CN113777925A - Method and system for determining content of rare earth extraction component - Google Patents
Method and system for determining content of rare earth extraction component Download PDFInfo
- Publication number
- CN113777925A CN113777925A CN202111067887.2A CN202111067887A CN113777925A CN 113777925 A CN113777925 A CN 113777925A CN 202111067887 A CN202111067887 A CN 202111067887A CN 113777925 A CN113777925 A CN 113777925A
- Authority
- CN
- China
- Prior art keywords
- component
- content
- population
- organic phase
- individuals
- 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.)
- Pending
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 150
- 238000000034 method Methods 0.000 title claims abstract description 59
- 229910052761 rare earth metal Inorganic materials 0.000 title claims abstract description 40
- 150000002910 rare earth metals Chemical class 0.000 title claims abstract description 36
- 239000012074 organic phase Substances 0.000 claims abstract description 123
- 238000005406 washing Methods 0.000 claims abstract description 100
- 238000000926 separation method Methods 0.000 claims abstract description 99
- 239000012071 phase Substances 0.000 claims abstract description 71
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 70
- 238000005457 optimization Methods 0.000 claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims description 115
- 239000008346 aqueous phase Substances 0.000 claims description 47
- 238000012360 testing method Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000035772 mutation Effects 0.000 claims description 10
- 239000000126 substance Substances 0.000 claims description 7
- 101150036841 minJ gene Proteins 0.000 claims description 6
- 230000009977 dual effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 13
- 238000011165 process development Methods 0.000 abstract description 2
- 238000005215 recombination Methods 0.000 abstract description 2
- 230000006798 recombination Effects 0.000 abstract description 2
- 230000000739 chaotic effect Effects 0.000 description 10
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 101100134058 Caenorhabditis elegans nth-1 gene Proteins 0.000 description 1
- 229910052684 Cerium Inorganic materials 0.000 description 1
- 229910052779 Neodymium Inorganic materials 0.000 description 1
- 229910052777 Praseodymium Inorganic materials 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003599 detergent Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000008775 paternal effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Abstract
The invention discloses a method and a system for determining the content of rare earth extraction components, wherein an optimized objective function is solved by utilizing an improved standard differential evolution algorithm, the solved actual energy efficiency separation coefficient is respectively substituted into a washing section water phase component content determination model and an extraction section organic phase component content determination model which accord with the actual working conditions, and the content of each component in the washing section organic phase and the content of each component in the extraction section water phase are respectively obtained, so that the calculated content of each component is closer to the content of each component in each stage detected by an actual factory, and important references are provided for new process development, the process flow recombination of the existing rare earth extraction process and the re-optimization of process parameters, and the method and the system have important practical significance.
Description
Technical Field
The invention relates to the technical field of extraction process optimization, in particular to a method and a system for determining the content of rare earth extraction components.
Background
The rare earth resources in China are rich, and the rare earth extraction process is in the advanced level in the world. When a factory develops a new process, a liquid separation funnel method or a mechanism model is generally adopted when calculating the stages required by the process, the design is more ideal, and some stages are added on the basis of calculating the stages in the actual factory building process. However, the energy efficiency problem of the extraction tank is not considered in the actual production process, so the calculated component contents of all levels can lag behind several levels or even dozens of levels relatively, and the difference from the actual process is large. For example, the theoretical calculation shows that the component content of 20 stages is A, and in the actual production process, the component content of the extraction tank with 26 stages is A. Obviously, the parameters of the designed optimal process do not guide the actual production.
Disclosure of Invention
The invention aims to provide a method and a system for determining the content of rare earth extraction components so as to improve the accuracy of predicting the content of the rare earth extraction components.
In order to achieve the above object, the present invention provides a method for determining a content of a rare earth extraction component, the method comprising:
step S1: constructing a model of the content of each component in the water phase of the washing section and a model of the content of each component in the organic phase of the extraction section;
step S2: constructing an optimization objective function based on a determination model of the content of each component in the water phase of the washing section and a determination model of the content of each component in the organic phase of the extraction section by adopting a least square method;
step S3: solving the optimized objective function by adopting an improved standard differential evolution algorithm to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section;
step S4: substituting actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section into a determination model of the content of each component in the water phase of the washing section to obtain the content of each component in the organic phase of the washing section; and substituting the actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section into the determination model of the content of each component in the organic phase of the extraction section to obtain the content of each component in the aqueous phase of the extraction section.
Optionally, the step of solving the optimized objective function by using an improved standard differential evolution algorithm to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section specifically includes:
step S31: initializing parameters;
step S32: determining an initial population obtained by the G generation evolution population; the initial population comprises NPsGIndividual population;
step S33: carrying out variation on target vectors corresponding to various group individuals in the initial population by adopting a double variation strategy method to obtain variation vectors corresponding to various group individuals;
step S34: performing two-term cross operation on target vectors and variation vectors corresponding to various group individuals in the initial population to obtain test vectors corresponding to various group individuals in the initial population;
step S35: determining next generation population individuals based on the fitness value of the test vector and the fitness value of the target vector by adopting a greedy selection mode, and storing various population individuals to an initial population;
step S36: judging whether G is larger than or equal to the maximum population evolution algebra Maxgem; if G is greater than or equal to Maxgem, executing step S37; if G is smaller than Maxgem, making G equal to G +1, and returning to the step S33;
step S37: substituting target vectors corresponding to various population individuals in the initial population into an optimization target function, and taking the target vectors corresponding to the population individuals with the minimum fitness value as actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section and the content of each component in the organic phase of the extraction section.
Optionally, the specific formula of the determination model for the content of each component in the organic phase at the extraction section is as follows:
the concrete formula of the determination model of the content of each component in the water phase of the washing section is as follows:
wherein, YciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckThe actual energy efficiency separation coefficient corresponding to the k component in the organic phase of the extraction section is shown, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicating the content of the ith component of the organic phase outlet.
