CN106228241A - The ore deposit rock intensity flexible measurement method that adaptability artificial bee colony optimizes - Google Patents
The ore deposit rock intensity flexible measurement method that adaptability artificial bee colony optimizes Download PDFInfo
- Publication number
- CN106228241A CN106228241A CN201610585884.0A CN201610585884A CN106228241A CN 106228241 A CN106228241 A CN 106228241A CN 201610585884 A CN201610585884 A CN 201610585884A CN 106228241 A CN106228241 A CN 106228241A
- Authority
- CN
- China
- Prior art keywords
- individual
- individuality
- popsize
- ore deposit
- population
- 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
- 239000011435 rock Substances 0.000 title claims abstract description 63
- 238000000691 measurement method Methods 0.000 title claims abstract description 10
- 230000007935 neutral effect Effects 0.000 claims abstract description 29
- 238000005259 measurement Methods 0.000 claims abstract description 19
- 238000013461 design Methods 0.000 claims abstract description 8
- 230000003044 adaptive effect Effects 0.000 claims abstract description 5
- 230000035772 mutation Effects 0.000 claims abstract description 3
- 238000012360 testing method Methods 0.000 claims description 19
- 241000256844 Apis mellifera Species 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 13
- 238000010521 absorption reaction Methods 0.000 claims description 6
- 230000000977 initiatory effect Effects 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000000205 computational method Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 claims 4
- 230000008447 perception Effects 0.000 claims 1
- 238000005065 mining Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- BVKZGUZCCUSVTD-UHFFFAOYSA-L Carbonate Chemical compound [O-]C([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-L 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 241000721047 Danaus plexippus Species 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Animal Husbandry (AREA)
- Primary Health Care (AREA)
- Marine Sciences & Fisheries (AREA)
- Marketing (AREA)
- Agronomy & Crop Science (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Mining & Mineral Resources (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Geophysics And Detection Of Objects (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses the ore deposit rock intensity flexible measurement method that a kind of adaptability artificial bee colony optimizes.The present invention uses three layer perceptron neutral net as the soft-sensing model of ore deposit rock intensity, utilizes adaptability artificial bee colony algorithm to optimize connection weights and the bias of design neutral net.In adaptability artificial bee colony algorithm, search zoom factor produces adaptively according to the feedback information of adaptive value, and devises the Gaussian mutation strategy based on neighborhood optimum individual and global optimum are individual and produce new individuality adaptively.The present invention can improve the hard measurement precision of ore deposit rock intensity, improves the measurement efficiency of ore deposit rock intensity.
Description
Technical field
The present invention relates to rock ionization meter field, ore deposit, especially relate to the ore deposit rock intensity that a kind of adaptability artificial bee colony optimizes
Flexible measurement method.
Background technology
In mining engineering, in order to ensure the safety of mining production, it is often necessary to grasp the intensity of ore deposit rock.Therefore ore deposit rock is strong
The measurement of degree is an important foundation sex work in mining production practice.Tradition ore deposit rock strength measurement method generally requires cost
Bigger human and material resources cost, thus cause ore deposit rock ionization meter inefficient.Therefore, ore removal is measured the most quickly and accurately
The intensity of rock always mining engineering personnel are continually striving to the problem of research.In order to improve the efficiency of ore deposit rock ionization meter, many
Engineering staff proposes the flexible measurement method of ore deposit rock intensity.This measuring method is closely related and appearance by some and ore deposit rock intensity
Easily measure and measure lower-cost auxiliary variable to set up the mathematical model of ore deposit rock intensity.Become by measuring these auxiliary
Amount, and utilize mathematical model to calculate ore removal rock intensity.This method has a lot of clear advantage, and it is possible not only to accelerate ore deposit rock
The measuring speed of intensity, it is also possible to reduce the measurement cost of ore deposit rock intensity, thus improve the efficiency of ore deposit rock ionization meter.
Owing to ore deposit rock intensity hard measurement has numerous advantages, it has attracted many engineers and technicians to study it
And propose various ore deposits rock intensity flexible measurement method.Such as Liu proposes nerual network technique to monarch and Asia, Luoping and sets up
The forecast model of rock strength parameter (Liu Xiangjun, Luoping is sub-. and utilize the nerual network technique to set up rock strength forecast model
[J]. Southwest Petroleum Institute journal, 1995,17 (3): 66-70);Cui Tiejun et al. utilizes neural network at single shaft and three
Under axle load condition to Strength Criteria of Rock model (Cui Tiejun, Ma Yundong, Xiao Xiaochun. rock strength based on neutral net is accurate
Then research [J]. Central China Normal University's journal: natural science edition, 2014,48 (1): 131-135);Lu Gongda et al. utilizes nerve
Network carbonate rock uniaxial compressive strength is established model (Lu Gongda, Yan Echuan, Wang Huanling, etc. based on rock geology essence
Property carbonate rock uniaxial compressive strength prediction [J]. Jilin University's journal (geoscience version), 2013,43 (6): 1915-
1921)。
Understanding from existing achievement in research, neutral net uses widely in the rock intensity hard measurement of ore deposit.But pass
System neutral net tends to occur being absorbed in local optimum when setting up the soft-sensing model of ore deposit rock intensity, and certainty of measurement is the highest
Shortcoming.
Summary of the invention
It is an object of the invention to be easily trapped into local optimum for traditional neural network model when ore deposit rock intensity hard measurement,
The shortcoming that hard measurement precision is the highest, proposes the ore deposit rock intensity flexible measurement method that adaptability artificial bee colony optimizes.The present invention can carry
The hard measurement precision of high ore deposit rock intensity, improves the measurement efficiency of ore deposit rock intensity.
Technical scheme: the ore deposit rock intensity flexible measurement method that a kind of adaptability artificial bee colony optimizes, including following
Step:
Step 1, gathers RN ore deposit rock test specimen in the region needing hard measurement, and ore deposit rock test specimen is carried out experiment measures
Water absorption rate, dry density, natural impedance, dynamical possion ratio, dynamic modulus of elasticity and the comprcssive strength of each ore deposit rock test specimen, by ore deposit rock test specimen
Experimental data as sample data set;Then the sample data set collected is normalized;
Step 2, user's initiation parameter, described initiation parameter includes three layer perceptron neutral net hidden layer neuron
Number HN, Population Size Popsize, maximum do not improves number of times Limit, radius of neighbourhood NK, maximum evaluates number of times MAX_FEs;
Step 3, current evolution algebraically t=0, Evaluation: Current number of times FEs=0;
Step 4, makes the normalized water absorption rate that input variable is ore deposit rock test specimen of three layer perceptron neutral net, dry close
Degree, natural impedance, dynamical possion ratio, dynamic modulus of elasticity, and it is output as the normalized comprcssive strength of ore deposit rock test specimen, it is then determined that three layers
The hidden layer of perceptron neural network and the transmission function of output layer, and calculate the optimization design ginseng of three layer perceptron neutral net
Several several D=HN × 7+1;
Step 5, random initializtion populationWherein: individual subscript i=1,
2,...,Popsize;For population PtIn i-th individual and to store three layer perceptron neural
The D of network design parameter to be optimized, it randomly generates formula and is:
Wherein dimension subscript j=1,2 .., D;Rand (0,1) represents the function producing random real number between [0,1];
Step 6, calculates population PtIn each individualityAdaptive valueWherein individual subscript i=1,2 ...,
Popsize, individualAdaptive valueComputational methods be: by individualityIt is decoded as three layer perceptron neutral net
Connect weights and bias, and calculate three layer perceptron neutral net mean square error NE on sample data seti, then order
BodyAdaptive value
Step 7, makes population PtIn all individualities do not improve number of timesWherein individual subscript i=1,2 ...,
Popsize;
Step 8, preserves population PtIn optimum individual Bestt, then make Evaluation: Current number of times FEs=FEs+Popsize,
And make average factor M NU=0.5;
Step 9, employs honeybee to perform adaptability search operation, specifically comprises the following steps that
Step 9.1, makes enumerator i=1, and makes zoom factor list SCFList for sky;
Step 9.2, order is new individual
Step 9.3, with MNU as average, 0.1 be standard deviation produce a gaussian random real number GRV, then order scaling because of
Sub-SCF=GRV × 2-1;
Step 9.4, randomly generates positive integer RD1 between [1, D];
Step 9.5, randomly generates two unequal positive integers RI1 and RI2 between [1, Popsize];
Step 9.6, order
Step 9.7, calculates new individual UtAdaptive value Fit (Ut);
Step 9.8, if new individual UtThan individualityMore excellent, then GRV is added in zoom factor list SCFList;
Step 9.9, at individualityWith new individual UtBetween perform select operation and update individual Bi tDo not improve number of times
Step 9.10, makes enumerator i=i+1;
Step 9.11, if enumerator i is less than or equal to Popsize, then forwards step 9.2 to, otherwise forwards step 9.12 to;
Step 9.12, calculates meansigma methods MeanSCF of data in zoom factor list SCFList;
Step 9.13, randomly generates a real number RW between [0.8,1.0];
Step 9.14, makes MNU=RW × MNU+ (1-RW) × MeanSCF;
Step 9.15, forwards step 10 to;
Step 10, according to population PtThe adaptive value of middle individuality calculates the select probability of all individualities;
Step 11, observes honeybee according to population PtIn the select probability of each individuality select the individual adaptability Gauss of execution and become
ETTHER-OR operation generates new individual, then perform to select operation and calculate individuality do not improve number of times, specifically comprise the following steps that
Step 11.1, makes enumerator i=1;
Step 11.2, according to population PtIn each individuality select probability use roulette policy selection go out individualityAnd
Order is new individual
Step 11.3, makes neighborhood subscript RSI=(SEI-NK+Popsize) %Popsize, and wherein SEI represents roulette plan
Slightly selecting the subscript of individuality, % represents that complementation accords with;
Step 11.4, makes neighborhood optimum individualAnd make enumerator rt=1;
Step 11.5, makes neighborhood subscript RSI=(RSI+1) %Popsize;
Step 11.6, if individualThan individual RSBesttMore excellent, then makeOtherwise keep
RSBesttConstant;
Step 11.7, makes enumerator rt=rt+1;
Step 11.8, if rt is less than or equal to NK × 2, then forwards step 11.5 to, otherwise forwards step 11.9 to;
Step 11.9, randomly generates positive integer RD2 between [1, D];
Step 11.10, randomly generates positive integer RSN between [1, NK × 2], then makes random neighborhood subscript RNI
=(SEI-NK+RSN+Popsize) %Popsize;
Step 11.11, makes average
Step 11.12, makes standard deviationWherein abs represents and takes absolute value
Function;
Step 11.13, with GRMean as average, GRSD is that standard deviation produces a gaussian random real number RVal, if
The value of RVal is beyond [LBRD2,UBRD2Scope between], then use same method to regenerate gaussian random real number RVal,
Until the value of RVal is without departing from [LBRD2,UBRD2Scope between];
Step 11.14, randomly generates positive integer RI3 between [1, Popsize];
Step 11.15, makes average
Step 11.16, makes standard deviationWherein abs represents the letter taken absolute value
Number;
Step 11.17, with GBMean as average, GBSD is that standard deviation produces a gaussian random real number BVal, if
The value of BVal is beyond [LBRD2,UBRD2Scope between], then use same method to regenerate gaussian random real number BVal,
Until the value of BVal is without departing from [LBRD2,UBRD2Scope between];
Step 11.18, randomly generates a real number RNW between [0,1];
Step 11.19, order
Step 11.20, calculates new individual UtAdaptive value Fit (Ut), then at individualityWith new individual UtBetween perform
Select operation, and calculate individualityDo not improve number of times
Step 11.21, makes enumerator i=i+1;
Step 11.22, if enumerator i is less than or equal to Popsize, then forwards step 11.2 to, otherwise forwards step 12 to;
Step 12, makes Evaluation: Current number of times FEs=FEs+Popsize × 2;
Step 13, search bee finds out population PtIn do not improve the individuality that number of times is maximum, and this individuality of labelling isAs
Fruit is individualDo not improve number of times less than Limit, then forward step 14 to, otherwise to individualityCarry out random initializtion,
And make individualityThe number of times that do not improves be 0;
Step 14, preserves population PtMiddle optimum individual Bestt;
Step 15, makes current evolution algebraically t=t+1;
Step 16, repeats step 9 to step 15 until Evaluation: Current number of times FEs terminates after reaching MAX_FEs, will perform
The optimum individual Best obtained in journeytIt is decoded as connection weights and the bias of three layer perceptron neutral net, and will obtain
Three layer perceptron neutral net, as soft-sensing model, can realize the hard measurement of ore deposit rock intensity.
The present invention uses three layer perceptron neutral net as the soft-sensing model of ore deposit rock intensity, utilizes adaptability people worker bee
Group's algorithm optimizes connection weights and the bias of design neutral net.In adaptability artificial bee colony algorithm, search scaling because of
Daughter root produces adaptively according to the feedback information of adaptive value, and devises individual based on neighborhood optimum individual and global optimum
Gaussian mutation strategy produces new individuality adaptively.The present invention can improve the hard measurement precision of ore deposit rock intensity, improves ore deposit rock
The measurement efficiency of intensity.
Accompanying drawing explanation
Fig. 1 is the flow chart of the present invention.
Detailed description of the invention
Below by embodiment, and combine accompanying drawing, technical scheme is described in further detail.
Embodiment:
Step 1, determines the region needing hard measurement ore deposit rock intensity, then gathers RN=28 ore deposit rock in the region determined
Test specimen, and ore deposit rock test specimen is tested measure the water absorption rate of each ore deposit rock test specimen, dry density, natural impedance, dynamical possion ratio, dynamic
Elastic modelling quantity and comprcssive strength, using the experimental data of ore deposit rock test specimen as sample data set;Then to the sample number collected
It is normalized according to collection;
Step 2, user's initiation parameter, described initiation parameter includes three layer perceptron neutral net hidden layer neuron
Number HN=6, Population Size Popsize=50, maximum do not improves number of times Limit=100, radius of neighbourhood NK=5, and maximum is commented
Valency number of times MAX_FEs=300000;
Step 3, current evolution algebraically t=0, Evaluation: Current number of times FEs=0;
Step 4, makes the normalized water absorption rate that input variable is ore deposit rock test specimen of three layer perceptron neutral net, dry close
Degree, natural impedance, dynamical possion ratio, dynamic modulus of elasticity, and it is output as the normalized comprcssive strength of ore deposit rock test specimen, it is then determined that three layers
The hidden layer of perceptron neural network and the transmission function of output layer, and calculate the optimization design ginseng of three layer perceptron neutral net
Several several D=HN × 7+1;
Step 5, random initializtion populationWherein: individual subscript i=1,
2,...,Popsize;For population PtIn i-th individual and store three layer perceptron god
Through D the design parameter to be optimized of network, it randomly generates formula and is:
Wherein dimension subscript j=1,2 .., D;Rand (0,1) represents the function producing random real number between [0,1];
Step 6, calculates population PtIn each individualityAdaptive valueWherein individual subscript i=1,2 ...,
Popsize, individualAdaptive valueComputational methods be: by individualityIt is decoded as three layer perceptron neutral net
Connect weights and bias, and calculate three layer perceptron neutral net mean square error NE on sample data seti, then order
BodyAdaptive value
Step 7, makes population PtIn all individualities do not improve number of timesWherein individual subscript i=1,2 ...,
Popsize;
Step 8, preserves population PtIn optimum individual Bestt, then make Evaluation: Current number of times FEs=FEs+Popsize,
And make average factor M NU=0.5;
Step 9, employs honeybee to perform adaptability search operation, specifically comprises the following steps that
Step 9.1, makes enumerator i=1, and makes zoom factor list SCFList for sky;
Step 9.2, order is new individual
Step 9.3, with MNU as average, 0.1 be standard deviation produce a gaussian random real number GRV, then order scaling because of
Sub-SCF=GRV × 2-1;
Step 9.4, randomly generates positive integer RD1 between [1, D];
Step 9.5, randomly generates two unequal positive integers RI1 and RI2 between [1, Popsize];
Step 9.6, order
Step 9.7, calculates new individual UtAdaptive value Fit (Ut);
Step 9.8, if new individual UtThan individualityMore excellent, then GRV is added in zoom factor list SCFList;
Step 9.9, at individualityWith new individual UtBetween perform select operation and update individual Bi tDo not improve number of times
Step 9.10, makes enumerator i=i+1;
Step 9.11, if enumerator i is less than or equal to Popsize, then forwards step 9.2 to, otherwise forwards step 9.12 to;
Step 9.12, calculates meansigma methods MeanSCF of data in zoom factor list SCFList;
Step 9.13, randomly generates a real number RW between [0.8,1.0];
Step 9.14, makes MNU=RW × MNU+ (1-RW) × MeanSCF;
Step 9.15, forwards step 10 to;
Step 10, according to population PtThe adaptive value of middle individuality calculates the select probability of all individualities;
Step 11, observes honeybee according to population PtIn the select probability of each individuality select the individual adaptability Gauss of execution and become
ETTHER-OR operation generates new individual, then perform to select operation and calculate individuality do not improve number of times, specifically comprise the following steps that
Step 11.1, makes enumerator i=1;
Step 11.2, according to population PtIn each individuality select probability use roulette policy selection go out individualityAnd
Order is new individual
Step 11.3, makes neighborhood subscript RSI=(SEI-NK+Popsize) %Popsize, and wherein SEI represents roulette plan
Slightly selecting the subscript of individuality, % represents that complementation accords with;
Step 11.4, makes neighborhood optimum individualAnd make enumerator rt=1;
Step 11.5, makes neighborhood subscript RSI=(RSI+1) %Popsize;
Step 11.6, if individualThan individual RSBesttMore excellent, then makeOtherwise keep
RSBesttConstant;
Step 11.7, makes enumerator rt=rt+1;
Step 11.8, if rt is less than or equal to NK × 2, then forwards step 11.5 to, otherwise forwards step 11.9 to;
Step 11.9, randomly generates positive integer RD2 between [1, D];
Step 11.10, randomly generates positive integer RSN between [1, NK × 2], then makes random neighborhood subscript RNI
=(SEI-NK+RSN+Popsize) %Popsize;
Step 11.11, makes average
Step 11.12, makes standard deviationWherein abs represents and takes absolute value
Function;
Step 11.13, with GRMean as average, GRSD is that standard deviation produces a gaussian random real number RVal, if
The value of RVal is beyond [LBRD2,UBRD2Scope between], then use same method to regenerate gaussian random real number RVal,
Until the value of RVal is without departing from [LBRD2,UBRD2Scope between];
Step 11.14, randomly generates positive integer RI3 between [1, Popsize];
Step 11.15, makes average
Step 11.16, makes standard deviationWherein abs represents the letter taken absolute value
Number;
Step 11.17, with GBMean as average, GBSD is that standard deviation produces a gaussian random real number BVal, if
The value of BVal is beyond [LBRD2,UBRD2Scope between], then use same method to regenerate gaussian random real number BVal,
Until the value of BVal is without departing from [LBRD2,UBRD2Scope between];
Step 11.18, randomly generates a real number RNW between [0,1];
Step 11.19, order
Step 11.20, calculates new individual UtAdaptive value Fit (Ut), then at individualityWith new individual UtBetween perform
Select operation, and calculate individualityDo not improve number of times
Step 11.21, makes enumerator i=i+1;
Step 11.22, if enumerator i is less than or equal to Popsize, then forwards step 11.2 to, otherwise forwards step 12 to;
Step 12, makes Evaluation: Current number of times FEs=FEs+Popsize × 2;
Step 13, search bee finds out population PtIn do not improve the individuality that number of times is maximum, and this individuality of labelling isAs
Fruit is individualDo not improve number of times less than Limit, then forward step 14 to, otherwise to individualityCarry out random initializtion,
And make individualityThe number of times that do not improves be 0;
Step 14, preserves population PtMiddle optimum individual Bestt;
Step 15, makes current evolution algebraically t=t+1;
Step 16, repeats step 9 to step 15 until Evaluation: Current number of times FEs terminates after reaching MAX_FEs, will perform
The optimum individual Best obtained in journeytIt is decoded as connection weights and the bias of three layer perceptron neutral net, and will obtain
Three layer perceptron neutral net, as soft-sensing model, can realize the hard measurement of ore deposit rock intensity.
Specific embodiment described herein is only to present invention spirit explanation for example.Technology neck belonging to the present invention
Described specific embodiment can be made various amendment or supplements or use similar mode to replace by the technical staff in territory
Generation, but without departing from the spirit of the present invention or surmount scope defined in appended claims.
Claims (1)
1. the ore deposit rock intensity flexible measurement method that an adaptability artificial bee colony optimizes, it is characterised in that comprise the following steps:
Step 1, gathers RN ore deposit rock test specimen in the region needing hard measurement, and ore deposit rock test specimen is carried out experiment measures each
Water absorption rate, dry density, natural impedance, dynamical possion ratio, dynamic modulus of elasticity and the comprcssive strength of ore deposit rock test specimen, by the reality of ore deposit rock test specimen
Test data as sample data set;Then the sample data set collected is normalized;
Step 2, user's initiation parameter, described initiation parameter includes the individual of three layer perceptron neutral net hidden layer neuron
Number HN, Population Size Popsize, maximum does not improves number of times Limit, radius of neighbourhood NK, maximum evaluation number of times MAX_FEs;
Step 3, current evolution algebraically t=0, Evaluation: Current number of times FEs=0;
Step 4, the input variable making three layer perceptron neutral net is the normalized water absorption rate of ore deposit rock test specimen, dry density, ripple
Impedance, dynamical possion ratio, dynamic modulus of elasticity, and it is output as the normalized comprcssive strength of ore deposit rock test specimen, it is then determined that three layers of perception
The hidden layer of device neutral net and the transmission function of output layer, and calculate the optimal design parameter of three layer perceptron neutral net
Number D=HN × 7+1;
Step 5, random initializtion populationWherein: individual subscript i=1,2 ...,
Popsize;For population PtIn i-th individual and store three layer perceptron neutral net
D design parameter to be optimized, it randomly generates formula and is:
Wherein dimension subscript j=1,2 .., D;Rand (0,1) represents the function producing random real number between [0,1];
Step 6, calculates population PtIn each individualityAdaptive valueWherein individual subscript i=1,2 ...,
Popsize, individualAdaptive valueComputational methods be: by individualityIt is decoded as three layer perceptron neutral net
Connect weights and bias, and calculate three layer perceptron neutral net mean square error NE on sample data seti, then order
BodyAdaptive value
Step 7, makes population PtIn all individualities do not improve number of timesWherein individual subscript i=1,2 ...,
Popsize;
Step 8, preserves population PtIn optimum individual Bestt, then make Evaluation: Current number of times FEs=FEs+Popsize, and make
Average factor M NU=0.5;
Step 9, employs honeybee to perform adaptability search operation, specifically comprises the following steps that
Step 9.1, makes enumerator i=1, and makes zoom factor list SCFList for sky;
Step 9.2, order is new individual
Step 9.3, with MNU as average, the 0.1 gaussian random real number GRV produced for standard deviation, then make zoom factor
SCF=GRV × 2-1;
Step 9.4, randomly generates positive integer RD1 between [1, D];
Step 9.5, randomly generates two unequal positive integers RI1 and RI2 between [1, Popsize];
Step 9.6, order
Step 9.7, calculates new individual UtAdaptive value Fit (Ut);
Step 9.8, if new individual UtThan individualityMore excellent, then GRV is added in zoom factor list SCFList;
Step 9.9, at individualityWith new individual UtBetween perform select operation and update individualityDo not improve number of times
Step 9.10, makes enumerator i=i+1;
Step 9.11, if enumerator i is less than or equal to Popsize, then forwards step 9.2 to, otherwise forwards step 9.12 to;
Step 9.12, calculates meansigma methods MeanSCF of data in zoom factor list SCFList;
Step 9.13, randomly generates a real number RW between [0.8,1.0];
Step 9.14, makes MNU=RW × MNU+ (1-RW) × MeanSCF;
Step 9.15, forwards step 10 to;
Step 10, according to population PtThe adaptive value of middle individuality calculates the select probability of all individualities;
Step 11, observes honeybee according to population PtIn the select probability of each individuality select and individual perform adaptability Gaussian mutation behaviour
Make to generate new individual, then perform to select operation and calculate individuality do not improve number of times, specifically comprise the following steps that
Step 11.1, makes enumerator i=1;
Step 11.2, according to population PtIn each individuality select probability use roulette policy selection go out individualityAnd make new
Individual
Step 11.3, makes neighborhood subscript RSI=(SEI-NK+Popsize) %Popsize, and wherein SEI represents that roulette strategy selects
Selecting out the subscript of individuality, % represents that complementation accords with;
Step 11.4, makes neighborhood optimum individualAnd make enumerator rt=1;
Step 11.5, makes neighborhood subscript RSI=(RSI+1) %Popsize;
Step 11.6, if individualThan individual RSBesttMore excellent, then makeOtherwise keep RSBesttNo
Become;
Step 11.7, makes enumerator rt=rt+1;
Step 11.8, if rt is less than or equal to NK × 2, then forwards step 11.5 to, otherwise forwards step 11.9 to;
Step 11.9, randomly generates positive integer RD2 between [1, D];
Step 11.10, randomly generates positive integer RSN between [1, NK × 2], then makes random neighborhood subscript RNI=
(SEI-NK+RSN+Popsize) %Popsize;
Step 11.11, makes average
Step 11.12, makes standard deviationWherein abs represents the function taken absolute value;
Step 11.13, with GRMean as average, GRSD is that standard deviation produces a gaussian random real number RVal, if RVal
Value is beyond [LBRD2,UBRD2Scope between], then use same method to regenerate gaussian random real number RVal, until
The value of RVal is without departing from [LBRD2,UBRD2Scope between];
Step 11.14, randomly generates positive integer RI3 between [1, Popsize];
Step 11.15, makes average
Step 11.16, makes standard deviationWherein abs represents the function taken absolute value;
Step 11.17, with GBMean as average, GBSD is that standard deviation produces a gaussian random real number BVal, if BVal
Value is beyond [LBRD2,UBRD2Scope between], then use same method to regenerate gaussian random real number BVal, until
The value of BVal is without departing from [LBRD2,UBRD2Scope between];
Step 11.18, randomly generates a real number RNW between [0,1];
Step 11.19, order
Step 11.20, calculates new individual UtAdaptive value Fit (Ut), then at individualityWith new individual UtBetween perform selection
Operation, and calculate individualityDo not improve number of times
Step 11.21, makes enumerator i=i+1;
Step 11.22, if enumerator i is less than or equal to Popsize, then forwards step 11.2 to, otherwise forwards step 12 to;
Step 12, makes Evaluation: Current number of times FEs=FEs+Popsize × 2;
Step 13, search bee finds out population PtIn do not improve the individuality that number of times is maximum, and this individuality of labelling isIf it is individual
BodyDo not improve number of times less than Limit, then forward step 14 to, otherwise to individualityCarry out random initializtion, and make
IndividualThe number of times that do not improves be 0;
Step 14, preserves population PtMiddle optimum individual Bestt;
Step 15, makes current evolution algebraically t=t+1;
Step 16, repeats step 9 to step 15 until Evaluation: Current number of times FEs terminates after reaching MAX_FEs, during performing
The optimum individual Best obtainedtIt is decoded as connection weights and the bias of three layer perceptron neutral net, and three layers will obtained
Perceptron neural network, as soft-sensing model, can realize the hard measurement of ore deposit rock intensity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610585884.0A CN106228241B (en) | 2016-07-24 | 2016-07-24 | The ore-rock intensity flexible measurement method of adaptability artificial bee colony optimization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610585884.0A CN106228241B (en) | 2016-07-24 | 2016-07-24 | The ore-rock intensity flexible measurement method of adaptability artificial bee colony optimization |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106228241A true CN106228241A (en) | 2016-12-14 |
CN106228241B CN106228241B (en) | 2018-10-16 |
Family
ID=57532721
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610585884.0A Expired - Fee Related CN106228241B (en) | 2016-07-24 | 2016-07-24 | The ore-rock intensity flexible measurement method of adaptability artificial bee colony optimization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106228241B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106991246A (en) * | 2017-04-16 | 2017-07-28 | 江西理工大学 | The ore-rock intensity flexible measurement method of gravitation chess game optimization |
CN111931990A (en) * | 2020-07-13 | 2020-11-13 | 江西理工大学 | Power load prediction method based on optimized least square support vector machine |
CN111984943A (en) * | 2020-07-29 | 2020-11-24 | 南京信息工程大学 | DWT-SVD digital watermarking method based on artificial bee colony algorithm |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104462795A (en) * | 2014-11-25 | 2015-03-25 | 三峡大学 | Rheological model suitable for medium-and-long-term settlement deformation behaviors of rockfill dam |
CN105426920A (en) * | 2015-12-02 | 2016-03-23 | 江西理工大学 | Method for predicting pH value of stream in rare earth mining area based on cloud model and artificial bee colony optimization |
-
2016
- 2016-07-24 CN CN201610585884.0A patent/CN106228241B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104462795A (en) * | 2014-11-25 | 2015-03-25 | 三峡大学 | Rheological model suitable for medium-and-long-term settlement deformation behaviors of rockfill dam |
CN105426920A (en) * | 2015-12-02 | 2016-03-23 | 江西理工大学 | Method for predicting pH value of stream in rare earth mining area based on cloud model and artificial bee colony optimization |
Non-Patent Citations (1)
Title |
---|
杨琳,孔峰: "嵌入粒子群优化算法的混合人工蜂群算法", 《自动化仪表》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106991246A (en) * | 2017-04-16 | 2017-07-28 | 江西理工大学 | The ore-rock intensity flexible measurement method of gravitation chess game optimization |
CN111931990A (en) * | 2020-07-13 | 2020-11-13 | 江西理工大学 | Power load prediction method based on optimized least square support vector machine |
CN111931990B (en) * | 2020-07-13 | 2022-03-08 | 江西理工大学 | Power load prediction method based on optimized least square support vector machine |
CN111984943A (en) * | 2020-07-29 | 2020-11-24 | 南京信息工程大学 | DWT-SVD digital watermarking method based on artificial bee colony algorithm |
CN111984943B (en) * | 2020-07-29 | 2023-08-22 | 南京信息工程大学 | DWT-SVD digital watermarking method based on artificial bee colony algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN106228241B (en) | 2018-10-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104632521B (en) | A kind of wind power optimization system and method based on drift correction | |
Yan et al. | Predicting permeability changes with injecting CO2 in coal seams during CO2 geological sequestration: A comparative study among six SVM-based hybrid models | |
DG et al. | Differential evolution algorithm with application to optimal operation of multipurpose reservoir | |
CN103018673A (en) | Method for predicating life of aerospace Ni-Cd storage battery based on improved dynamic wavelet neural network | |
CN106228241A (en) | The ore deposit rock intensity flexible measurement method that adaptability artificial bee colony optimizes | |
Zhao et al. | Improved multiple-objective dynamic programming model for reservoir operation optimization | |
CN105426920A (en) | Method for predicting pH value of stream in rare earth mining area based on cloud model and artificial bee colony optimization | |
CN107038516A (en) | Complex Fault Block Oil Reservoir water flooding effectiveness quantitative evaluation method is oozed in one kind | |
Liu et al. | A systems dynamic model of a coal-based city with multiple adaptive scenarios: A case study of Ordos, China | |
CN109308544A (en) | Based on to sdpecific dispersion-shot and long term memory network cyanobacterial bloom prediction technique | |
CN106645620B (en) | Using the rare-earth mining area farmland water body BOD flexible measurement methods of mixing differential evolution | |
CN115980826A (en) | Rock burst intensity prediction method based on weighted meta-heuristic combined model | |
CN105930685B (en) | The rare-earth mining area underground water ammonia nitrogen concentration Forecasting Methodology of Gauss artificial bee colony optimization | |
CN106650028A (en) | Optimization method and system based on agile satellite design parameters | |
CN106339573B (en) | The rare-earth mining area underground water total nitrogen concentration flexible measurement method of artificial bee colony optimization | |
CN105512383A (en) | Dredging process regulation and control parameter screening method based on BP neural network | |
CN113393051A (en) | Power distribution network investment decision method based on deep migration learning | |
Bani-Hani et al. | Prediction of energy gains from Jordanian wind stations using artificial neural network | |
CN102854299B (en) | Ore rock intensity prediction method based on component thermodynamic gene expression programming | |
CN109193779A (en) | A kind of distributed wind-power generator maximum capacity appraisal procedure | |
Wang et al. | Optimal reservoir operation using PSO with adaptive random inertia weight | |
Wang et al. | CNN Based Fault Recognition with Multi-Scale Fusion Attention Mechanism | |
Jihong et al. | Groundwater table prediction based on improved PSO Algorithm and RBF Neural Network | |
CN109858127A (en) | Cyanobacterial bloom prediction technique based on recurrence sequential depth confidence network | |
Zhang et al. | Parameters Optimization of SVM Based on Improved FOA and Its Application in Fault Diagnosis. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181016 |