CN111210877A - Method and device for deducing physical property parameters - Google Patents
Method and device for deducing physical property parameters Download PDFInfo
- Publication number
- CN111210877A CN111210877A CN202010006973.1A CN202010006973A CN111210877A CN 111210877 A CN111210877 A CN 111210877A CN 202010006973 A CN202010006973 A CN 202010006973A CN 111210877 A CN111210877 A CN 111210877A
- Authority
- CN
- China
- Prior art keywords
- parameters
- physical property
- neural network
- network model
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000000704 physical effect Effects 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000000463 material Substances 0.000 claims abstract description 60
- 238000003062 neural network model Methods 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000005457 optimization Methods 0.000 claims abstract description 39
- 230000008569 process Effects 0.000 claims abstract description 30
- 238000004088 simulation Methods 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 239000013078 crystal Substances 0.000 claims description 56
- 238000012544 monitoring process Methods 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 7
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 2
- 230000004913 activation Effects 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 abstract description 3
- 230000002349 favourable effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C10/00—Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Crystals, And After-Treatments Of Crystals (AREA)
Abstract
The application discloses a method and a device for deducing physical property parameters, which are used for solving the problem that accurate physical property parameters of materials are difficult to obtain under certain specific conditions, so that simulation results obtained by simulation software are influenced. According to the method, a training data set is established through simulation software according to preset physical parameters of a material to be inferred, and a neural network model is trained; determining actual result parameters corresponding to the material to be inferred under the preset process conditions; and determining the actual physical property parameters of the material to be inferred by adopting the neural network model and a preset numerical optimization algorithm according to the actual result parameters. The method can obtain the physical property parameters of the material as accurate as possible by combining a numerical optimization algorithm on the basis of machine learning, and is favorable for accurately grasping the physical property parameters, so that the consistency between a simulation result and an actual result is enhanced.
Description
Technical Field
The application relates to the technical field of simulated crystal growth, in particular to a method and a device for deducing physical property parameters.
Background
In industrial production, the physical parameters of the material often have a great influence on the production process and the production result. The physical property parameter of the material represents parameter data indicating whether the material can meet production requirements in the aspects of manufacturing, performance and the like.
Especially in the process of simulating crystal growth, incorrect material physical parameters can cause inaccurate prediction of result parameters such as temperature distribution, crystal convexity, crystal shape and the like in the process of crystal growth, thereby causing larger error between the simulation result and the actual result.
Currently, the physical parameters of a material are determined from a material supplier. However, the accuracy of the data given by the material supplier may be low. Especially for the physical parameters of the material required in the crystal growth process, since the temperature in the crystal growth process is as high as thousands of degrees centigrade, it is difficult to obtain accurate data of the physical parameters at high temperature, which is not favorable for the accurate simulation of the crystal growth process.
Disclosure of Invention
The embodiment of the application provides a method and a device for deducing physical property parameters, which are used for solving the problem that the physical property parameters of a material are difficult to obtain accurately under specific conditions such as high temperature, so that simulation results obtained by simulation software are influenced.
The method for deducing the physical property parameter provided by the embodiment of the application comprises the following steps:
establishing a training data set through simulation software according to preset physical parameters of a material to be inferred, and training a neural network model;
determining actual result parameters corresponding to the material to be inferred under preset process conditions;
and determining the actual physical property parameters of the material to be inferred by adopting the neural network model and a preset numerical optimization algorithm according to the actual result parameters.
The device of inference rerum natura parameter that this application embodiment provided includes:
the training module is used for establishing a training data set through simulation software according to preset physical parameters of a material to be inferred and training a neural network model;
the first determination module is used for determining actual result parameters corresponding to the material to be inferred under the preset process condition;
and the second determination module is used for determining the actual physical property parameters of the material to be inferred by adopting the neural network model and a preset numerical optimization algorithm according to the actual result parameters.
The embodiment of the application provides a method and a device for deducing physical property parameters.