Optionally, the optimization objective function comprises an objective function in the organic phase of the extraction section and an objective function in the aqueous phase of the washing section;
the specific formula of the objective function in the organic phase of the extraction section is as follows:
the specific formula of the target function in the water phase of the washing section is as follows:
wherein J represents the square sum of the difference between the content of each component in the organic phase of the extraction section and the actual plant data, W represents the square sum of the difference between the content of each component in the aqueous phase of the washing section and the actual plant data, minJ and minW are the minimum values of J and W, respectively, and Y is the minimum value ofciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckRepresents the corresponding fact of the kth component in the organic phase of the extraction sectionThe energy efficiency separation coefficient, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicates the content of the ith component of the organic phase outlet,
and
respectively representing the content of the ith component in an organic phase of an extraction section and an aqueous phase of a washing section obtained in an actual plant.
Optionally, the target vectors corresponding to the various group individuals in the initial population are mutated by using a double mutation strategy method to obtain the mutation vectors corresponding to the various group individuals, and a specific calculation formula is as follows:
wherein the content of the first and second substances,
representing variation vectors corresponding to the nth population individuals,
representing the target vector corresponding to the nth population of individuals, FnRepresenting the scaling factor corresponding to the nth population individual,
the expression is randomly selected from the first NP multiplied by p population individuals with the minimum fitness value in the G generation individuals, and p belongs to [0,1]]，
All represent randomly selected population individuals from the G-th generation,
representing randomly selected population individuals from the union of the current initial population and A, r1≠r2≠r3≠r4≠r5Not equal to i represents [1, NPG]The random number in (1) and gamma represent a variation scale control factor.
The invention also provides a system for determining the content of rare earth extraction components, which comprises:
the model building module is used for building a model of the content of each component in the water phase of the washing section and a model of the content of each component in the organic phase of the extraction section;
the optimization target function building module is used for building an optimization target function based on a determination model of the content of each component in the water phase of the washing section and a determination model of the content of each component in the organic phase of the extraction section by adopting a least square method;
the solving module is used for solving the optimized objective function by adopting an improved standard differential evolution algorithm to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section;
the component content determination module is used for substituting the actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section into the component content determination model in the water phase of the washing section to obtain the content of each component in the organic phase of the washing section; and substituting the actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section into the determination model of the content of each component in the organic phase of the extraction section to obtain the content of each component in the aqueous phase of the extraction section.
Optionally, the solving module specifically includes:
an initialization unit for initializing parameters;
the initial population determining unit is used for determining an initial population obtained by the G generation evolution population; the initial population comprises NPsGIndividual population;
a variation unit, configured to perform variation on target vectors corresponding to various group individuals in the initial population by using a dual variation strategy method, so as to obtain variation vectors corresponding to various group individuals;
the second-term cross operation unit is used for performing second-term cross operation on target vectors and variation vectors corresponding to various group individuals in the initial population to obtain test vectors corresponding to various group individuals in the initial population;
the next generation population individual determining unit is used for determining next generation population individuals based on the fitness value of the test vector and the fitness value of the target vector by adopting a greedy selection mode, and storing various population individuals to an initial population;
the judging unit is used for judging whether G is larger than or equal to the maximum population evolution algebra Maxgem; if G is greater than or equal to Maxgem, executing an actual energy efficiency separation coefficient determining unit; if G is smaller than Maxgem, making G equal to G +1, and returning to a mutation unit;
and the actual energy efficiency separation coefficient determining unit is used for substituting target vectors corresponding to various group individuals in the initial population into the optimization target function, and taking the target vectors corresponding to the group individuals with the minimum fitness value as actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section and the content of each component in the organic phase of the extraction section.
Optionally, the specific formula of the determination model for the content of each component in the organic phase at the extraction section is as follows:
the concrete formula of the determination model of the content of each component in the water phase of the washing section is as follows:
wherein, YciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckThe actual energy efficiency separation coefficient corresponding to the k component in the organic phase of the extraction section is shown, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicating the content of the ith component of the organic phase outlet.
Optionally, the optimization objective function comprises an objective function in the organic phase of the extraction section and an objective function in the aqueous phase of the washing section;
the specific formula of the objective function in the organic phase of the extraction section is as follows:
the specific formula of the target function in the water phase of the washing section is as follows:
wherein J represents the square sum of the difference between the content of each component in the organic phase of the extraction section and the actual plant data, W represents the square sum of the difference between the content of each component in the aqueous phase of the washing section and the actual plant data, minJ and minW are the minimum values of J and W, respectively, and Y is the minimum value ofciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckThe actual energy efficiency separation coefficient corresponding to the k component in the organic phase of the extraction section is shown, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicates the content of the ith component of the organic phase outlet,
and
respectively representing the content of the ith component in an organic phase of an extraction section and an aqueous phase of a washing section obtained in an actual plant.
Optionally, the target vectors corresponding to the various group individuals in the initial population are mutated by using a double mutation strategy method to obtain the mutation vectors corresponding to the various group individuals, and a specific calculation formula is as follows:
wherein the content of the first and second substances,
representing variation vectors corresponding to the nth population individuals,
representing the target vector corresponding to the nth population of individuals, FnRepresenting the scaling factor corresponding to the nth population individual,
the expression is randomly selected from the first NP multiplied by p population individuals with the minimum fitness value in the G generation individuals, and p belongs to [0,1]]，
All represent randomly selected population individuals from the G-th generation,
representing randomly selected population individuals from the union of the current initial population and A, r1≠r2≠r3≠r4≠r5Not equal to i represents [1, NPG]The random number in (1) and gamma represent a variation scale control factor.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a method and a system for determining the content of rare earth extraction components, wherein an optimized objective function is solved by utilizing an improved standard differential evolution algorithm, the solved actual energy efficiency separation coefficient is respectively substituted into a washing section water phase component content determination model and an extraction section organic phase component content determination model which accord with the actual working conditions, and the content of each component in the washing section organic phase and the content of each component in the extraction section water phase are respectively obtained, so that the calculated content of each component is closer to the content of each component in each stage detected by an actual factory, and important references are provided for new process development, the process flow recombination of the existing rare earth extraction process and the re-optimization of process parameters, and the method and the system have important practical significance.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for determining the content of rare earth extraction components according to the present invention;
FIG. 2 is a flow chart of the rare earth cascade extraction production process of the present invention;
FIG. 3 is a flow chart of the improved differential evolution algorithm LCTADE of the present invention;
FIG. 4 is a diagram of a system for determining the content of a rare earth extraction component according to the present invention;
FIG. 5 is a graph showing the convergence of the fitness value error of the LCTADE and other DE algorithms of the present invention as a function of evolution algebra on CEC2017, namely functions 5, 8, 12, 26 and 30;
FIG. 6 is a schematic diagram of an actual energy efficiency separation coefficient obtained by optimizing the improved differential evolution algorithm of the present invention;
FIG. 7 is a schematic diagram of the comparison of the content of each component and an actual value calculated based on an actual energy efficiency separation coefficient according to the present invention;
FIG. 8 is a schematic diagram of the error between the calculated value and the actual value of the content of each component calculated by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for determining the content of rare earth extraction components so as to improve the accuracy of predicting the content of the rare earth extraction components.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example 1
As shown in fig. 1, the present invention provides a method for determining a content of a rare earth extraction component, the method comprising:
step S1: and constructing a model for determining the content of each component in the water phase of the washing section and a model for determining the content of each component in the organic phase of the extraction section.
Step S2: and constructing an optimization objective function by adopting a least square method based on the determination model of the content of each component in the water phase of the washing section and the determination model of the content of each component in the organic phase of the extraction section.
Step S3: and solving the optimized objective function by adopting an improved standard differential evolution algorithm to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section.
Step S4: substituting actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section into a determination model of the content of each component in the water phase of the washing section to obtain the content of each component in the organic phase of the washing section; and substituting the actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section into the determination model of the content of each component in the organic phase of the extraction section to obtain the content of each component in the aqueous phase of the extraction section.
The individual steps are discussed in detail below:
as shown in fig. 2, the cascade extraction separation process is to connect several extraction tanks in series to continuously contact the rare earth elements with the organic phase and the aqueous phase to separate different elements. The rare earth cascade extraction production flow with grade a washing and grade b extraction is characterized by that the extractant is added from grade 1, and is left-handed under the action of motor and stirrer in the extraction tankRight flow; the detergent is added from the a + b stage and flows from right to left; the feed liquid is added into an organic phase from the B-level, moves from right to left, extracts different rare earth elements into different solvents through continuous fusion with an extracting agent to realize separation, and is divided into N components, wherein the content of the component B difficult to extract in the organic phase of the first component is YBThe N component is the easily extracted component A with the content of organic phase YA。
According to the cascade extraction theory, when the rare earth extraction system reaches a steady state, A is an easy-to-extract component, B is a difficult-to-extract component, Y is an organic phase composition, X is a water phase composition, and N is a component number. The adjacent separation coefficient is defined as:
wherein, betaA/BDenotes the adjacent separation coefficient of the extractable component A relative to the less extractable component B, YBRepresents the content of the hard-to-extract component B in the organic phase, YARepresents the content of the extractable component A in the organic phase, XBRepresents the content of the difficult-to-extract component B in the aqueous phase, XAThe content of the extractable component a in the aqueous phase is indicated.
The expression formula of the relative separation coefficient of the i-th component relative to the refractory component B (first component) can be deduced based on the definition of adjacent separation coefficients:
wherein, beta1/iRepresents a relative separation coefficient, beta, of the refractory component B with respect to the i-th componenti/1Denotes the relative separation coefficient of the i-th component from the refractory component B, YiDenotes the content of the i-th component in the organic phase, XiDenotes the content of the i-th component in the aqueous phase, i is 1,2, …, N, N is the number of components, YBRepresents the content of the hard-to-extract component B in the organic phase, XBThe content of the hard-extraction component B in the aqueous phase is shown.
Similarly, the expression formula of the relative separation coefficient of the i-th component with respect to the extractable component a (last component) can be derived based on the definition of the adjacent separation coefficients:
wherein, betaN/iRepresents a relative separation coefficient, β, of the extractable component A with respect to the i-th componenti/NDenotes the relative separation coefficient of the i-th component from the extractable component A, YiDenotes the content of the i-th component in the organic phase, XiDenotes the content of the i-th component in the aqueous phase, i is 1,2, …, N, N is the number of components, YARepresents the content of organic phase in the extractable component A, XARepresents the content of the water phase in the extractable component A.
When the rare earth extraction system is balanced, a calculation formula of a relative separation coefficient is shown in table 1, wherein L is an element serial number of a cutting position for dividing the difficult-to-extract component and the easy-to-extract component, the component number is N, k is a current element serial number, for example, when the rare earth extraction system is a Ce, Pr and Nd three-component extraction separation process, Pr is an element for dividing the cutting position of the easy-to-extract component Ce and the difficult-to-extract component Nd, the component number N is 3, and L is 2.
TABLE 1 actual separation coefficients at each stage of rare earth extraction separation
When simulation calculation is carried out step by step from the 1 st stage to the intermediate feeding stage, the content of the ith component at the outlet of the water phase is known as XciThe solution of the i component Y in the organic phase of the extraction section is requiredci. From equation (2):
for each of the organic phases of formula (4)The sum of the components being equal to 1, i.e. (Y)1+Y2+…+YN1), so summarized:
and then the formula (5) is substituted back to the formula (4) to obtain a general formula for calculating the content of each component in the organic phase at the extraction section, wherein the general formula is as follows:
similarly, the content of the ith component at the outlet of the organic phase is known to be YwiCalculating a general formula for calculating the content of each component in the water phase of the washing section as follows:
based on the two formulas, the separation coefficient beta can be separated according to the theoretical agingckOr betawkAnd calculating the content of each element component between different phases in each stage.
Considering that the extraction efficiency is different due to certain energy consumption of a stirrer in an extraction tank in an actual extraction industrial field, when a rare earth extraction system is stable, the composition X and the composition Y of a water phase and an organic phase are inaccurate, so that the relative separation coefficient values of the formulas (2) and (3) are incorrect, and the output values of the calculation models of the content of each level of each component of the rare earth element based on the relative separation coefficients are inconsistent with the actual working conditions. Therefore, the energy efficiency separation coefficient is provided to reduce the influence of the energy efficiency of the extraction tank on the component content of the model calculation, and the specific formula of the step S1 of establishing the determination model of the component content in the organic phase of the extraction section based on the actual energy efficiency separation coefficient is as follows:
the concrete formula for establishing a determination model of the content of each component in the water phase of the washing section based on the actual energy efficiency separation coefficient is as follows:
wherein, YciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckThe actual energy efficiency separation coefficient corresponding to the k component in the organic phase of the extraction section is shown, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicating the content of the ith component of the organic phase outlet.
Step S2: constructing an optimization objective function based on a determination model of the content of each component in the water phase of the washing section and a determination model of the content of each component in the organic phase of the extraction section by adopting a least square method; the optimization objective function includes an objective function in the organic phase of the extraction section and an objective function in the aqueous phase of the washing section.
The specific formula of the objective function in the organic phase of the extraction section is as follows:
the specific formula of the target function in the water phase of the washing section is as follows:
wherein J represents the square sum of the difference between the content of each component in the organic phase of the extraction section and the actual plant data, W represents the square sum of the difference between the content of each component in the aqueous phase of the washing section and the actual plant data, minJ and minW are the minimum values of J and W, respectively, and Y is the minimum value ofciDenotes the content of the i-th component in the organic phase of the extraction section, XwiRepresents the content of the ith component in the water phase of the washing section, i is 1,2,…, N, N is component number, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckThe actual energy efficiency separation coefficient corresponding to the k component in the organic phase of the extraction section is shown, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicates the content of the ith component of the organic phase outlet,
and
respectively representing the content of the ith component in an organic phase of an extraction section and an aqueous phase of a washing section obtained in an actual plant.
In the embodiment, the least square method is used to minimize the sum of squares of differences between the component contents of each stage calculated by two content determination models and actual plant data, wherein the two optimization objective functions need to be solved respectively when an optimization algorithm is used for solving, and a fitness function f () is used for replacing J and W when the two optimization objective functions are solved.
In the embodiment, an improved DE algorithm is used for solving two optimization targets respectively, an objective function J is firstly made to be minimum to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in an organic phase of an extraction section, and an objective function W is made to be minimum to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in a water phase of a washing section in the same manner.
As shown in fig. 3, the optimized objective function is solved by using an improved standard differential evolution algorithm to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section, and the method specifically includes:
step S31: initializing parameters; the parameters include: population evolution algebra G, spatial dimension D, maximum population number NPmaxMinimum population number NPminMaximum population evolution algebra Maxgem, mean μ CR, external archive A. Wherein D ═ N-1.
Step S32: determining an initial population obtained by the G generation evolution population; the initial populationIncluding NPGThe number of individuals in a population is small,
n＝1,2,…, NP G1,2, ·, D; wherein the content of the first and second substances,
representing a set of vectors corresponding to the initial population,
indicates the NP in the G-th generation starting populationGTarget vectors corresponding to the individual population, wherein each target vector consists of D-dimensional parameters, beta'm,n,GAnd representing the parameter corresponding to the mth dimension of the nth population individual in the G-th generation initial population.
The method for mapping the chaotic space to the solution space of the target function comprises the following steps:
1) randomly generating a random number within the range of-1 ≦ h (1)mLess than or equal to 1; d-dimensional chaotic variable H ═ H (1) with m ≦ 1 ≦ D1,h(1)2,...,h(1)d) Wherein, h (1)mAn m-th dimension parameter representing the generated chaotic vector.
2) NP is performed on each dimension of the generated H by the equation (12)G1 iteration to yield NP G1 chaotic variable.
The population is initialized by using cubic mapping in the chaotic model, and the distribution of the generated chaotic sequence is relatively even compared with the common Logistic mapping, so that an iterative expression generated by the chaotic sequence is as follows:
h(n+1)m＝4h(n)m 3-3h(n)m；-1≤h(n)m≤1；n＝0,1,2,...,NPG；m＝1,...,D (12)；
wherein, h (n)m,h(n+1)mThe values obtained by the nth-1 th iteration and the nth iteration of the mth dimension of the chaotic vector are obtained.
3) According to
Will generate NPGMapping the D-dimensional chaotic variables to a solution space of an optimized objective function to obtain a population number NPGOf which is beta'min,β'maxRespectively the minimum and maximum values per dimension for each population individual (i.e. the target vector),
m-dimensional parameter of the nth population individual representing the solution space of the mapping, h (n)mAnd the m-dimension parameter represents the nth population individual of the chaos vector generated by iteration.
The initial population generated by chaotic initialization is NPGEach population individual is composed of parameters with dimension D, and the number G of population evolution generations is initialized to be 0, so that the vector set corresponding to the initial population is obtained as follows:
the performance requirements on the mutation strategy are different in different stages of evolution, and DE/current-to-pbest/1 and DE/rand/1 are selected as a multi-scale mutation strategy set. In order to balance the convergence speed and the accuracy of the algorithm, a dual-variation strategy method based on DE/current-to-pbest/1 and DE/rand/1 is provided, and target vectors corresponding to various population individuals in the initial population are subjected to G generation
Performing variation to obtain variation vector
The method comprises the following specific steps:
step S33: and (3) carrying out variation on the target vectors corresponding to various group individuals in the initial population by adopting a double variation strategy method to obtain the variation vectors corresponding to various group individuals, wherein the specific calculation formula is as follows:
wherein the content of the first and second substances,
representing variation vectors corresponding to the nth population individuals,
representing the target vector corresponding to the nth population of individuals, FnRepresenting the scaling factor corresponding to the nth population individual,
indicates the pre-NP p (p E [0, 1) with the smallest (better) fitness value among individuals from the G-th generation]) Randomly selecting the individual from a plurality of population individuals,
all represent randomly selected population individuals from the G-th generation,
representing randomly selected population individuals from the union of the current initial population and A, r1≠r2≠r3≠r4≠r5Not equal to i represents [1, NPG]The random number in (1) and gamma represent a variation scale control factor.
And
obtained by the mutation strategies DE/current-to-pbest/1 and DE/rand/1 respectively. When the fitness value of the individual after evolution is better than that before evolution, the individual before evolution is stored in an external archive a. And when the actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section is obtained, substituting the target vectors corresponding to various groups of individuals before evolution into a formula (10) to obtain J, and expressing the fitness f () by using the J.
Gamma belongs to [0,1] as a variation scale control factor, and is reduced along with evolution algebra in the optimization process. Most evolutionary algorithm search process earlier than later stage important, need increase DE/current-to-pbest/1 generated variation vector proportion, make search range close to the optimal solution, accelerate convergence rate, gamma is great. In the later stage, due to poor population diversity, the algorithm is easy to fall into a local optimal solution, so that the proportion of the variation vectors generated by DE/rand/1 needs to be increased, and the gamma value is smaller in the later stage. γ is defined according to evolutionary properties as:
wherein γ represents a variation scale control factor, γ belongs to [0,1], G represents a current population evolution algebra, and Maxgem represents a maximum iteration algebra, which is generally set to 3000.
FnUpdating according to the fitness value of each generation of population in the evolution process, so summarizing to obtain FnThe specific calculation formula of (A) is as follows:
wherein, FnRepresenting the scale factor corresponding to the nth population individual in the initial population,
respectively representing target vectors, randc, corresponding to population individuals with the maximum and minimum fitness values in the G-th generation initial populationi(0.5,0.1) is a random number generated according to the Cauchy distribution,
represents the maximum fitness value in the G-th generation initial population,
represents the minimum fitness value in the G generation initial population,
and representing the target vector corresponding to the nth population individual.
Step S34: target vectors corresponding to various group individuals in the initial population
And the variance vector
Performing two-term cross operation to obtain test vectors corresponding to various population individuals in the initial population
Wherein u ism,n,GRepresenting test vectors corresponding to nth population individuals in the G generation initial population
The m-th dimension parameter of (1).
The specific formula for calculating the binomial crossover operation is as follows:
wherein, CRnRepresents the cross probability, CR, of the nth population individual in the initial populationnE.g., (0,1), if randn,m[0,1]The generated random number is less than or equal to the cross probability CRnOr the dimension m of the current vector is equal to some dimension m generated randomlyrandAnd testing vector corresponding to nth population individual in G generation initial population
M-dimension parameter u in (1)m,n,GVariation vectors corresponding to nth population individuals in G generation initial population
M-th dimension parameter v ofm,n,GReplacing; otherwise, test vectors corresponding to nth population individuals in G-th generation initial population
M-dimension parameter u in (1)m,n,GTarget vectors corresponding to nth population individuals in G-th generation initial population
M-th dimension parameter beta'm,n,GInstead.
Calculating the cross probability CR corresponding to the nth population individual in the G-th generation initial populationn,GThe concrete formula of (1) is as follows:
CRn,G＝randi(μCRG,0.1) (18)；
wherein, CRn,GRepresents the cross probability CR corresponding to the nth population individual in the G generation initial populationn,G，randi(μCRG0.1) mean value μ CRGAnd the standard deviation is 0.1 normal distribution generation mode. Initial time μ CRGSet to 0.5. After each iteration, the mean value μ CR is updatedGThe concrete formula of (1) is as follows:
μCRG+1＝(1-cCR)×μCRG+cCR×meanWL(SCR,G) (19)；
wherein S isCR,GRepresents a set consisting of the cross probabilities corresponding to all successful population individuals, μ CRGIn the range of [0,1]，maenWL(SCR,G) Represents SCR,GCross probability CR corresponding to all successful population individuals in (1)i,GWeighted average of cCRIs constant and is set to 0.5.
Calculate maenWL(SCR,G) The concrete formula of (1) is as follows:
wherein, ω iskFor the weight coefficient,. DELTA.fk is the nth species in the initial populationFitness value of group individual after evolution
Fitness value before evolution
Absolute value of the difference, Sk,CR,GDenotes SCR,GThe value of the k-th cross probability in the set,
representing the test vector corresponding to the nth population individual in the G-th generation initial population, the evolved vector,
representing a target vector corresponding to the nth population individual in the G-th generation initial population, a vector before evolution, and SCR,GRepresenting a set consisting of the cross probabilities corresponding to all successful population individuals.
Step S35: using greedy selection mode based on test vectors
Is associated with the target vector
The fitness value of the next generation population is determined, and various population individuals are stored in the initial population. When the initial population includes NPsG+1Each population individual corresponds to a target vector, and each target vector comprises D-dimensional parameters.
The number of population individuals is linearly reduced, the population number is larger at the early stage of evolution, the population diversity is increased, the population number is smaller at the later stage of evolution, the convergence speed is accelerated, and therefore the number NP of the population individuals in the G +1 generation is calculated at the momentG+1The concrete formula of (1) is as follows:
wherein, NPmaxFor the maximum population number, it is typically set at 18 × D; NPminIs the minimum population number and is set to 4; NFE is the fitness value evaluation number, which increases with the number of iterations, MAX _ NFE is the maximum fitness value evaluation number, and round () represents a rounding function.
Using greedy selection mode to make descendant test vectors
Is always better than or equal to the paternal target vector
The optimization objective function value, i.e. the fitness value, is minimized, so a greedy selection mode is adopted based on the test vector
Is associated with the target vector
The specific formula for determining the individuals in the next generation population by the fitness value is as follows:
wherein the content of the first and second substances,
representing test vectors corresponding to nth population individuals in the G generation initial population
The value of the fitness value of (a) is,
representing a target vector corresponding to an nth population individual in a G-th generation initial population
The value of the fitness value of (a) is,
and representing a target vector corresponding to the nth population individual in the G +1 th generation initial population.
The above formula illustrates that the test vectors obtained when evolving
Fitness value of
Superior to target vector
Fitness value of
Time, trial vector
Substituting target vectors
Evolving into individuals in the next generation population, otherwise, retaining the original target vectors
Step S36: judging whether G is larger than or equal to Maxgem; if G is greater than or equal to Maxgem, executing step S37; if G is smaller than Maxgem, G +1 is made, and the process returns to step S33.
Step S37: substituting target vectors corresponding to various group individuals in the initial population into an optimization objective function, taking the target vectors corresponding to the group individuals with the minimum fitness value as an actual energy efficiency separation coefficient, and specifically, substituting the target vectors corresponding to the various group individuals in the initial population into an optimization objective function
Substituting a plurality of parameters in (1) into β 'in formula 10'ckCorresponding the minimum fitness value minJ to the target vector of the population individual
As the actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section. In the same way, the target vectors corresponding to various group individuals in the initial group are used
Substituting a plurality of parameters in (b) into β 'in formula 11'wkCorresponding the minimum fitness value minW to the target vector of the individual population
And the actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section is used.
Example 2
As shown in fig. 4, the present invention also discloses a rare earth extraction component content determination system, which includes:
the model building module 401 is used for building a model of the content of each component in the water phase of the washing section and a model of the content of each component in the organic phase of the extraction section.
An optimization objective function constructing module 402, configured to construct an optimization objective function based on the determination model of the content of each component in the water phase of the washing section and the determination model of the content of each component in the organic phase of the extraction section by using a least square method.
And a solving module 403, configured to solve the optimized objective function by using an improved standard differential evolution algorithm, to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section.
A component content determination module 404, configured to substitute actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section into a component content determination model in the water phase of the washing section, so as to obtain the content of each component in the organic phase of the washing section; and substituting the actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section into the determination model of the content of each component in the organic phase of the extraction section to obtain the content of each component in the aqueous phase of the extraction section.
As an optional implementation manner, the solving module 403 in the present invention specifically includes:
and the initialization unit is used for initializing the parameters.
The initial population determining unit is used for determining an initial population obtained by the G generation evolution population; the initial population comprises NPsGAnd (4) individual population.
And the variation unit is used for performing variation on the target vectors corresponding to the various groups of individuals in the initial population by adopting a double variation strategy method to obtain the variation vectors corresponding to the various groups of individuals.
And the two-term cross operation unit is used for performing two-term cross operation on the target vectors and the variation vectors corresponding to the various group individuals in the initial population to obtain test vectors corresponding to the various group individuals in the initial population.
And the next generation population individual determining unit is used for determining next generation population individuals based on the fitness value of the test vector and the fitness value of the target vector by adopting a greedy selection mode, and storing various population individuals to the initial population.
The judging unit is used for judging whether G is larger than or equal to the maximum population evolution algebra Maxgem; if G is greater than or equal to Maxgem, executing an actual energy efficiency separation coefficient determining unit; if G is smaller than Maxgem, making G equal to G +1, and returning to a mutation unit;
and the actual energy efficiency separation coefficient determining unit is used for substituting target vectors corresponding to various group individuals in the initial population into the optimization target function, and taking the target vectors corresponding to the group individuals with the minimum fitness value as actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section and the content of each component in the organic phase of the extraction section.
The same contents as those in embodiment 1 are not described in detail herein.
Example 3
The initialization parameter values of the invention are as follows: d2, NPmax＝18*D，NPmin＝4，μCRG＝0.5，MAX _ NFE ═ D × 1000, Maxgem ═ 3000; the same steps as those in embodiment 1 are not described in detail.
Fig. 3 is a specific flowchart of the improved differential evolution algorithm lcade of the present invention, and the convergence curve of the fitness error varying with the evolution algebra when the lcade and other DE improved algorithms optimize different functions is shown in fig. 5, where (a) is the convergence curve of the fitness error varying with the evolution algebra for function 5, (b) is the convergence curve of the fitness error varying with the evolution algebra for function 8, (c) is the convergence curve of the fitness error varying with the evolution algebra for function 12, (d) is the convergence curve of the fitness error varying with the evolution algebra for function 26, and (e) is the convergence curve of the fitness error varying with the evolution algebra for function 30; the invention uses an improved algorithm LCTADE to optimize objective functions (10) and (11) to obtain actual energy efficiency separation coefficients corresponding to the contents of components of an extraction section and a washing section, and the result is shown in figure 6, wherein (a) is the actual energy efficiency separation coefficient of the extraction section, and (b) is the actual energy efficiency separation coefficient of the washing section; substituting the actual energy efficiency separation coefficient corresponding to each optimized component content into rare earth element component content calculation models (8) and (9) established based on the energy efficiency separation coefficient to obtain the component content values of each level which meet the actual requirement, wherein a comparison graph of the actual component content and the component content is shown in figure 7, and an error graph is shown in figure 8.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A method for determining the content of rare earth extraction components is characterized by comprising the following steps:
step S1: constructing a model of the content of each component in the water phase of the washing section and a model of the content of each component in the organic phase of the extraction section;
step S2: constructing an optimization objective function based on a determination model of the content of each component in the water phase of the washing section and a determination model of the content of each component in the organic phase of the extraction section by adopting a least square method;
step S3: solving the optimized objective function by adopting an improved standard differential evolution algorithm to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section;
step S4: substituting actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section into a determination model of the content of each component in the water phase of the washing section to obtain the content of each component in the organic phase of the washing section; and substituting the actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section into the determination model of the content of each component in the organic phase of the extraction section to obtain the content of each component in the aqueous phase of the extraction section.
2. The method for determining the content of the rare earth extraction component according to claim 1, wherein the optimized objective function is solved by using an improved standard differential evolution algorithm to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section, and the method specifically comprises the following steps:
step S31: initializing parameters;
step S32: determining an initial population obtained by the G generation evolution population; the initial population comprises NPsGIndividual population;
step S33: carrying out variation on target vectors corresponding to various group individuals in the initial population by adopting a double variation strategy method to obtain variation vectors corresponding to various group individuals;
step S34: performing two-term cross operation on target vectors and variation vectors corresponding to various group individuals in the initial population to obtain test vectors corresponding to various group individuals in the initial population;
step S35: determining next generation population individuals based on the fitness value of the test vector and the fitness value of the target vector by adopting a greedy selection mode, and storing various population individuals to an initial population;
step S36: judging whether G is larger than or equal to the maximum population evolution algebra Maxgem; if G is greater than or equal to Maxgem, executing step S37; if G is smaller than Maxgem, making G equal to G +1, and returning to the step S33;
step S37: substituting target vectors corresponding to various population individuals in the initial population into an optimization target function, and taking the target vectors corresponding to the population individuals with the minimum fitness value as actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section and the content of each component in the organic phase of the extraction section.
3. The method for determining the content of the rare earth extraction component according to claim 1, wherein the specific formula of the determination model of the content of each component in the organic phase at the extraction section is as follows:
the concrete formula of the determination model of the content of each component in the water phase of the washing section is as follows:
wherein, YciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckRepresenting the actual energy efficiency separation corresponding to the k component in the organic phase of the extraction sectionThe coefficients, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicating the content of the ith component of the organic phase outlet.
4. The rare earth extraction component content determination method according to claim 1, wherein the optimization objective function includes an objective function in an organic phase of the extraction section and an objective function in an aqueous phase of the washing section;
the specific formula of the objective function in the organic phase of the extraction section is as follows:
the specific formula of the target function in the water phase of the washing section is as follows:
wherein J represents the square sum of the difference between the content of each component in the organic phase of the extraction section and the actual plant data, W represents the square sum of the difference between the content of each component in the aqueous phase of the washing section and the actual plant data, minJ and minW are the minimum values of J and W, respectively, and Y is the minimum value ofciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckThe actual energy efficiency separation coefficient corresponding to the k component in the organic phase of the extraction section is shown, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicates the content of the ith component of the organic phase outlet,
and
respectively representing the content of the ith component in an organic phase of an extraction section and an aqueous phase of a washing section obtained in an actual plant.
5. The method for determining the content of rare earth extraction components according to claim 2, wherein the target vectors corresponding to the various groups of individuals in the initial population are varied by using a double variation strategy method to obtain the variation vectors corresponding to the various groups of individuals, and the specific calculation formula is as follows:
wherein the content of the first and second substances,
representing variation vectors corresponding to the nth population individuals,
representing the target vector corresponding to the nth population of individuals, FnRepresenting the scaling factor corresponding to the nth population individual,
the expression is randomly selected from the first NP multiplied by p population individuals with the minimum fitness value in the G generation individuals, and p belongs to [0,1]]，
All represent randomly selected population individuals from the G-th generation,
representing randomly selected population individuals from the union of the current initial population and A, r1≠r2≠r3≠r4≠r5Not equal to i represents [1, NPG]The random number in (1) and gamma represent a variation scale control factor.
6. A rare earth extraction component content determination system, the system comprising:
the model building module is used for building a model of the content of each component in the water phase of the washing section and a model of the content of each component in the organic phase of the extraction section;
the optimization target function building module is used for building an optimization target function based on a determination model of the content of each component in the water phase of the washing section and a determination model of the content of each component in the organic phase of the extraction section by adopting a least square method;
the solving module is used for solving the optimized objective function by adopting an improved standard differential evolution algorithm to obtain an actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section and an actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section;
the component content determination module is used for substituting the actual energy efficiency separation coefficient corresponding to the content of each component in the water phase of the washing section into the component content determination model in the water phase of the washing section to obtain the content of each component in the organic phase of the washing section; and substituting the actual energy efficiency separation coefficient corresponding to the content of each component in the organic phase of the extraction section into the determination model of the content of each component in the organic phase of the extraction section to obtain the content of each component in the aqueous phase of the extraction section.
7. The rare earth extraction component content determination system of claim 6, wherein the solving module specifically comprises:
an initialization unit for initializing parameters;
the initial population determining unit is used for determining an initial population obtained by the G generation evolution population; the initial population comprises NPsGIndividual population;
a variation unit, configured to perform variation on target vectors corresponding to various group individuals in the initial population by using a dual variation strategy method, so as to obtain variation vectors corresponding to various group individuals;
the second-term cross operation unit is used for performing second-term cross operation on target vectors and variation vectors corresponding to various group individuals in the initial population to obtain test vectors corresponding to various group individuals in the initial population;
the next generation population individual determining unit is used for determining next generation population individuals based on the fitness value of the test vector and the fitness value of the target vector by adopting a greedy selection mode, and storing various population individuals to an initial population;
the judging unit is used for judging whether G is larger than or equal to the maximum population evolution algebra Maxgem; if G is greater than or equal to Maxgem, executing an actual energy efficiency separation coefficient determining unit; if G is smaller than Maxgem, making G equal to G +1, and returning to a mutation unit;
and the actual energy efficiency separation coefficient determining unit is used for substituting target vectors corresponding to various group individuals in the initial population into the optimization target function, and taking the target vectors corresponding to the group individuals with the minimum fitness value as actual energy efficiency separation coefficients corresponding to the content of each component in the water phase of the washing section and the content of each component in the organic phase of the extraction section.
8. The rare earth extraction component content determination system according to claim 6, wherein the specific formula of the determination model of the content of each component in the organic phase at the extraction section is as follows:
the concrete formula of the determination model of the content of each component in the water phase of the washing section is as follows:
wherein, YciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckRepresenting practical energy efficiency separation system corresponding to k component in organic phase of extraction sectionThe numbers k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicating the content of the ith component of the organic phase outlet.
9. The rare earth extraction component content determination system as claimed in claim 6, wherein the optimization objective function includes an objective function in an organic phase of the extraction section and an objective function in an aqueous phase of the washing section;
the specific formula of the objective function in the organic phase of the extraction section is as follows:
the specific formula of the target function in the water phase of the washing section is as follows:
wherein J represents the square sum of the difference between the content of each component in the organic phase of the extraction section and the actual plant data, W represents the square sum of the difference between the content of each component in the aqueous phase of the washing section and the actual plant data, minJ and minW are the minimum values of J and W, respectively, and Y is the minimum value ofciDenotes the content of the i-th component in the organic phase of the extraction section, XwiDenotes the content of the i-th component in the water phase of the washing stage, i ═ 1,2, …, N, N are component numbers, beta'wkRepresents an actual energy efficiency separation coefficient, beta ', corresponding to a k component in an aqueous phase of a washing section'ckThe actual energy efficiency separation coefficient corresponding to the k component in the organic phase of the extraction section is shown, k and i are independent variables, k is 1,2, …, i, XciDenotes the content of the i-th component at the outlet of the aqueous phase, YwiIndicates the content of the ith component of the organic phase outlet,
and
respectively representing the content of the ith component in an organic phase of an extraction section and an aqueous phase of a washing section obtained in an actual plant.
10. The system for determining rare earth extraction component content according to claim 7, wherein the target vectors corresponding to the various groups of individuals in the initial population are varied by using a double variation strategy method to obtain the variation vectors corresponding to the various groups of individuals, and the specific calculation formula is as follows:
wherein the content of the first and second substances,
representing variation vectors corresponding to the nth population individuals,
representing the target vector corresponding to the nth population of individuals, FnRepresenting the scaling factor corresponding to the nth population individual,
the expression is randomly selected from the first NP multiplied by p population individuals with the minimum fitness value in the G generation individuals, and p belongs to [0,1]]，
All represent randomly selected population individuals from the G-th generation,
representing randomly selected population individuals from the union of the current initial population and A, r1≠r2≠r3≠r4≠r5Not equal to i represents [1, NPG]The random number in (1) and gamma represent a variation scale control factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111067887.2A CN113777925A (en) | 2021-09-13 | 2021-09-13 | Method and system for determining content of rare earth extraction component |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111067887.2A CN113777925A (en) | 2021-09-13 | 2021-09-13 | Method and system for determining content of rare earth extraction component |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113777925A true CN113777925A (en) | 2021-12-10 |
Family
ID=78842974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111067887.2A Pending CN113777925A (en) | 2021-09-13 | 2021-09-13 | Method and system for determining content of rare earth extraction component |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113777925A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744292A (en) * | 2014-01-22 | 2014-04-23 | 东北大学 | Rare earth extraction process dynamic operating control method based on data driving |
| CN106354017A (en) * | 2016-11-14 | 2017-01-25 | 华东交通大学 | Method for controlling content ranges of components in rare earth extraction and separation process |
| WO2021142916A1 (en) * | 2020-01-15 | 2021-07-22 | 深圳大学 | Proxy-assisted evolutionary algorithm-based airfoil optimization method and apparatus |
| CN113377072A (en) * | 2021-06-24 | 2021-09-10 | 华东交通大学 | Rare earth extraction process drug dosage optimization setting method based on instant learning |
-
2021
- 2021-09-13 CN CN202111067887.2A patent/CN113777925A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744292A (en) * | 2014-01-22 | 2014-04-23 | 东北大学 | Rare earth extraction process dynamic operating control method based on data driving |
| CN106354017A (en) * | 2016-11-14 | 2017-01-25 | 华东交通大学 | Method for controlling content ranges of components in rare earth extraction and separation process |
| WO2021142916A1 (en) * | 2020-01-15 | 2021-07-22 | 深圳大学 | Proxy-assisted evolutionary algorithm-based airfoil optimization method and apparatus |
| CN113377072A (en) * | 2021-06-24 | 2021-09-10 | 华东交通大学 | Rare earth extraction process drug dosage optimization setting method based on instant learning |
Non-Patent Citations (1)
| Title |
|---|
| 杨辉;代文豪;陆荣秀;朱建勇;: "基于分离系数校正的稀土萃取流程模拟", 化工学报, vol. 71, no. 07, pages 3181 - 3190 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104459560B (en) | Lithium battery method for predicting residual useful life based on wavelet de-noising and Method Using Relevance Vector Machine | |
| CN110807544B (en) | Oil field residual oil saturation distribution prediction method based on machine learning | |
| CN109002656B (en) | Multi-stage task system redundancy configuration optimization method | |
| CN108074015B (en) | Ultra-short-term prediction method and system for wind power | |
| CN110610225A (en) | Multi-objective particle swarm optimization algorithm based on kriging proxy model plus-point strategy | |
| CN109934330A (en) | The method of prediction model is constructed based on the drosophila optimization algorithm of diversified population | |
| CN110413878A (en) | User based on adaptive elastomeric network-commodity preference prediction meanss and method | |
| CN109066651B (en) | Method for calculating limit transmission power of wind power-load scene | |
| CN113468817A (en) | Ultra-short-term wind power prediction method based on IGOA (optimized El-electric field model) | |
| CN109325613B (en) | Method for online predicting static voltage stability margin by using parallel sequential extreme learning machine | |
| CN111105005B (en) | Wind power prediction method | |
| CN110222816B (en) | Deep learning model establishing method, image processing method and device | |
| CN111563203A (en) | Intelligent household user-service interest degree personalized prediction device and method based on rapid non-negative implicit characteristic analysis | |
| CN113407185A (en) | Compiler optimization option recommendation method based on Bayesian optimization | |
| CN114282646B (en) | Optical power prediction method and system based on two-stage feature extraction and BiLSTM improvement | |
| CN111832817A (en) | Small world echo state network time sequence prediction method based on MCP penalty function | |
| CN113095477B (en) | Wind power prediction method based on DE-BP neural network | |
| CN113777925A (en) | Method and system for determining content of rare earth extraction component | |
| CN112381591A (en) | Sales prediction optimization method based on LSTM deep learning model | |
| CN116054144A (en) | Distribution network reconstruction method, system and storage medium for distributed photovoltaic access | |
| CN113610665B (en) | Wind power generation power prediction method based on multi-delay output echo state network | |
| CN114971325A (en) | Method for screening key quality characteristic set of electric tool rotor | |
| CN114912331A (en) | Cabin reinforcing rib optimization method, device, equipment and medium | |
| Liu et al. | Automatic calibration of numerical models using fast optimisation by fitness approximation | |
| CN111460550B (en) | Free-form surface structure multi-working-condition Pareto solution set optimization method based on changing niches |
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 |