CN114036670B - Method for optimizing separation performance of liquid-solid hydrocyclone based on transfer learning - Google Patents
Method for optimizing separation performance of liquid-solid hydrocyclone based on transfer learning Download PDFInfo
- Publication number
- CN114036670B CN114036670B CN202111323572.XA CN202111323572A CN114036670B CN 114036670 B CN114036670 B CN 114036670B CN 202111323572 A CN202111323572 A CN 202111323572A CN 114036670 B CN114036670 B CN 114036670B
- Authority
- CN
- China
- Prior art keywords
- liquid
- hydrocyclone
- solid
- transfer learning
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000007787 solid Substances 0.000 title claims abstract description 106
- 238000000926 separation method Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000013526 transfer learning Methods 0.000 title claims abstract description 46
- 238000004088 simulation Methods 0.000 claims abstract description 40
- 239000007788 liquid Substances 0.000 claims abstract description 17
- 230000005514 two-phase flow Effects 0.000 claims abstract description 11
- 239000007790 solid phase Substances 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000009826 distribution Methods 0.000 claims description 15
- 238000013508 migration Methods 0.000 claims description 15
- 230000005012 migration Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000012071 phase Substances 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 239000002245 particle Substances 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 239000012530 fluid Substances 0.000 claims description 4
- 238000010998 test method Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010992 reflux Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 abstract description 2
- 238000013461 design Methods 0.000 description 13
- 238000005457 optimization Methods 0.000 description 13
- 238000002474 experimental method Methods 0.000 description 11
- 238000012360 testing method Methods 0.000 description 10
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000008901 benefit Effects 0.000 description 4
- 239000012141 concentrate Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 239000003973 paint Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004062 sedimentation Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000005406 washing Methods 0.000 description 2
- 229920002472 Starch Polymers 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000010840 domestic wastewater Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000010842 industrial wastewater Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000005191 phase separation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 235000019698 starch Nutrition 0.000 description 1
- 239000008107 starch Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
- 238000004065 wastewater treatment Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- Computing Systems (AREA)
- Fluid Mechanics (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for optimizing the separation performance of a liquid-solid hydrocyclone based on transfer learning, which comprises the following steps: training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, and modeling the working condition under an unknown mode through transfer learning so as to determine characteristic parameters of the liquid-solid hydrocyclone; acquiring empirical characteristic parameters of the liquid-solid hydrocyclone; performing numerical simulation according to the characteristic parameters of the liquid-solid hydrocyclone and the obtained empirical characteristic parameters; determining and obtaining a geometric model of the liquid-solid hydrocyclone determined by transfer learning through numerical simulation; calculating the flow characteristic, air column characteristic, solid phase flow characteristic and simulated separation efficiency of the liquid-solid hydrocyclone of the gas-liquid two-phase flow; and then the optimal separation efficiency value of the liquid-solid hydrocyclone is calculated. The invention can effectively realize the improvement of the separation performance of the liquid-solid separation hydrocyclone.
Description
Technical Field
The invention relates to the technical field of hydrocyclone design, in particular to a method for optimizing the separation performance of a liquid-solid hydrocyclone based on transfer learning.
Background
The hydrocyclone is a commonly used two-phase separation device in industrial production, and has the advantages of simple structure, convenient operation, large production capacity, high separation efficiency, small occupied area and the like. The application of the hydrocyclone comprises solid-liquid separation, liquid-gas separation, solid-solid separation, liquid-liquid separation, liquid-gas-solid three-phase simultaneous separation and the like. The hydrocyclone is used as separation and classification equipment, the basic working principle is based on centrifugal sedimentation, when two-phase mixed liquid to be separated enters the device from an inlet of the hydrocyclone under a certain pressure, strong rotary motion is generated, and due to the density difference of the light phase and the heavy phase, the centrifugal force, the centripetal buoyancy and the fluid drag are different, most of heavy phase is discharged through a bottom flow port of the hydrocyclone under the action of centrifugal sedimentation, and most of light phase is discharged from an overflow port, so that the purpose of separation is achieved.
Currently, hydrocyclones are widely used in many fields such as petroleum, chemical industry, mining, food, environmental protection, etc. For example, classification, sorting, product concentration, paint washing clarification, etc. in mining and metallurgy engineering; oil-water separation in petrochemical industry; coarse and fine grain classification, impurity removal, starch paint washing and the like in the food industry; preparation of paper coating in the paper industry, treatment of paper-making wastewater and the like; industrial and domestic wastewater treatment in environmental engineering, and the like.
Hydrocyclones are commonly used in industrial scale production, and the performance of hydrocyclones has important effects on their productivity, economic benefits and product quality. In practice, hydrocyclones are often selected according to production capacity, classified particle size or existing products, or preliminary designs of the hydrocyclone base diameter and related structural parameters are made empirically, and it is difficult to determine the hydrocyclone performance in these ways to optimize for a particular production requirement. Therefore, the method has important engineering significance for further optimizing the hydrocyclone.
Currently, more optimization studies on hydrocyclones are directed to specific engineering application problems. (1) The influence of each factor on the performance of the hydrocyclone is quantitatively analyzed by a single factor test method, so that the selection of key parameters of the hydrocyclone is realized. The method can intuitively obtain the influence rule of each factor on the performance of the hydrocyclone, but has huge test quantity, and meanwhile, the method ignores the interaction influence among the factors; (2) And (3) designing a test scheme by using a test design method, and carrying out statistical analysis on test results to realize parameter optimization. The method is also limited by test cost and workload, the number of test factors is greatly limited, and only partial parameters can be optimized; (3) And the other is to apply a numerical simulation method, and analyze the influence of each influence factor on the internal flow field characteristics and the performance of the hydrocyclone through single-factor numerical simulation. The method can perform approximate quantitative analysis on partial performance of the hydrocyclone by selecting a proper turbulence model and simulation parameters, and simultaneously obtain the influence rule of each factor on the internal flow field, so as to analyze the separation mechanism of the hydrocyclone. However, the numerical simulation method is greatly influenced by the model selection and the grid division method, and the current numerical simulation method is mostly used for researching the influence rule of each factor on the internal flow field characteristics of the hydrocyclone, has a certain theoretical guiding effect on the structural design and process formulation of the hydrocyclone, and is difficult to directly use for engineering application. (4) And the other is to analyze the internal flow field of the hydrocyclone through numerical simulation, so that the structure of the hydrocyclone is improved according to the existing hydrocyclone separation mechanism. Obviously, the improvement is still obtained by a qualitative method, has limited optimizing capability, has strong pertinence and is inconvenient for reference of other engineering application problems.
Specifically, the separation performance of a hydrocyclone is affected by a number of factors, including: physical parameters, operating parameters, and structural parameters. Wherein, the physical parameters comprise particle density and particle size 2; the operating parameters comprise ore pulp concentration and inlet speed 2; the structural parameters comprise 8 items of the basic diameter of the hydrocyclone, the length of the column section, the cone angle, the inlet diameter, the overflow port diameter, the bottom flow port diameter, the insertion depth of the overflow pipe, the wall thickness of the overflow pipe and the like. In addition, the installation inclination angle of the hydrocyclone and the external environmental pressure can also have an influence on the separation performance.
Theoretically, the performance of a hydrocyclone can be analyzed and described by its internal flow field. However, the structure and operation of the hydrocyclone are seemingly simple, the internal flow field is extremely complex, and although students at home and abroad have studied the internal flow field of the hydrocyclone in a large number, and put forward a plurality of theories, methods and empirical models for the design and optimization of the hydrocyclone, various defects still exist. For example, lack of generality based on certain specific conditions; or lower accuracy due to the removal of various influencing factors and the interaction between the factors; or simply analysis optimization from a qualitative point of view results in a more monolithic result; or rely on a large number of experiments to cause problems of huge workload and cost and low working efficiency. Based on this, there is a need to propose a new method for optimizing the separation performance of a liquid-solid hydrocyclone based on transfer learning, so as to solve the above technical problems.
Disclosure of Invention
Based on the above, the present invention aims to provide a method for optimizing the separation performance of a liquid-solid hydrocyclone based on transfer learning, so as to solve the above technical problems.
The invention provides a method for optimizing the separation performance of a liquid-solid hydrocyclone based on transfer learning, wherein the method comprises the following steps:
Step one: training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, and modeling the working condition under an unknown mode through migration learning to determine characteristic parameters of the liquid-solid hydrocyclone;
step two: acquiring empirical characteristic parameters of the liquid-solid hydrocyclone;
Step three: respectively carrying out numerical simulation by adopting a secondary orthogonal rotation combination test method according to the characteristic parameters of the liquid-solid hydrocyclone and the acquired empirical characteristic parameters;
step four: respectively determining a geometric model of the liquid-solid hydrocyclone determined by transfer learning and a geometric model of the liquid-solid hydrocyclone determined by the empirical characteristic parameters through numerical simulation in the third step;
Step five: using the computational fluid dynamics principle, performing simulation calculation on the flow characteristics, the air column characteristics, the solid phase flow characteristics and the simulated separation efficiency of the liquid-solid hydrocyclone, which are determined by transfer learning, of the gas-liquid two-phase flow corresponding to the geometric model of the liquid-solid hydrocyclone, and performing simulation calculation on the flow characteristics, the air column characteristics, the solid phase flow characteristics and the simulated separation efficiency of the liquid-solid hydrocyclone, which are determined by empirical characteristic parameters, of the gas-liquid two-phase flow corresponding to the geometric model of the liquid-solid hydrocyclone;
Step six: and determining and obtaining the optimal separation efficiency value of the liquid-solid hydrocyclone according to the flow characteristic, the air column characteristic, the solid phase flow characteristic and the simulated separation efficiency of the liquid-solid hydrocyclone of each gas-liquid two-phase flow.
In the first step, training and establishing a data source domain of the liquid-solid hydrocyclone under various working conditions, and modeling the working conditions under unknown modes through transfer learning, wherein the method specifically comprises the following steps:
Training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, wherein a data sample in the data source domain is provided with a label;
And taking a new working condition to be tested in an unknown mode as a target field, and constructing a characteristic subspace according to the data of the data source field and the target field based on a migration learning principle.
In the method for optimizing the separation performance of the liquid-solid hydrocyclone based on transfer learning, in the first step, the characteristic parameters comprise physical parameters, geometric parameters, operation parameters and separation efficiency;
Wherein the physical parameters comprise inlet flow rate, particle size, inlet density difference and particle concentration; the geometric parameters comprise a feeding pipe diameter, a cylindrical section length, a conical section upper diameter, a conical section lower diameter, a cone angle, an overflow pipe diameter, an overflow pipe length, an underflow pipe diameter and an underflow pipe length; the operating parameters include inlet speed and reflux ratio.
In the method for optimizing the separation performance of the liquid-solid hydrocyclone based on the transfer learning, in the fifth step, when the simulation calculation is performed, the corresponding simulation condition setting comprises the following steps:
Adopting pressure coupling; performing simulation calculation based on an implicit equation and an unsteady algorithm; constructing a flow volume function model and a gas-liquid two-phase environment; the inlet adopts a speed inlet, and the overflow port and the low-flow port adopt pressure outlets; the pressure and speed coupling adopts a pressure correction method, and the discrete format adopts PRESTO-! Format.
The method for optimizing the separation performance of the liquid-solid hydrocyclone based on the transfer learning, wherein after the step six, the method further comprises the following steps:
And inputting the obtained optimal separation efficiency value of the liquid-solid hydrocyclone into the data source domain to reduce the error when performing data migration calculation iteration.
The method for optimizing the separation performance of the liquid-solid hydrocyclone based on the transfer learning comprises the following steps of:
And constructing the relationship between the data source domain and the target domain by using the Euclidean distance formula, the cosine similarity formula, the probability mutual information formula, the information divergence formula, the JS distance formula, the maximum mean difference formula and the greedy distance formula.
The method for optimizing the separation performance of the liquid-solid hydrocyclone based on transfer learning comprises the following steps:
wherein d Euclidean represents the Euclidean distance, x and y respectively represent coordinates corresponding to a point x and a point y on a space model, and T is transposed matrix operation;
the cosine similarity formula is expressed as:
the cos (x, y) represents cosine similarity between the points x and y, and the x and y are absolute value operations of the points x and y respectively.
The method for optimizing the separation performance of the liquid-solid hydrocyclone based on transfer learning comprises the following steps of:
Wherein I (X; Y) represents the probability mutual confidence between the point X and the point Y, p (X, Y) represents the probability of having a common characteristic subspace between the point X and the point Y, p (X) represents the probability of having an independent subspace for the point X, and p (Y) represents the probability of having an independent subspace for the point Y;
The information divergence formula is expressed as:
where D KL (p||q) represents the information divergence between the region P and the region Q, P (x) represents the probability distribution of the point x at the region P, and Q (x) represents the probability distribution of the point x at the region Q.
The method for optimizing the separation performance of the liquid-solid hydrocyclone based on transfer learning comprises the following steps:
Wherein JSD (p|q) represents JS distance, D KL (p|m) represents information divergence between region P and region M, and D KL (q|m) represents information divergence between region Q and region M;
the maximum mean difference formula is expressed as:
wherein MMD 2 (X, Y) represents the maximum mean difference, Representing the mapping set corresponding to point x,/>Representing the mapping set corresponding to point y,/>Representing the regenerated kernel hilbert space.