By the method, the actual physical property parameters of the material can be obtained as accurately as possible according to the actual result parameters and through multiple iterations under the condition that the physical property parameters of the material are difficult to obtain by combining a numerical optimization algorithm on the basis of machine learning.
Particularly, in the crucible used for crystal growth, the method is not limited by the high temperature of the crystal growth environment and does not need to worry about the difficulty in obtaining the physical parameters of the crucible. Even under the condition of high temperature, the most accurate physical property parameters of the material can be determined by back-stepping according to the result parameters of crystal growth, thereby further perfecting the simulation result parameters of the crystal obtained by simulation.
The physical property parameters obtained by the method can make simulation result parameters obtained by simulation software according to the physical property parameters consistent with actual result parameters as much as possible, so as to reduce errors between simulation results and actual results and achieve consistency between the simulation results and the actual results.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow chart of a method for inferring physical parameters provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of an optimization principle of an L-BFGS algorithm provided in an embodiment of the present application;
3(a) to 3(c) are schematic diagrams of the results of the optimization of physical property parameters of the crucible provided by the embodiment of the present application;
fig. 4(a) -4 (b) are schematic diagrams illustrating relationships between simulation result parameters and actual result parameters provided in the embodiments of the present application;
fig. 5 is a schematic structural diagram of an apparatus for estimating a physical property parameter according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, 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 application.
Fig. 1 is a flowchart of a method for inferring a physical property parameter according to an embodiment of the present application, which specifically includes the following steps:
s101: and establishing a training data set through simulation software according to the preset physical property parameters of the material to be deduced, and training a neural network model.
In the embodiment of the present application, the relationship between the physical property parameter of the material and the corresponding result parameter can be represented by training the neural network model.
Specifically, the training process of the neural network model includes:
firstly, determining corresponding simulation result parameters through simulation software according to preset physical property parameters.
The server can determine different value ranges corresponding to the physical property parameters according to the preset physical property parameters. And determining possible values of the physical property parameters within the corresponding value ranges of the physical property parameters. Different values of the physical parameters are combined to form a large amount of combined data.
And inputting each combined data into simulation software, and performing simulation through the simulation software to respectively obtain corresponding simulation result parameters under preset process conditions for each combined data. The acquisition of the simulation result parameters of the crystal growth can be acquired through simulation software for simulating the crystal growth. For example, simulation software Virtual Reactor, etc.
Taking the crystal growth process as an example, determining different physical property parameters of thermal conductivity lambda, electrical conductivity sigma and surface emissivity epsilon of the crucible, and simulating through simulation software, so as to determine simulation result parameters of crystal growth corresponding to the corresponding physical property parameters, including temperature T of a plurality of preset monitoring points corresponding to a plurality of preset moments in the crystal growth stage, thickness H of crystal growth and convexity C of the crystal. Wherein the convexity of the crystal represents the difference between the thickness of the middle and the thickness of the edge of the crystal.
For convenience of description, the crucible used in the crystal growth process will be described below as an example. However, this does not limit the scope of application of the present invention, and the present method is not limited to the estimation of physical parameters of the crucible, and is also applicable to other production processes having the same principle.
And secondly, establishing a training data set.
The server can establish a training data set according to the determined simulation result parameters and the values of the corresponding physical property parameters.
Taking a crucible adopted in the crystal growth process as an example, the server can establish a training data set according to physical parameters of the crucible, such as thermal conductivity lambda, electrical conductivity sigma and surface emissivity epsilon, and simulation result parameters of crystal growth, including the temperature T of a plurality of preset monitoring points corresponding to a plurality of preset moments in the crystal growth stage, the thickness H of crystal growth and the convexity C of the crystal.
And thirdly, training a neural network model by adopting the established training data set.
Specifically, the server may perform model training by using the physical property parameters of the material as input data for neural network model training and using the corresponding simulation result parameters as output data for neural network model training. Through machine learning, the neural network model can learn the functional relationship between the physical property parameters of the material and the corresponding simulation result parameters under the preset process conditions.
In one embodiment, the server may employ a BP neural network model for training of the neural network model. In the training process, the training data set may be divided into a training set and a test set, wherein if the training data set is 300 groups, the training set may include 200 groups of training data, and the test set may include 100 groups of training data. The server can train the BP neural network model by adopting the data of the training set, and verify the accuracy and the like of the trained BP neural network model by adopting the data of the test set.
Specifically, the trained BP neural network model may include three fully-connected layers, for a total of 33 neurons. Wherein, the three full-connection layers respectively comprise 16 neurons, 16 neurons and 5 neurons. Taking the crystal growth process as an example, the last 5 neurons can respectively correspond to the temperature of three preset monitoring points in the crystal growth result parameters, the thickness of the crystal and the convexity of the crystal.
And when training the BP neural network model, the activation function can adopt Relu, the optimization mode can adopt Adam, and the loss function can adopt average absolute error.
S102: and determining actual result parameters corresponding to the material to be inferred under the preset process conditions.
In the embodiment of the application, the server may determine the corresponding actual result parameter according to the application of the material to be inferred in the actual production process with the preset process condition, so as to infer the actual physical property parameter of the material to be inferred according to the actual result parameter in the following. The material to be inferred refers to a material of which the accurate physical property parameters need to be determined, and the preset process conditions represent operations such as pressurization, temperature rise and the like adopted in the production process and can be set as required.
The server can determine a plurality of actual result parameters corresponding to the material to be inferred under different preset process conditions, so that the physical property parameters of the material to be inferred are optimized through the actual result parameters, and more accurate physical property parameters of the material to be inferred are obtained.
In one embodiment, if the material to be inferred is a crucible used in a crystal growth process, the physical parameters of the crucible may include thermal conductivity, electrical conductivity, surface emissivity, etc., and the resulting parameters of the crystal produced by the crucible may include temperature of a predetermined monitoring point of the crystal, thickness of the crystal, convexity of the crystal, etc.
It should be noted that, in the embodiment of the present application, there is no sequential limitation between step 101 and step 102, and step 101 and step 102 may also be performed simultaneously.
S103: and determining the actual physical property parameters of the material to be inferred by adopting a neural network model and a preset numerical optimization algorithm according to the actual result parameters.
In the embodiment of the application, the actual physical property parameters of the material to be inferred can be determined through reverse estimation by the trained neural network model according to the actual result parameters corresponding to the material to be inferred. The process of determining the physical property parameters of the material to be inferred through reverse estimation is realized through a preset numerical optimization algorithm.
Specifically, the server can determine a plurality of initial values of the physical property parameters of the material, and determine a prediction result parameter obtained by predicting each initial value through a neural network model. And the server can evaluate the correlation between the predicted result parameters and the actual result parameters corresponding to the initial values through the objective function so as to perform iterative optimization on the initial values according to the evaluation results.
And then, the server can perform iterative optimization on each initial value by adopting an optimizer in the L-BFGS-B algorithm according to the fitting result between the predicted result parameter and the actual result parameter until the iteration is finished.
And finally, determining the optimal physical property parameter as the actual physical property parameter of the material to be inferred according to the optimization result obtained by carrying out iterative optimization on each initial value.
Further, the server may determine an initial value of the physical property parameter according to a preset range. And, in order to make the initial values to achieve full coverage of the preset range, and simultaneously to narrow the difference between the initial values as much as possible, the number of the determined initial values should be sufficient. For example, 10000 initial values may be determined.
The numerical optimization algorithm comprises a gradient algorithm and a Newton algorithm, the gradient algorithm is low in convergence speed and low in calculation efficiency, and is prone to falling into local minimum points. Compared with a gradient algorithm, the Newton algorithm has the advantages of high precision, high convergence rate and the like, but the Newton algorithm needs more storage variables, and the Hessian matrix and the inverse of the Hessian matrix are difficult to obtain.
Therefore, in order to avoid direct solving of the Hessian matrix, a quasi-newton class algorithm L-BFGS-B algorithm is adopted in the embodiment of the application. In the L-BFGS-B algorithm, a positive definite matrix without a second derivative can be constructed
Wherein HkIs an approximate Hessian matrix. Thus, by the configuration BkAnd then, the inverse of the Hessian matrix can be directly obtained to obtain the matrix.
Fig. 2 is a schematic diagram of the optimization principle of the L-BFGS algorithm. In fig. 2, the three circles at the top of the curve represent the initial values, the two circles in the middle represent the locally optimal solution, and the large circle at the bottom represents the globally optimal solution. Therefore, through iterative optimization, two initial values only find a local optimal solution, and one initial value finds a global optimal solution.
Further, the server may be based on an objective function
And determining the correlation between the result parameters predicted by the neural network model and the actual result parameters. Wherein, taking the crystal growth process as an example, F represents TiH, C and tiH, c, TiThe temperature of each preset monitoring point of the crystal predicted by the neural network model is represented, H represents the thickness of the crystal predicted by the neural network model, C represents the convexity of the crystal predicted by the neural network model, tiThe actual temperature of each preset monitoring point of the crystal is shown, h represents the actual thickness of the crystal, and c represents the actual convexity of the crystal. Fitting between the two can be achieved by minimizing the square of the difference between the predicted outcome parameter and the actual outcome parameter of the neural network model, i.e., F.
Further, in the process of fitting the result parameters predicted by the neural network model and the actual result parameters, the iterative update formula is mk+1＝mk+akPk. Wherein m represents a physical property parameter, akRepresenting the step size of the iteration, PkIndicates the direction of iteration and k indicates the number of iterations.
The selection of the search step length has an important influence on the process of deducing the physical property parameters of the material. If the search step length is too small, the local optimization capability is strong, but the local optimization is easy to fall into a local optimal solution, the convergence speed is low, and the solution precision is low. If the search step is too large, the stability of the iterative process may be compromised and the optimal value may be easily skipped.
In one possible implementation, the size of the step size may be determined using a line search algorithm. The algorithm can simply select smaller and smaller step sizes until iteration of the initial value is completed. By the dynamic step size in the algorithm, the problem of overlarge or undersize step size can be solved, and the determination of an optimal value is facilitated.
During each iteration, each initial value is updated and adjusted through corresponding optimization. In the iterative optimization process, the conditions for iteration termination may include: objective function
Less than a preset value, or the iteration has reached a maximum number of iterations. Thus, all optimized initial values are available until all iterations are completed.
Further, when the optimal physical property parameters are determined, different values in the optimization result can be counted respectively according to the optimization result obtained after the initial values are subjected to iterative optimization. Then, the optimization result with the largest count can be determined as the optimal physical property parameter.
Fig. 3(a) to 3(c) are schematic diagrams illustrating the results of optimizing physical parameters of the crucible according to the embodiment of the present application.
Fig. 3(a) shows the result of optimizing the thermal conductivity of the crucible, in which the abscissa represents the value of the thermal conductivity and the ordinate represents the count. Fig. 3(b) shows the result of optimizing the electrical conductivity of the crucible, in which the abscissa represents the value of the electrical conductivity and the ordinate represents the count. Fig. 3(c) shows the result of optimizing the surface emissivity of the crucible, wherein the abscissa represents the value of the surface emissivity and the ordinate represents the count.
According to the ordinate of the three bar charts, the abscissa corresponding to the column with the maximum ordinate in each chart, namely the abscissa with the highest column distribution frequency, can be determined, and the abscissa is respectively the optimal thermal conductivity, the optimal electrical conductivity and the optimal surface emissivity of the crucible.
Fig. 4(a) to fig. 4(b) are schematic diagrams illustrating the relationship between simulation results and actual results provided in the embodiments of the present application. In both fig. 4(a) and 4(b), the abscissa indicates the distance from the center of the crystal in millimeters, and the ordinate indicates the crystal growth rate in micrometers per hour.
In fig. 4(a), the solid line represents the actual result of crystal growth, and the dotted line represents the simulation result obtained by the simulation software for the physical property parameter that has not been optimized. In fig. 4(b), the solid line represents the actual result of crystal growth, and the dotted line represents the simulation result corresponding to the optimized physical property parameter obtained by the simulation software.
It can be known that, under inaccurate physical parameters, the error between the simulation result obtained by the simulation software and the actual result is large, and the simulation result cannot truly reflect the actual result. After the physical property parameters are optimized, the error between the simulation result and the actual result can be reduced, so that the simulation result is basically consistent with the actual result.
In the embodiment of the application, the optimal solution of the physical property parameters of the material can be determined as the actual physical property parameters of the material by training a neural network model and performing back-stepping by adopting a numerical optimization algorithm. In this way, the physical property parameters of the material can be obtained as accurately as possible under the condition that the physical property parameters of the material are difficult to know, and the error between the simulation result and the actual result can be favorably reduced.
Based on the same inventive concept, the method for inferring physical property parameters provided in the embodiments of the present application further provides a device for inferring physical property parameters, as shown in fig. 5.
Fig. 5 is a schematic structural diagram of an apparatus for inferring a physical property parameter according to an embodiment of the present application, which specifically includes:
the training module 401 establishes a training data set through simulation software according to preset physical property parameters of a material to be inferred, and trains a neural network model;
a second determining module 402, configured to determine an actual result parameter corresponding to the material to be inferred under a preset process condition;
and a third determining module 403, configured to determine an actual physical property parameter of the material to be inferred by using the neural network model and a preset numerical optimization algorithm according to the actual result parameter.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method of inferring a property parameter, comprising:
establishing a training data set through simulation software according to preset physical parameters of a material to be inferred, and training a neural network model;
determining actual result parameters corresponding to the material to be inferred under preset process conditions;
and determining the actual physical property parameters of the material to be inferred by adopting the neural network model and a preset numerical optimization algorithm according to the actual result parameters.
2. The method of claim 1, wherein the establishing a training data set and training the neural network model by simulation software according to the preset physical parameters of the material to be inferred comprises:
respectively determining the value of each physical property parameter from a preset value range according to a plurality of preset physical property parameters, and determining the value of a corresponding simulation result parameter under a preset process condition by adopting simulation software;
establishing a training data set according to the determined simulation result parameters and the values of the corresponding preset physical property parameters;
and training the neural network model by adopting the established training data set.
3. The method of claim 2, wherein the neural network model is a BP neural network model, and the BP neural network model comprises 3 fully-connected layers, and the 3 fully-connected layers comprise 16 neurons, and 5 neurons, respectively.
4. The method according to claim 3, wherein the neural network model uses Relu as an activation function, Adam as an optimization method, and the mean absolute error as a loss function.
5. The method of claim 1, wherein the material to be inferred is a crucible;
the actual physical property parameter includes at least any one of: thermal conductivity, electrical conductivity, surface emissivity;
the actual result parameters at least comprise any one of the following items: the temperature of the preset monitoring point of the crystal, the thickness of the crystal and the convexity of the crystal.
6. The method of claim 5, wherein determining the actual physical property parameter of the material to be inferred according to the actual result parameter by using the neural network model and a preset numerical optimization algorithm comprises:
determining a plurality of initial values of physical property parameters;
determining a prediction result parameter corresponding to the plurality of initial values by adopting the neural network model;
evaluating the prediction result parameters by adopting an L-BFGS-B algorithm according to a preset target function, and performing iterative optimization on the plurality of initial values;
and determining the optimal physical property parameter as the actual physical property parameter of the material to be inferred according to the optimization result obtained after iterative optimization is carried out on the plurality of initial values.
7. The method of claim 6, wherein evaluating the predicted outcome parameter according to a predetermined objective function comprises:
according to
Determining the correlation between the predicted result parameter obtained by the neural network model and the actual result parameter, wherein F represents TiH, C and tiH, c, TiThe temperature of each preset monitoring point of the crystal predicted by the neural network model is represented, H represents the thickness of the crystal predicted by the neural network model, C represents the convexity of the crystal predicted by the neural network model, tiThe actual temperature of each preset monitoring point of the crystal is shown, h represents the actual thickness of the crystal, and c represents the actual convexity of the crystal.
8. The method of claim 7, wherein the iterative optimization of the initial values is performed usingIs given as mk+1＝mk+akPkWherein m represents a physical property parameter, akRepresenting the step size of the iteration, PkIndicates the direction of iteration and k indicates the number of iterations.
9. The method of claim 6, wherein determining the optimal physical property parameter according to an optimization result obtained by iteratively optimizing the plurality of initial values comprises:
determining an optimization result obtained after iteration is carried out on the plurality of initial values;
respectively counting the optimization results with different values;
and determining the optimization result with the largest count as the optimal physical property parameter.
10. An apparatus for inferring a property parameter, comprising:
the training module is used for establishing a training data set through simulation software according to preset physical parameters of a material to be inferred and training a neural network model;
the first determination module is used for determining actual result parameters corresponding to the material to be inferred under the preset process condition;
and the second determination module is used for determining the actual physical property parameters of the material to be inferred by adopting the neural network model and a preset numerical optimization algorithm according to the actual result parameters.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006973.1A CN111210877B (en) | 2020-01-03 | 2020-01-03 | Method and device for deducing physical parameters |
| PCT/CN2020/130763 WO2021135719A1 (en) | 2020-01-03 | 2020-11-23 | Method and apparatus for deducing physical property parameter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006973.1A CN111210877B (en) | 2020-01-03 | 2020-01-03 | Method and device for deducing physical parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111210877A true CN111210877A (en) | 2020-05-29 |
| CN111210877B CN111210877B (en) | 2023-11-24 |
Family
ID=70789452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010006973.1A Active CN111210877B (en) | 2020-01-03 | 2020-01-03 | Method and device for deducing physical parameters |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111210877B (en) |
| WO (1) | WO2021135719A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021135719A1 (en) * | 2020-01-03 | 2021-07-08 | 山东天岳先进科技股份有限公司 | Method and apparatus for deducing physical property parameter |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033189A (en) * | 2015-03-16 | 2016-10-19 | 徐州工程学院 | Flight robot pose nerve network prediction controller |
| CN108256689A (en) * | 2018-02-06 | 2018-07-06 | 华中科技大学 | A kind of neural network prediction method of non-crystaline amorphous metal thermoplastic forming performance |
| CN109034388A (en) * | 2018-07-27 | 2018-12-18 | 湖北中烟工业有限责任公司 | A kind of prediction model of cigarette material and mainstream smoke constituents based on Genetic Algorithm Optimized Neural Network |
| CN109541143A (en) * | 2018-11-28 | 2019-03-29 | 西安建筑科技大学 | A kind of prediction technique that the constituent element clinker actual constituent transitivity containing volatilization changes over time |
| CN110009150A (en) * | 2019-04-02 | 2019-07-12 | 中国石油大学(华东) | The compact reservoir physical parameter intelligent Forecasting of data-driven |
| CN110619393A (en) * | 2019-09-27 | 2019-12-27 | 上海交通大学 | Traffic simulation software parameter calibration method, system and medium based on learning algorithm |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109557126B (en) * | 2018-12-07 | 2021-03-26 | 东北大学 | Measuring device for soil thermophysical property parameters and seepage parameters |
| CN109521051B (en) * | 2018-12-07 | 2021-02-09 | 东北大学 | Soil thermophysical property parameter identification method |
| CN110443364A (en) * | 2019-06-21 | 2019-11-12 | 深圳大学 | A kind of deep neural network multitask hyperparameter optimization method and device |
| CN111210877B (en) * | 2020-01-03 | 2023-11-24 | 山东天岳先进科技股份有限公司 | Method and device for deducing physical parameters |
-
2020
- 2020-01-03 CN CN202010006973.1A patent/CN111210877B/en active Active
- 2020-11-23 WO PCT/CN2020/130763 patent/WO2021135719A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033189A (en) * | 2015-03-16 | 2016-10-19 | 徐州工程学院 | Flight robot pose nerve network prediction controller |
| CN108256689A (en) * | 2018-02-06 | 2018-07-06 | 华中科技大学 | A kind of neural network prediction method of non-crystaline amorphous metal thermoplastic forming performance |
| CN109034388A (en) * | 2018-07-27 | 2018-12-18 | 湖北中烟工业有限责任公司 | A kind of prediction model of cigarette material and mainstream smoke constituents based on Genetic Algorithm Optimized Neural Network |
| CN109541143A (en) * | 2018-11-28 | 2019-03-29 | 西安建筑科技大学 | A kind of prediction technique that the constituent element clinker actual constituent transitivity containing volatilization changes over time |
| CN110009150A (en) * | 2019-04-02 | 2019-07-12 | 中国石油大学(华东) | The compact reservoir physical parameter intelligent Forecasting of data-driven |
| CN110619393A (en) * | 2019-09-27 | 2019-12-27 | 上海交通大学 | Traffic simulation software parameter calibration method, system and medium based on learning algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 汤秀华;孙兴波;: "基于BP神经网络的结晶成核速率预测" * |
| 王文娟;曹俊兴;张元标;王小权;: "基于微粒群算法的神经网络储层物性参数预测" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021135719A1 (en) * | 2020-01-03 | 2021-07-08 | 山东天岳先进科技股份有限公司 | Method and apparatus for deducing physical property parameter |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021135719A1 (en) | 2021-07-08 |
| CN111210877B (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111414977A (en) | Weighted integration temperature sensitive point combination selection method for machine tool spindle thermal error modeling | |
| CN112926152B (en) | Digital twin-driven thin-wall part clamping force precise control and optimization method | |
| CN108563895B (en) | Interval model correction method for gear assembly body considering correlation | |
| CN110442911B (en) | High-dimensional complex system uncertainty analysis method based on statistical machine learning | |
| CN110555231A (en) | Dynamic simulation model correction method | |
| CN108460462A (en) | A kind of Interval neural networks learning method based on interval parameter optimization | |
| CN114970688A (en) | Landslide monitoring data preprocessing method based on LSTMAD algorithm and Hermite interpolation method | |
| CN110308658A (en) | A kind of pid parameter setting method, device, system and readable storage medium storing program for executing | |
| CN110110406B (en) | Slope stability prediction method for achieving LS-SVM model based on Excel computing platform | |
| CN111210877A (en) | Method and device for deducing physical property parameters | |
| CN111444619B (en) | Online analysis method and equipment for injection mold cooling system | |
| CN113010954A (en) | Bridge structure damage identification method and device and terminal equipment | |
| CN114417681B (en) | Two-dimensional structure deformation monitoring method and device based on dynamic decision and neural network | |
| CN116292057A (en) | Control method, device, equipment and medium for variable-speed pumped storage unit | |
| CN110909492A (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
| CN109323677A (en) | Improve the Circularity error evaluation algorithm of cuckoo searching algorithm | |
| CN115688924A (en) | Multi-sample combined multivariate self-adaptive regression spline model | |
| CN109858699B (en) | Water quality quantitative simulation method and device, electronic equipment and storage medium | |
| CN107944552A (en) | A kind of industrial Internet of Things parameter prediction method based on Elman neutral nets | |
| CN112685954A (en) | Method and device for predicting wind speed and fan rotating speed of automobile environment wind tunnel | |
| CN111199774B (en) | Three-coordinate equipment position calibration method | |
| CN114297940B (en) | Method and device for determining unsteady state reservoir parameters | |
| CN117556345B (en) | Magnetorheological polishing removal function prediction device and method based on neural network | |
| CN109376337B (en) | Distributed soft measurement method based on Girvan-Newman algorithm | |
| WO2023233858A1 (en) | Calculation device and calculation method for neural network |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: No.99, Tianyue South Road, Huaiyin District, Jinan City, Shandong Province Applicant after: Shandong Tianyue advanced technology Co.,Ltd. Address before: No.99, Tianyue South Road, Huaiyin District, Jinan City, Shandong Province Applicant before: SICC Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |