CN102854299B - Ore rock intensity prediction method based on component thermodynamic gene expression programming - Google Patents
Ore rock intensity prediction method based on component thermodynamic gene expression programming Download PDFInfo
- Publication number
- CN102854299B CN102854299B CN201210261469.1A CN201210261469A CN102854299B CN 102854299 B CN102854299 B CN 102854299B CN 201210261469 A CN201210261469 A CN 201210261469A CN 102854299 B CN102854299 B CN 102854299B
- Authority
- CN
- China
- Prior art keywords
- population
- individual
- ore deposit
- individuality
- gene expression
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an ore rock intensity prediction method based on component thermodynamic gene expression programming. With a provided component thermodynamic gene expression programming algorithm, the invention adopts a water absorption rate, a dry density, wave impedance, a dynamic Poisson's ratio, and a dynamic elastic modulus as input variables, adopts compressive strength as an output variable, automatically and intelligently digs out a mathematical model of the ore rock intensity, and thus predicts the compressive strength of the ore rock. The invention can quantitatively harmonize the balance between a selected pressure and population diversity in the gene expression programming, and thus improves the rate of convergence, solving precision and algorithmic stability of traditional gene expression programming when applied to the prediction of ore rock intensity.
Description
Technical field
The present invention relates to a kind of ore deposit rock intensity prediction method, especially relate to a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming.
Background technology
Ore deposit rock strength problem is the basic problem in Mineral Engineering, but needs to carry out a large amount of site tests due to traditional ore deposit rock intensity prediction method, thus causes manpower, fund etc. sharply to increase.By the restriction of the condition such as fund, equipment in Practical Project practice, often a large amount of site tests cannot be carried out.Therefore how predicting ore deposit rock intensity efficiently and accurately, is the major issue that many engineering staffs extremely pay close attention to.At present, the Forecasting Methodology for ore deposit rock intensity has a lot, mainly can be divided into: mathematical physics Forecasting Methodology and Intelligent Forecasting.Mathematical physics Forecasting Methodology needs engineering staff to grasp many professional knowledge, and therefore universality is not very strong.Intelligent Forecasting is then fusion calculation machine science and technology, especially Intelligent Computation Technology and the one developed is simple, grasp a lot of domain knowledges without the need to engineering staff, and there is flexible, highly versatile, the advantages such as complicated and diversified Practical Project demand can be met.Therefore Intelligent Forecasting has broad prospects, and is the focus of current ore deposit rock prediction of strength research.
At present, the Intelligent Forecasting mainly neural network of ore deposit rock intensity, the methods such as support vector machine.But these methods also exist a lot of deficiency, Practical Project effect is not very desirable.The subject matter that the method for neural network and support vector machine exists needs collection ore deposit rock test specimen quantity more, and when the easy overfitting of ore deposit rock test specimen negligible amounts, the model accuracy obtained is very limited, often cannot reach Practical Project requirement.And when ore deposit rock test specimen quantity is more, the increase such as manpower, fund can be caused on the one hand; Too increase the complicacy of Algorithm Learning process on the other hand, thus cause learning time long.Can see related documents: based on the ultrasonic Prediction of the ore deposit rock intensity index of particle swarm support vector machine. in recent years, there is gene expression programming in developing rapidly of Intelligent Computation Technology.Gene expression programming is the effective intelligent computation method of one of the simulation natural selection of Darwinian evolutionism and the biological evolution process of genetic mechanisms, it adopts the linear string representation solution of regular length, therefore it have succinctly, the advantage such as high-performance and strong robustness, be successfully applied in numerous Practical Project fields.But find in Practical Project practice, when traditional gene expression programming is applied to ore deposit rock prediction of strength, there is the problem that speed of convergence is absorbed in local optimum slowly and easily.The reason of this two problems is due in the evolution operating process of traditional gene expression programming to a great extent, the balance between selection pressure and population diversity cannot be coordinated quantitatively, thus easily cause selection pressure and population diversity to occur arbitrarily shake, have impact on speed of convergence and the solving precision of traditional gene expression programming.When traditional gene expression programming is applied to ore deposit rock prediction of strength, selection pressure and population diversity are conflicting between the two.Under normal conditions, when selection pressure is excessive, individuality close to current optimum individual in population is more, the average adaptive value of population is more outstanding, gene expression programming speed of convergence can be made to accelerate, but most individuality in population can be caused all to trend towards near current optimum individual, and population diversity is deteriorated, increase the probability that algorithm is absorbed in local optimum; When selection pressure is too small, although individual distribution in population can be made to be tending towards dispersion, population diversity improves, and increases the probability of algorithm convergence to globally optimal solution, the speed of convergence of the gene expression programming that can slow down like this.At present, the achievement in research how coordinating quantitatively to balance between the selection pressure of gene expression programming and population diversity also lacks very much.
Summary of the invention
The present invention mainly solves the technical matters existing for prior art; Provide a kind of balance coordinated quantitatively in gene expression programming between selection pressure and population diversity, to improve the stability of the speed of convergence of traditional gene expression programming, solving precision and algorithm.Utilize the component thermodynamic gene expression programming of proposition with the water-intake rate of ore deposit rock test specimen, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity for input variable, compressive strength is output variable, automated intelligent ground excavates the mathematical model of ore removal rock intensity, thus a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming of the compressive strength of prediction ore deposit rock.
Above-mentioned technical matters of the present invention is mainly solved by following technical proposals:
Based on an ore deposit rock intensity prediction method for component thermodynamic gene expression programming, it is characterized in that, comprise the following steps:
Step 1, gathers N number of ore deposit rock sample originally, and carries out testing each ore deposit rock sample of rear acquisition test figure originally for N number of ore deposit rock sample water-intake rate originally, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity and compressive strength; And rock sample test figure originally in N number of ore deposit is designated as matrix A;
Step 2, User Defined initiation parameter, described initiation parameter comprises Population Size PS, sub-Population Size M, maximum evaluation number of times MAX_FE, scale factor, number of degrees K, Markov chain length LK, initial temperature T0, functor and terminal symbol, mrna length, gene number, mutation probability, insert string probability, insert string length and recombination probability;
Step 3, makes current evolution algebraically t=0; Temperature descending factors k=0; Temperature T=T0;
Step 4, produces initialization population P
t, be decoded into mathematic(al) representation to the chromosome of each individuality, and utilize matrix A to evaluate the adaptive value of each individuality, wherein water-intake rate, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity are input variable, and compressive strength is output variable; Then preserve optimum individual, and calculated for the 0th generation enliven window W
0;
Step 5, by performing the selection of gene expression programming, variation, inserting string, recombination operator to population P
tin PS individual generate M new individual, and M new group of individuals is made into sub-population O
t, to O
tin each individuality carry out adaptive value evaluation; Then the individuality preserving adaptive value maximum is optimum individual;
Step 6, by population P
tin PS individuality and sub-population O
tin each and every one soma of M become interim population P '
t, what then calculate t+1 generation enlivens window W
t+1, and calculate interim population P '
tin the free energy component of each individuality, then it is individual to find out maximum front M of free energy component value, then delete this M individual, obtain the population P of new generation be made up of PS individuality
t+1;
Step 7, repeat step 5 to step 6 until evaluation number of times terminates after reaching MAX_FE, the chromosome of the optimum individual obtained in implementation is decoded into mathematic(al) representation just can obtain with water-intake rate, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity as input variable, compressive strength is the ore deposit rock intensity mathematical model of output variable, utilizes the ore deposit rock intensity mathematical model obtained just can predict the compressive strength of ore deposit rock.
In above-mentioned a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming, the concrete operation step of described step 4 is as follows:
Mathematic(al) representation is decoded into the chromosome of each individuality, and the adaptive value utilizing matrix A evaluation every individual, and to preserve the maximum individuality of adaptive value be optimum individual, if the chromosome of any individual j is decoded into mathematic(al) representation be designated as f
j, its adaptive value computing formula is:
Wherein, N is ore deposit rock total sample number, A
i1, A
i2, A
i3, A
i4, A
i5, A
i6, be respectively the i-th ore deposit rock sample water-intake rate originally, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity and the compressive strength that store in matrix A, the criterion of optimum individual is: the individuality that adaptive value is maximum in all individualities.
In above-mentioned a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming, the concrete operation step in described step 5 is as follows:
Step 5.1, judges whether Evaluation: Current number of times the maximum evaluation number of times MAX_FE such as is greater than, if then forward step 7 to, otherwise performs following steps;
Step 5.2, i=0; Wherein, i is temporary variable, is register;
Step 5.3, judges whether i is more than or equal to Markov chain length LK, if then perform temperature descending factors k=k+1; Current Temperatures T=T/ (1+k), rear execution step 5.1, otherwise perform following steps;
Step 5.4, generates M by the operator such as selection, variation, slotting string, restructuring performing gene expression programming individual new individual;
Step 5.5, is made into sub-population O by M new group of individuals
t, then press formula:
Calculate O
tin the adaptive value of each individuality, and to preserve the maximum individuality of adaptive value be optimum individual.
In above-mentioned a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming, the concrete operation step of described step 6 is as follows:
Step 6.1, what calculate t+1 generation enlivens window W
t+1; And make interim population P '
t=P
t∪ O
t; , wherein P
tcurrent population, O
tsub-population:
Step 6.2, calculates P '
tin PS+M individual relative energy;
Step 6.3, according to the relative energy calculated in step 6.2, calculates P '
tin PS+M individual free energy component;
Step 6.4, from P '
tin to find out free energy component maximum front M individual;
Step 6.5, has the individuality of maximum free energy component from P ' by the M found out in step 6.4
tmiddle deletion;
Step 6.6, current evolution algebraically t=t+1; , new population P of future generation
t=P '
t; I=i+1, rear execution step 5.3.
In above-mentioned a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming, in described step 6.2, the relative energy method calculating each individuality is as follows:
wherein F (X) the adaptive value function that is individual X, and its characteristic is that individuality is more excellent, then adaptive value is larger.
In above-mentioned a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming, in described step 6.1, what calculate t generation enlivens window W
tmethod as follows:
As t=0, W
0=[l
0, u
0], wherein:
L
0=min{-F (X) | X ∈ P
0, u
0=max{-F (X) | X ∈ P
0; As t>0, if W
t-1=[l
t-1, u
t-1], and t is for sub-population: O
t(X
n+1, X
n+2..., X
n+M) ∈ S, then W
t=[l
t, u
t], wherein:
l
t=min(l
t-1,min{-F(X)|X∈O
t}),u
t=max(u
t-1,max{-F(X)|X∈O
t})。
In above-mentioned a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming, in described step 6.3, calculate individual free energy components method as follows:
Wherein T is Current Temperatures, and individual X is at population P
tgrade be b, population P
tin fall into W
tb grade
in individual amount be n
b, and
Wherein, a is scale factor, and K is number of degrees.
Therefore, tool of the present invention has the following advantages: by the selection pressure in gene expression programming with population is various is mapped as energy in thermodynamics and entropy, based on the principle of the minimum law of free energy, select in several individual replicates to population of new generation and carry out evolution operation, the free energy minimization of population of new generation is made by this system of selection, and the individuality of the population of new generation that the free energy minimization of population of new generation namely chooses is optimum as far as possible, the many property of population are as well as possible simultaneously, thus the balance coordinated quantitatively in gene expression programming between selection pressure and population diversity, to improve the speed of convergence of traditional gene expression programming, the stability of solving precision and algorithm.Utilize the component thermodynamic gene expression programming of proposition with the water-intake rate of ore deposit rock test specimen, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity for input variable, compressive strength is output variable, automated intelligent ground excavates the mathematical model of ore removal rock intensity, thus the compressive strength of prediction ore deposit rock.
Accompanying drawing explanation
Fig. 1 is the individual method schematic diagram being decoded into mathematic(al) representation in the present invention.
Fig. 2 is the calculation process schematic diagram of individual freedom energy component in the present invention.
Embodiment
Below by embodiment, and by reference to the accompanying drawings, technical scheme of the present invention is described in further detail.
Embodiment:
Step 1, collecting quantity is the ore deposit rock sample basis of 15-30, the campaigns such as line density of going forward side by side test, triaxial test, supersonic test, obtain each ore deposit rock sample test figure originally, mainly comprise water-intake rate, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity and compressive strength, the test figure obtained is designated as matrix A, if any row i in matrix A, is designated as A
i, its value is six attributes of i-th ore deposit rock test specimen: water-intake rate, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity and compressive strength.
Step 2, initiation parameter: Population Size PS=100, maximum evaluation number of times MAX_FE=3000000, scale factor=2, number of degrees K=20, Markov chain length LK=100, initial temperature T0=10, functor=+,-, *, /, P, Q, S, C, L, E} wherein P representative square, Q represents extraction of square root, S represents sin function, C represents cos function, L represents log function, E represents exp function, terminal symbol={ a, b, c, d, e} wherein a represents water-intake rate, b represents dry density, c represents wave impedance, d represents dynamical possion ratio, e represents dynamic modulus of elasticity, mrna length=21, gene number=3, mutation probability=0.06, insert string probability=0.1, insert string length=3, recombination probability=0.3,
Step 3, produces initialization population P
0, by the method shown in Fig. 1, mathematic(al) representation is decoded into the chromosome of each individuality, and utilizes the every individual adaptive value of matrix A evaluation, and preserve optimum individual, if the chromosome of any individual j is decoded into mathematic(al) representation be designated as f
j, its adaptive value computing formula is:
Step 4, t=0, k=0, T=T0;
Step 5, by formula W
0=[min{-F (X) | X ∈ P
0, max{-F (X) | X ∈ P
0], what calculated for the 0th generation enlivens window W
0;
Step 6, judges whether Evaluation: Current number of times the maximum evaluation number of times MAX_FE such as is greater than, if then forward step 20 to, otherwise forwards step 7 to;
Step 7, i=0;
Step 8, judges whether i the Markov chain length LK such as is greater than, if then forward step 18 to, otherwise forwards step 9 to;
Step 9, generates M by the operator such as selection, variation, slotting string, restructuring performing gene expression programming individual new individual;
Step 10, is made into sub-population O by M new group of individuals
t, then press formula:
Calculate O
tin the adaptive value of each individuality, and preserve optimum individual;
Step 11, what calculate t+1 generation enlivens window W
t+1, computing formula is:
W
t+1=[l
t+1, u
t+1], wherein:
l
t+1=min(l
t,min{-F(X)|X∈O
t})
u
t+1=max(u
t,max{-F(X)|X∈O
t});
Step 12, P '
t=P '
t∪ O
t;
Step 13, by formula:
Calculate P '
tin PS+M individual relative energy;
Step 14, calculates P '
tin PS+M individual free energy component, computing formula is:
Step 15, from P '
tbefore middle deletion, M has the individuality of maximum free energy component;
Step 16, t=t+1, P
t=P '
t;
Step 17, i=i+1, forwards step 8 to;
Step 18, k=k+1;
Step 19, T=T/ (1+k), forwards step 6 to;
Step 20, the chromosome of optimum individual is decoded into mathematic(al) representation by the method shown in Fig. 1 just can obtain with water-intake rate, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity as input variable, compressive strength is the ore deposit rock intensity mathematical model of output variable, utilizes the ore deposit rock intensity mathematical model obtained just can predict the compressive strength of ore deposit rock.
Specific embodiment described herein is only to the explanation for example of the present invention's spirit.Those skilled in the art can make various amendment or supplement or adopt similar mode to substitute to described specific embodiment, but can't depart from spirit of the present invention or surmount the scope that appended claims defines.
Claims (7)
1., based on an ore deposit rock intensity prediction method for component thermodynamic gene expression programming, it is characterized in that, comprise the following steps:
Step 1, gathers N number of ore deposit rock sample originally, and carries out testing each ore deposit rock sample of rear acquisition test figure originally for N number of ore deposit rock sample water-intake rate originally, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity and compressive strength; And rock sample test figure originally in N number of ore deposit is designated as matrix A;
Step 2, User Defined initiation parameter, described initiation parameter comprises Population Size PS, sub-Population Size M, maximum evaluation number of times MAX_FE, scale factor, number of degrees K, Markov chain length LK, initial temperature T0, functor and terminal symbol, mrna length, gene number, mutation probability, insert string probability, insert string length and recombination probability;
Step 3, makes current evolution algebraically t=0; Temperature descending factors k=0; Temperature T=T0;
Step 4, produces initialization population P
t, be decoded into mathematic(al) representation to the chromosome of each individuality, and utilize matrix A to evaluate the adaptive value of each individuality, wherein water-intake rate, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity are input variable, and compressive strength is output variable; Then preserve optimum individual, and calculated for the 0th generation enliven window W
0;
Step 5, generates M new individuality after performing the selection of gene expression programming, variation, slotting string, recombination operator successively, this M is individual new individual by population P
tin PS individual to generate; And M new group of individuals is made into sub-population O
t, to O
tin each individuality carry out adaptive value evaluation; Then the individuality preserving adaptive value maximum is optimum individual;
Step 6, by population P
tin PS individuality and sub-population O
tin each and every one soma of M become interim population P '
t, what then calculate t+1 generation enlivens window W
t+1, and calculate interim population P '
tin the free energy component of each individuality, then it is individual to find out maximum front M of free energy component value, then delete this M individual, obtain the population P of new generation be made up of PS individuality
t+1;
Step 7, repeat step 5 to step 6 until evaluation number of times terminates after reaching MAX_FE, the chromosome of the optimum individual obtained in implementation is decoded into mathematic(al) representation just can obtain with water-intake rate, dry density, wave impedance, dynamical possion ratio, dynamic modulus of elasticity as input variable, compressive strength is the ore deposit rock intensity mathematical model of output variable, utilizes the ore deposit rock intensity mathematical model obtained just can predict the compressive strength of ore deposit rock.
2. a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming according to claim 1, it is characterized in that, the concrete operation step of described step 4 is as follows:
Mathematic(al) representation is decoded into the chromosome of each individuality, and the adaptive value utilizing matrix A evaluation every individual, and to preserve the maximum individuality of adaptive value be optimum individual, if the chromosome of any individual j is decoded into mathematic(al) representation be designated as f
j, its adaptive value computing formula is:
3. a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming according to claim 1, it is characterized in that, the concrete operation step in described step 5 is as follows:
Step 5.1, judges whether Evaluation: Current number of times is more than or equal to maximum evaluation number of times MAX_FE, if then forward step 7 to, otherwise performs following steps;
Step 5.2i=0; Wherein, i is temporary variable, is register;
Step 5.3, judges whether i is more than or equal to Markov chain length LK, if then perform temperature descending factors k=k+1; Current Temperatures T=T/ (1+k), rear execution step 5.1, otherwise perform following steps;
Step 5.4, by performing the selection of gene expression programming, variation, insert string, recombination operator generate M new individual;
Step 5.5, is made into sub-population O by M new group of individuals
t, then press formula:
Calculate O
tin the adaptive value of each individuality, and to preserve the maximum individuality of adaptive value be optimum individual.
4. a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming according to claim 1, it is characterized in that, the concrete operation step of described step 6 is as follows:
Step 6.1, what calculate t+1 generation enlivens window W
t+1; And make interim population P '
t=P
t∪ O
t; , wherein P
tcurrent population, O
tsub-population:
Step 6.2, calculates P '
tin PS+M individual relative energy;
Step 6.3, according to the relative energy calculated in step 6.2, calculates P '
tin PS+M individual free energy component;
Step 6.4, from P '
tin to find out free energy component maximum front M individual;
Step 6.5, has the individuality of maximum free energy component from P ' by the M found out in step 6.4
tmiddle deletion;
Step 6.6, current evolution algebraically t=t+1; , new population P of future generation
t=P '
t; I=i+1, rear execution step 5.3.
5. a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming according to claim 4, it is characterized in that, in described step 6.2, the relative energy method calculating each individuality is as follows:
wherein F (X) the adaptive value function that is individual X, and its characteristic is that individuality is more excellent, then adaptive value is larger.
6. a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming according to claim 4, it is characterized in that, in described step 6.1, what calculate t generation enlivens window W
tmethod as follows:
As t=0, W
0=[l
0, u
0], wherein:
L
0=min{-F (X) | X ∈ P
0, u
0=max{-F (X) | X ∈ P
0; As t>0, if W
t-1=[l
t-1, u
t-1], and t is for sub-population: O
t(X
n+1, X
n+2..., X
n+M) ∈ S, then W
t=[l
t, u
t], wherein:
l
t=min(l
t-1,min{-F(X)|X∈O
t}),u
t=max(u
t-1,max{-F(X)|X∈O
t})。
7. a kind of ore deposit rock intensity prediction method based on component thermodynamic gene expression programming according to claim 4, is characterized in that, in described step 6.3, calculates individual free energy components method as follows:
Wherein, T is Current Temperatures, and individual X is at population P
tgrade be b, population P
tin fall into W
tb grade
in individual amount be n
b, and
Wherein, a is scale factor, and K is number of degrees.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210261469.1A CN102854299B (en) | 2012-07-26 | 2012-07-26 | Ore rock intensity prediction method based on component thermodynamic gene expression programming |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210261469.1A CN102854299B (en) | 2012-07-26 | 2012-07-26 | Ore rock intensity prediction method based on component thermodynamic gene expression programming |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102854299A CN102854299A (en) | 2013-01-02 |
CN102854299B true CN102854299B (en) | 2014-12-17 |
Family
ID=47401066
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210261469.1A Expired - Fee Related CN102854299B (en) | 2012-07-26 | 2012-07-26 | Ore rock intensity prediction method based on component thermodynamic gene expression programming |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102854299B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105781536B (en) * | 2014-12-16 | 2019-01-18 | 中国石油天然气股份有限公司 | Method for measuring and calculating porosity of petroleum reservoir |
CN105243193B (en) * | 2015-09-16 | 2018-02-02 | 三峡大学 | A kind of method for determining creep test prism test specimen compression strength conversion factor |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1214757A (en) * | 1996-03-25 | 1999-04-21 | 装饰工业公司 | Method of assaying compressive strength of rock |
CN1296170A (en) * | 1999-11-16 | 2001-05-23 | 王晓利 | Concrete and rock strength home position testing method and instrument |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060200436A1 (en) * | 2005-03-07 | 2006-09-07 | Chi Zhou | Gene expression programming with enhanced preservation of attributes contributing to fitness |
US7526385B2 (en) * | 2007-06-22 | 2009-04-28 | Schlumberger Technology Corporation | Method, system and apparatus for determining rock strength using sonic logging |
-
2012
- 2012-07-26 CN CN201210261469.1A patent/CN102854299B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1214757A (en) * | 1996-03-25 | 1999-04-21 | 装饰工业公司 | Method of assaying compressive strength of rock |
CN1296170A (en) * | 1999-11-16 | 2001-05-23 | 王晓利 | Concrete and rock strength home position testing method and instrument |
Non-Patent Citations (5)
Title |
---|
Evaluating the strength of intact rocks through genetic programming;M. Asadi等;《Applied Soft Computing》;20110331;第11卷(第2期);第1932-1937页 * |
Prediction of compressive and tensile strength of limestone via genetic programming;A. Baykasoglu等;《Expert Systems with Applications》;20080830;第35卷(第1-2期);第111-123页 * |
一种基于分量热力学迁移策略的并行多种群 GEP;郭肇禄等;《四川大学学报(工程科学版)》;20120331;第44卷(第2期);第83-90页 * |
基于模拟退火的并行基因表达式编程算法研究;蒋思伟等;《电子学报》;20051130;第33卷(第11期);第2017-2021页 * |
基于粒子群支持向量机的矿岩强度指标的超声预测;邱景平等;《东北大学学报(自然科学版)》;20120531;第33卷(第5期);第731-734页 * |
Also Published As
Publication number | Publication date |
---|---|
CN102854299A (en) | 2013-01-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ye et al. | Predicting electricity consumption in a building using an optimized back-propagation and Levenberg–Marquardt back-propagation neural network: Case study of a shopping mall in China | |
Moonchai et al. | Short-term forecasting of renewable energy consumption: Augmentation of a modified grey model with a Kalman filter | |
Ding et al. | Application of a novel structure-adaptative grey model with adjustable time power item for nuclear energy consumption forecasting | |
CN110363344B (en) | Probability integral parameter prediction method for optimizing BP neural network based on MIV-GP algorithm | |
Tang et al. | How effective and efficient are multiobjective evolutionary algorithms at hydrologic model calibration? | |
Yu et al. | A hybrid procedure for energy demand forecasting in China | |
CN103514457B (en) | The multi-target improvement differential evolution model of Land use structure type when Ecology Restriction | |
Yu et al. | Solar photovoltaic model parameter estimation based on orthogonally-adapted gradient-based optimization | |
Xavier et al. | Orthogonal learning-based Gray Wolf Optimizer for identifying the uncertain parameters of various photovoltaic models | |
Sogabe et al. | Optimization of decentralized renewable energy system by weather forecasting and deep machine learning techniques | |
CN106651023A (en) | Grey correlation analysis-based improved fireworks algorithm mid-long term load prediction method | |
CN105335619A (en) | Collaborative optimization method applicable to parameter back analysis of high calculation cost numerical calculation model | |
Lu et al. | A multi-objective optimizer-based model for predicting composite material properties | |
Dyczko | Real-time forecasting of key coking coal quality parameters using neural networks and artificial intelligence | |
CN114925845A (en) | Machine learning construction method embedded with atomic potential function | |
CN104732067A (en) | Industrial process modeling forecasting method oriented at flow object | |
Yousri et al. | An efficient photovoltaic modeling using an Adaptive Fractional-order Archimedes Optimization Algorithm: Validation with partial shading conditions | |
Mohammad et al. | Short term load forecasting using deep neural networks | |
Wang et al. | Improved surrogate-assisted whale optimization algorithm for fractional chaotic systems’ parameters identification | |
CN102854299B (en) | Ore rock intensity prediction method based on component thermodynamic gene expression programming | |
Shashikant et al. | Development of an optimal operating policy of multi-reservoir systems in Mahanadi Reservoir Project Complex, Chhattisgarh | |
Xu et al. | A class of multi-objective equilibrium chance maximization model with twofold random phenomenon and its application to hydropower station operation | |
CN113393051A (en) | Power distribution network investment decision method based on deep migration learning | |
CN105809286A (en) | Incremental SVR load prediction method based on representative data reconstruction | |
Vega Zuñiga et al. | Evaluation of eleven numerical methods for determining weibull parameters for wind energy generation in the Caribbean Region of Colombia |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141217 Termination date: 20150726 |
|
EXPY | Termination of patent right or utility model |