The method for optimizing the separation performance of the liquid-solid hydrocyclone based on transfer learning comprises the following steps:
Wherein W p (P, Q) represents greedy distance, ρ (x, y) represents distance function between point x and point y in set M, Γ (P, Q) represents joint distribution of all the distributions with region P and region Q as edges in set M×M, dμ (x, y) represents distance function differential value between point x and point less.
The method for optimizing the separation performance of the liquid-solid hydrocyclone based on the transfer learning has the following beneficial effects:
1. According to the invention, based on the principle of transfer learning and based on the design theory and experience method of the liquid-solid hydrocyclone, the relevant structural parameters and efficiency comparison of the liquid-solid hydrocyclone are specifically and rapidly given, the structural parameters of the hydrocyclone to be optimized are determined according to the actual engineering conditions, and a foundation is laid for the parameter optimization of the liquid-solid hydrocyclone;
2. In the invention, the optimization of the operation parameters and the structural parameters is carried out step by utilizing a numerical simulation method, and the numerical simulation method is used for optimizing the performance of the liquid-solid hydrocyclone, thereby effectively solving the problems of complex design, huge cost and low efficiency of the traditional hydrocyclone. The separation performance of the liquid-solid separation hydrocyclone can be simply, economically and efficiently improved;
3. By adopting the migration data and experience data combined orthogonal numerical simulation parameter experiment method, the consistency of the numerical simulation result and the experiment result can be effectively ensured, and the feasibility of substituting the numerical simulation result for the experiment result is ensured; meanwhile, the influence of errors existing in the numerical simulation result on the optimization result can be effectively avoided by processing the orthogonal parameter test design method;
4. According to the invention, the structural design and parameter optimization of the liquid-solid hydrocyclone can be rapidly realized by utilizing data migration according to the actual engineering requirements, the separation performance of the hydrocyclone is obviously improved, the production efficiency is improved, the production cost is reduced, and the product quality is improved; and the data optimized by the experiment is fed back to the source field, so that the accuracy and the high efficiency of data migration under different working conditions can be continuously improved. Proved by experiments: the optimized result obtained by the invention can reduce energy consumption, improve concentrate concentration in overflow and obtain high-purity overflow concentrate.
Additional features and advantages of the disclosure will be set forth in the description which follows, or in part will be obvious from the description, or may be learned by practice of the techniques of the disclosure.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
FIG. 1 is a schematic block diagram of a method for optimizing the separation performance of a liquid-solid hydrocyclone based on transfer learning according to the present invention;
FIG. 2 is a flow chart of a method for optimizing the separation performance of a liquid-solid hydrocyclone based on transfer learning according to the present invention;
FIG. 3 is a schematic diagram of a liquid-solid hydrocyclone in accordance with the present invention;
FIG. 4 is a basic geometric model of a liquid-solid hydrocyclone in the present invention;
FIG. 5 is a top view of an orthogonally optimized inlet configuration of a liquid-solid hydrocyclone in accordance with the present invention;
FIG. 6 is a comparison of separation efficiency curves for a liquid-solid hydrocyclone in accordance with the present invention.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1 and 2, the present invention provides a method for optimizing separation performance of a liquid-solid hydrocyclone based on transfer learning, wherein the method comprises the following steps:
s101, training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, and modeling the working condition under an unknown mode through transfer learning so as to determine characteristic parameters of the liquid-solid hydrocyclone.
In this step, the above-mentioned characteristic parameters include physical parameters, geometric parameters, operation parameters, and separation efficiency.
Wherein, the physical parameters comprise inlet flow rate, particle diameter, inlet density difference and particle concentration. The geometric parameters include feed pipe diameter, cylindrical section length, conical section upper diameter, conical section lower diameter, cone angle, overflow pipe diameter, overflow pipe length, underflow pipe diameter and underflow pipe length. Further, the operating parameters include inlet speed and reflux ratio.
Specifically, in this step, training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, and modeling the working condition under an unknown mode through migration learning, where the method specifically includes the following steps:
and S1011, training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, wherein a data sample in the data source domain is provided with a label.
S1012, taking a new working condition to be tested in an unknown mode as a target field, and constructing a feature subspace according to data of a data source field and the target field based on a migration learning principle.
In the step of constructing the feature subspace according to the data of the data source domain and the target domain, the relationship between the data source domain and the target domain needs to be constructed by using a Euclidean distance formula, a cosine similarity formula, a probability mutual information formula, an information divergence formula, a JS distance formula, a maximum mean difference formula and a greedy distance formula.
Wherein, the Euclidean distance formula is expressed as:
Wherein d Euclidean represents the Euclidean distance, x and y respectively represent coordinates corresponding to a point x and a point y on the space model, and T is the transposed matrix operation.
Meanwhile, the cosine similarity formula is expressed as:
where cos (x, y) represents cosine similarity between points x and y, |x|, |y| are absolute value operations of points x and y, respectively.
Further, in this embodiment, defined on two probability distributions X and Y, X e X, Y e Y, the probability mutual information formula is:
Wherein I (X; Y) represents the probability mutual confidence between the point X and the point Y, p (X, Y) represents the probability of having a common characteristic subspace between the point X and the point Y, p (X) represents the probability of having an independent subspace for the point X, and p (Y) represents the probability of having an independent subspace for the point Y.
Further, the information divergence formula is expressed as:
Where D KL (p||q) represents the information divergence between the region P and the region Q, P (x) represents the probability distribution of the point x at the region P, and Q (x) represents the probability distribution of the point x at the region Q. It should be noted here that D KL (p||q) is used to represent the distance between the probability distribution P (x) and the probability distribution Q (x).
Further, the JS distance formula is expressed as:
Wherein JSD (p|q) represents JS distance, D KL (p|m) represents information divergence between region P and region M, and D KL (q|m) represents information divergence between region Q and region M.
Further, the maximum mean difference formula is expressed as:
wherein MMD 2 (X, Y) represents the maximum mean difference, Representing the mapping set corresponding to point x,/>Representing the mapping set corresponding to point y,/>Representing the regenerated kernel hilbert space.
Further, the greedy distance (WASSERSTEIN DISTANCE) is formulated as:
Where W p (P, Q) represents the greedy distance, ρ (x, y) represents the distance function between point x and point y in the set M, Γ (P, Q) represents the joint distribution of all distributions within the set M×M that are bordered by regions P and Q, dμ (x, y) represents the differential value of the distance function between point x and point y.
S102, acquiring empirical characteristic parameters of the liquid-solid hydrocyclone.
In this step, it should be noted that the empirical characteristic parameter is calculated by a conventional empirical calculation method.
S103, respectively carrying out numerical simulation by adopting a secondary orthogonal rotation combination test method according to the characteristic parameters of the liquid-solid hydrocyclone and the obtained empirical characteristic parameters.
In the step, the characteristic parameters of the liquid-solid hydrocyclone determined by the transfer learning and traditional method of the secondary orthogonal rotation combined test are adopted, and the scheme parameters are operated to perform numerical simulation and test optimization. Wherein, as described in the above step S101, the characteristic parameters include physical parameters, geometric parameters, and operation parameters.
S104, respectively determining and obtaining a geometric model of the liquid-solid hydrocyclone determined by transfer learning and a geometric model of the liquid-solid hydrocyclone determined by the empirical characteristic parameters through numerical simulation in the third step.
S105, using the principle of computational fluid dynamics, simulating and calculating the flow characteristics, air column characteristics, solid phase flow characteristics and simulated separation efficiency of the liquid-solid hydrocyclone, which are determined by transfer learning, of the gas-liquid two-phase flow corresponding to the geometric model of the liquid-solid hydrocyclone, and simulating and calculating the flow characteristics, air column characteristics, solid phase flow characteristics and simulated separation efficiency of the liquid-solid hydrocyclone, which are determined by empirical characteristic parameters, of the gas-liquid two-phase flow corresponding to the geometric model of the liquid-solid hydrocyclone.
In this step, when performing simulation calculation, the corresponding simulation condition settings include:
Adopting pressure coupling; performing simulation calculation based on an implicit equation and an unsteady algorithm; constructing a flow volume function model and a gas-liquid two-phase environment; the inlet adopts a speed inlet, and the overflow port and the low-flow port adopt pressure outlets; the pressure and speed coupling adopts a pressure correction method, and the discrete format adopts PRESTO-! Format.
Further, after the conditions are set, the pressure drop, tangential velocity, axial velocity and radial velocity of the gas-liquid two-phase flow and the gas-liquid-solid three-phase flow of the liquid-solid hydrocyclone can be calculated and determined.
S106, determining and obtaining the optimal separation efficiency value of the liquid-solid hydrocyclone according to the flow characteristic, the air column characteristic, the solid phase flow characteristic and the simulated separation efficiency of the liquid-solid hydrocyclone of each gas-liquid two-phase flow.
In this step, specifically, the method includes:
And inputting the obtained optimal separation efficiency value of the liquid-solid hydrocyclone into a data source domain to reduce errors when performing data migration calculation iteration.
The method is characterized in that characteristic parameters of the working condition liquid-solid hydrocyclone, including physical parameters, geometric parameters, operation parameters and separation efficiency, are fed back to a data source domain, so that the richness of data, the accuracy of transfer learning and the richness of the data source domain are further improved, and finally, the effect of obtaining an optimal solution by only one-time transfer is realized by continuously learning errors when data transfer is reduced.
In the present invention, please refer to fig. 3 and 4, for the liquid-solid hydrocyclone proposed in the present invention, 1 is the length of the cylindrical section of the hydrocyclone, 2 is the insertion depth of the overflow pipe of the hydrocyclone, 3 is the diameter of the overflow port, 4 is the wall thickness of the overflow pipe, 5 is the inlet width of the hydrocyclone, 6 is the basic diameter of the hydrocyclone, 7 is the cone angle, 8 is the diameter of the underflow port, and 9 is the inlet length of the hydrocyclone.
Meanwhile, as shown in fig. 5 and 6, the method for optimizing the separation performance of the liquid-solid hydrocyclone based on transfer learning provided by the invention has the following beneficial effects:
1. According to the invention, based on the principle of transfer learning and based on the design theory and experience method of the liquid-solid hydrocyclone, the relevant structural parameters and efficiency comparison of the liquid-solid hydrocyclone are specifically and rapidly given, the structural parameters of the hydrocyclone to be optimized are determined according to the actual engineering conditions, and a foundation is laid for the parameter optimization of the liquid-solid hydrocyclone;
2. In the invention, the optimization of the operation parameters and the structural parameters is carried out step by utilizing a numerical simulation method, and the numerical simulation method is used for optimizing the performance of the liquid-solid hydrocyclone, thereby effectively solving the problems of complex design, huge cost and low efficiency of the traditional hydrocyclone. The separation performance of the liquid-solid separation hydrocyclone can be simply, economically and efficiently improved;
3. By adopting the migration data and experience data combined orthogonal numerical simulation parameter experiment method, the consistency of the numerical simulation result and the experiment result can be effectively ensured, and the feasibility of substituting the numerical simulation result for the experiment result is ensured; meanwhile, the influence of errors existing in the numerical simulation result on the optimization result can be effectively avoided by processing the orthogonal parameter test design method;
4. According to the invention, the structural design and parameter optimization of the liquid-solid hydrocyclone can be rapidly realized by utilizing data migration according to the actual engineering requirements, the separation performance of the hydrocyclone is obviously improved, the production efficiency is improved, the production cost is reduced, and the product quality is improved; and the data optimized by the experiment is fed back to the source field, so that the accuracy and the high efficiency of data migration under different working conditions can be continuously improved. Proved by experiments: the optimized result obtained by the invention can reduce energy consumption, improve concentrate concentration in overflow and obtain high-purity overflow concentrate.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1.A method for optimizing the separation performance of a liquid-solid hydrocyclone based on transfer learning, comprising the steps of:
Step one: training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, and modeling the working condition under an unknown mode through migration learning to determine characteristic parameters of the liquid-solid hydrocyclone;
step two: acquiring empirical characteristic parameters of the liquid-solid hydrocyclone;
Step three: respectively carrying out numerical simulation by adopting a secondary orthogonal rotation combination test method according to the characteristic parameters of the liquid-solid hydrocyclone and the acquired empirical characteristic parameters;
step four: respectively determining a geometric model of the liquid-solid hydrocyclone determined by transfer learning and a geometric model of the liquid-solid hydrocyclone determined by the empirical characteristic parameters through numerical simulation in the third step;
Step five: using the computational fluid dynamics principle, performing simulation calculation on the flow characteristics, the air column characteristics, the solid phase flow characteristics and the simulated separation efficiency of the liquid-solid hydrocyclone, which are determined by transfer learning, of the gas-liquid two-phase flow corresponding to the geometric model of the liquid-solid hydrocyclone, and performing simulation calculation on the flow characteristics, the air column characteristics, the solid phase flow characteristics and the simulated separation efficiency of the liquid-solid hydrocyclone, which are determined by empirical characteristic parameters, of the gas-liquid two-phase flow corresponding to the geometric model of the liquid-solid hydrocyclone;
Step six: and determining and obtaining the optimal separation efficiency value of the liquid-solid hydrocyclone according to the flow characteristic, the air column characteristic, the solid phase flow characteristic and the simulated separation efficiency of the liquid-solid hydrocyclone of each gas-liquid two-phase flow.
2. The method for optimizing separation performance of a liquid-solid hydrocyclone based on transfer learning according to claim 1, wherein in the first step, training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, the method for modeling the working condition under the unknown mode by transfer learning specifically comprises the following steps:
Training and establishing a data source domain of the liquid-solid hydrocyclone under each working condition, wherein a data sample in the data source domain is provided with a label;
And taking a new working condition to be tested in an unknown mode as a target field, and constructing a characteristic subspace according to the data of the data source field and the target field based on a migration learning principle.
3. The method for optimizing liquid-solid hydrocyclone separation performance based on transfer learning of claim 2, wherein in the first step, the characteristic parameters include physical parameters, geometric parameters, operation parameters and separation efficiency;
Wherein the physical parameters comprise inlet flow rate, particle size, inlet density difference and particle concentration; the geometric parameters comprise a feeding pipe diameter, a cylindrical section length, a conical section upper diameter, a conical section lower diameter, a cone angle, an overflow pipe diameter, an overflow pipe length, an underflow pipe diameter and an underflow pipe length; the operating parameters include inlet speed and reflux ratio.
4. The method for optimizing separation performance of a liquid-solid hydrocyclone based on transfer learning of claim 2, wherein in the fifth step, when performing simulation calculation, the corresponding simulation condition setting comprises:
Adopting pressure coupling; performing simulation calculation based on an implicit equation and an unsteady algorithm; constructing a flow volume function model and a gas-liquid two-phase environment; the inlet adopts a speed inlet, and the overflow port and the low-flow port adopt pressure outlets; the pressure and speed coupling adopts a pressure correction method, and the discrete format adopts PRESTO-! Format.
5. The method for optimizing liquid-solid hydrocyclone separation performance based on transfer learning of claim 2, further comprising, after the sixth step:
And inputting the obtained optimal separation efficiency value of the liquid-solid hydrocyclone into the data source domain to reduce the error when performing data migration calculation iteration.
6. The method for optimizing separation performance of a liquid-solid hydrocyclone based on transfer learning of claim 2, wherein the step of constructing a feature subspace from data of a data source domain and a target domain based on transfer learning principle comprises:
And constructing the relationship between the data source domain and the target domain by using the Euclidean distance formula, the cosine similarity formula, the probability mutual information formula, the information divergence formula, the JS distance formula, the maximum mean difference formula and the greedy distance formula.
7. The method for optimizing liquid-solid hydrocyclone separation performance based on transfer learning of claim 6, wherein the euclidean distance formula is expressed as:
wherein d Euclidean represents the Euclidean distance, x and y respectively represent coordinates corresponding to a point x and a point y on a space model, and T is transposed matrix operation;
the cosine similarity formula is expressed as:
where cos (x, y) represents cosine similarity between points x and y, |x|, |y| are absolute value operations of points x and y, respectively.
8. The method for optimizing liquid-solid hydrocyclone separation performance based on transfer learning of claim 7, wherein the probability mutual information formula is:
Wherein I (X; Y) represents the probability mutual confidence between the point X and the point Y, p (X, Y) represents the probability of having a common characteristic subspace between the point X and the point Y, p (X) represents the probability of having an independent subspace for the point X, and p (Y) represents the probability of having an independent subspace for the point Y;
The information divergence formula is expressed as:
where D KL (p||q) represents the information divergence between the region P and the region Q, P (x) represents the probability distribution of the point x at the region P, and Q (x) represents the probability distribution of the point x at the region Q.
9. The method for optimizing liquid-solid hydrocyclone separation performance based on transfer learning of claim 8, wherein the JS distance equation is expressed as:
Wherein JSD (p|q) represents JS distance, D KL (p|m) represents information divergence between region P and region M, and D KL (q|m) represents information divergence between region Q and region M;
the maximum mean difference formula is expressed as:
wherein MMD 2 (X, Y) represents the maximum mean difference, Representing the mapping set corresponding to point x,/>Representing the mapping set corresponding to point y,/>Representing the regenerated kernel hilbert space.
10. The method for optimizing liquid-solid hydrocyclone separation performance based on transfer learning of claim 9, wherein the greedy distance formula is expressed as:
Where W p (P, Q) represents the greedy distance, ρ (x, y) represents the distance function between point x and point y in the set M, Γ (P, Q) represents the joint distribution of all distributions within the set M×M that are bordered by regions P and Q, dμ (x, y) represents the differential value of the distance function between point x and point y.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111323572.XA CN114036670B (en) | 2021-11-09 | 2021-11-09 | Method for optimizing separation performance of liquid-solid hydrocyclone based on transfer learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111323572.XA CN114036670B (en) | 2021-11-09 | 2021-11-09 | Method for optimizing separation performance of liquid-solid hydrocyclone based on transfer learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114036670A CN114036670A (en) | 2022-02-11 |
| CN114036670B true CN114036670B (en) | 2024-04-26 |
Family
ID=80143714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111323572.XA Active CN114036670B (en) | 2021-11-09 | 2021-11-09 | Method for optimizing separation performance of liquid-solid hydrocyclone based on transfer learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114036670B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112517258A (en) * | 2020-11-05 | 2021-03-19 | 上海明罗石油天然气工程有限公司 | Novel liquid-liquid separation hydrocyclone |
| CN113011114A (en) * | 2021-03-25 | 2021-06-22 | 赣江新区澳博颗粒科技研究院有限公司 | Numerical simulation method for optimizing separation performance of liquid-solid hydrocyclone |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10345764B2 (en) * | 2015-04-27 | 2019-07-09 | Baker Hughes, A Ge Company, Llc | Integrated modeling and monitoring of formation and well performance |
| CN110780146B (en) * | 2019-12-10 | 2021-04-27 | 武汉大学 | Transformer fault identification and positioning diagnosis method based on multi-stage transfer learning |
-
2021
- 2021-11-09 CN CN202111323572.XA patent/CN114036670B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112517258A (en) * | 2020-11-05 | 2021-03-19 | 上海明罗石油天然气工程有限公司 | Novel liquid-liquid separation hydrocyclone |
| CN113011114A (en) * | 2021-03-25 | 2021-06-22 | 赣江新区澳博颗粒科技研究院有限公司 | Numerical simulation method for optimizing separation performance of liquid-solid hydrocyclone |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114036670A (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bing et al. | Numerical simulation and experimental study on internal and external characteristics of novel Hydrocyclones | |
| CN108536979B (en) | Underflow concentration prediction method based on thickener mechanism model | |
| Zhao et al. | Fluidization characteristics of a fine magnetite powder fluidized bed for density-based dry separation of coal | |
| CN109868157A (en) | A kind of double-field coupled dehydration device and parameter optimization method | |
| CN114036670B (en) | Method for optimizing separation performance of liquid-solid hydrocyclone based on transfer learning | |
| Zhang et al. | Simulation analysis on the separation performance of spiral inlet hydrocyclone | |
| CN105843998B (en) | The numerical simulation of optimum method of solid-solid separation hydrocyclone parameter | |
| Xu et al. | Simulation analysis of multiphase flow and performance of hydrocyclones at different atmospheric pressures | |
| Nakhaei et al. | Recovery and grade prediction of pilot plant flotation column concentrate by a hybrid neural genetic algorithm | |
| Xu et al. | CFD simulations to portray the bubble distribution and the hydrodynamics in an annulus sparged air‐lift bioreactor | |
| CN100570327C (en) | Measure the support vector machine method that hydrocyclone Separation of Solid and Liquid overflow granularity distributes | |
| Saraswathi K et al. | Random forest and autoencoder data-driven models for prediction of dispersed-phase holdup and drop size in rotating disc contactors | |
| Li et al. | Experimental and numerical study of a hydrocyclone with the modification of geometrical structure | |
| Vieira et al. | Study of the Performance of a Novel Hydrocyclone Built in the Configurations of the Classical Families | |
| Podgorska | Multiphase particulate systems in turbulent flows: fluid-liquid and solid-liquid dispersions | |
| CN113011114A (en) | Numerical simulation method for optimizing separation performance of liquid-solid hydrocyclone | |
| CN115994395A (en) | Three-dimensional pipeline generation method, device and product based on drawing conversion | |
| CN112613252B (en) | Energy-saving operation method of absorption tower stirrer | |
| Svarovsky | Hydrocyclones | |
| Meng et al. | Turbulence model development for flotation cells based on piezoelectric sensor measurements | |
| Xu et al. | The effect of bubble size on oil-water separation efficiency for a novel oil-water separation column | |
| Su et al. | Effect of the Axially Inserted Solid Rod on the Flow Field Characteristics and Separation Performance of a Hydrocyclone | |
| Shen et al. | Numerical simulation of the flow field in a dense-media cyclone | |
| Liu et al. | Influence mechanism of hydrocyclone main diameter on separation performance | |
| Chen et al. | Effect of gas flow rate on separation efficiency at different scaling scales of cyclone separators |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |