.5 algorithm | |
| JP5375429B2 (en) | Design support apparatus, method, and program | |
| CN103761337A (en) | Method and system for processing unstructured data | |
| CN106503755A (en) | A kind of structural similarity matching process towards fault tree | |
| CN112288397A (en) | Flow template configuration method, flow execution method and device and electronic equipment | |
| CN102799960B (en) | The concurrent service flow process method for detecting abnormality of data-orlented model | |
| CN104462329B (en) | A kind of operation flow method for digging suitable for diverse environments | |
| CN110363237A (en) | A kind of coal discharge outlet operation decision-making technique based on Hidden Markov random field models | |
| CN115659522B (en) | Aircraft transition position prediction method, device, equipment and medium | |
| Krivtchik | COSI7: The new CEA reference electro-nuclear simulation tool | |
| CN104461780B (en) | A kind of method and device for discharging data block | |
| CN104992015B (en) | A kind of HFSS Engineering Optimizational Methods based on optimized algorithm | |
| Qu et al. | Mining Engineering Image Recognition Method Based on Simulated Annealing Algorithm | |
| CN112765766A (en) | Dynamic interactive fine-grained discrete event system time sequence advancing method | |
| Sotoudeh et al. | Introducing a user-friendly computer program for determining the location of underground stopes | |
| Sheth et al. | Intelligent time-stepping for practical numerical simulation | |
| Askari-Nasab et al. | Intelligent optimal production scheduling estimator | |
| CN114840545B (en) | Block chain fine-grained editing method supporting rapid state updating |
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 |