CN116861736A - Multi-scale material intelligent computing platform combining artificial intelligence - Google Patents
Multi-scale material intelligent computing platform combining artificial intelligence Download PDFInfo
- Publication number
- CN116861736A CN116861736A CN202310796986.7A CN202310796986A CN116861736A CN 116861736 A CN116861736 A CN 116861736A CN 202310796986 A CN202310796986 A CN 202310796986A CN 116861736 A CN116861736 A CN 116861736A
- Authority
- CN
- China
- Prior art keywords
- computing
- software
- module
- artificial intelligence
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000463 material Substances 0.000 title claims abstract description 96
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 34
- 230000001568 sexual effect Effects 0.000 claims abstract description 36
- 238000004088 simulation Methods 0.000 claims abstract description 35
- 238000000329 molecular dynamics simulation Methods 0.000 claims abstract description 15
- 230000005540 biological transmission Effects 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 58
- 238000013528 artificial neural network Methods 0.000 claims description 22
- 239000013078 crystal Substances 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 13
- 239000000126 substance Substances 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 230000010287 polarization Effects 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 6
- 102100021164 Vasodilator-stimulated phosphoprotein Human genes 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012827 research and development Methods 0.000 description 3
- 108010054220 vasodilator-stimulated phosphoprotein Proteins 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000005294 ferromagnetic effect Effects 0.000 description 2
- 230000005389 magnetism Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005556 structure-activity relationship Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a multi-scale material intelligent computing platform combined with artificial intelligence, which is characterized by comprising a computing module, a database module and an artificial intelligence module; the computing module comprises first sexual principle computing software of a microscale, molecular dynamics computing software, phase field simulation software of a mesoscale and finite element computing software of a macroscale, and is used for selecting a required computing scale and software and performing simulation computation under different scales according to computing parameters acquired from the database module; the artificial intelligence module is used for transmitting parameters among multiple scales and analyzing material characteristics; the database module is used for storing material information and transmission parameters among multiple scales generated by the artificial intelligence module.
Description
Technical Field
The application belongs to the technical field of the intersection of novel material technology and computer technology, and particularly relates to an artificial intelligence combined multi-scale material intelligent computing platform.
Background
The calculation of the materiality mainly refers to a science for carrying out material behavior mechanism discovery, material performance prediction and material optimization design by solving a theoretical formula through a mathematical tool by using a computer numerical value based on a physical theoretical model. One of the future development trends of computing materials is to deeply combine the traditional computing materials method with the data-driven artificial intelligence method, so as to develop a new research direction of 'intelligent computing materials'. The intelligent computing material is a research and development mode combining a research and development paradigm of computing drive and data drive, and becomes a powerful tool for solving the problem of material science. In recent years, information technology, data science and artificial intelligence technology are integrated with material science, and further, a great change is brought to the material science, and the technology is regarded as a fourth range of material research and development. This revolution has also prompted the advent of material genome technology, making the high integration of computing, data and high throughput experimentation three into three major technological tools that motivate the technological development of the twenty-first century materials.
In the development of new materials, computational simulations have gained equal importance as theoretical and experimental roles. For material calculations, different simulation methods need to be employed at different scales. On a microscopic scale, first principles of computation, molecular dynamics, etc. simulation methods are required. On the mesoscale, methods such as phase field simulation, thermodynamic calculation, and micromechanics calculation are required. On a macroscopic scale, simulation methods such as finite element are required. The calculation methods at these different scales correspond to different calculation software, for example, VASP, abinit, etc. corresponding to first principle calculation, LAMMPS corresponding to molecular dynamics, comsol corresponding to phase field, ANSYS corresponding to finite element, etc. While the result of the first principles of microcosmic computation can provide the parameters required for the mesoscopic phase field and macroscopic finite elements, the process is excessively dependent on manpower, is not only cumbersome, but also is difficult to realize data sharing. And its main root is the lack of interaction between computing software at different scales.
Disclosure of Invention
Aiming at the problems existing in the prior art, the embodiment of the application aims to provide a multi-scale material intelligent computing platform combined with artificial intelligence, which can analyze input and output data of different scales by utilizing the artificial intelligence, thereby opening gaps among various simulation software of different scales and further realizing a multi-scale computing method.
According to a first aspect of an embodiment of the present application, there is provided a multi-scale material intelligent computing platform incorporating artificial intelligence, including a computing module, a database module, and an artificial intelligence module;
the computing module comprises first sexual principle computing software of a microscale, molecular dynamics computing software, phase field simulation software of a mesoscale and finite element computing software of a macroscale, and is used for selecting a required computing scale and software and performing simulation computation under different scales according to computing parameters acquired from the database module;
the artificial intelligence module is used for transmitting parameters among multiple scales and analyzing material characteristics;
the database module is used for storing material information and transmission parameters among multiple scales generated by the artificial intelligence module.
Further, the computing module also includes a conversion script for generating different software input files based on the input material information.
Further, the transferring parameters between the multiple scales includes:
(1) Taking a calculation result of the first sexual principle calculation software as input, calculating a required potential function of molecular dynamics obtained through a BP neural network and a required potential function of a second sexual principle;
(2) Taking a calculation result of the first sexual principle calculation software as input, and obtaining parameters required by phase field simulation through a BP neural network;
(3) And taking the elastic properties and dielectric properties under different mesoscopic domain structures obtained by the phase field simulation software as input, and calculating required parameters through finite elements obtained by the BP neural network.
Further, the artificial intelligence module analyzes material components and relationships between structures and material properties by using material properties through a convolutional neural network, wherein the material properties are obtained by the output result of the calculation module or the database module.
Further, in "(1) taking the calculation result of the first sexual principle calculation software as input, the calculation result is a crystal structure, energy, and an interatomic acting force in the function of the potential required by the molecular dynamics obtained through the BP neural network and the function of the potential required by the second sexual principle calculation.
Further, in the step (2) of calculating the first sexual principle calculating software, the calculation result is a polarization, energy, a born effective charge, and a phonon spectrum, and the calculation result is a parameter required by a phase field simulation obtained through a BP neural network, and the parameter required by the phase field simulation includes a langerhans energy coefficient, a gradient energy coefficient, and an electrostriction coefficient.
Further, in "(3) taking the elastic properties and the dielectric properties under different mesoscopic domain structures obtained by the phase field simulation software as input, finite elements obtained by the BP neural network calculate required parameters", the finite elements calculate required parameters such as the elastic constant and the dielectric constant.
According to a second aspect of the embodiment of the present application, there is provided a multi-scale material intelligent computing method, based on the above-mentioned multi-scale material intelligent computing platform combined with artificial intelligence, including:
(1) Extracting relevant information of the required simulation materials from a database, wherein the relevant information comprises chemical formulas, crystal structures and elastic constants;
(2) Converting the extracted material information into an input file required by first sexual principle computing software under a microscale by using a conversion script of a computing module, and performing operation by using the first sexual principle computing software to obtain values of energy and force under different structures;
(3) According to the scale of the required simulation, correspondingly selecting software required by micro, meso or macro simulation calculation, and transmitting the parameters obtained in the step (2) to each software in the step by utilizing an artificial intelligent module, wherein after each level of calculation, the obtained parameters are stored in a database module and are transmitted to corresponding software as transmission parameters of the next level until the required material properties are obtained;
(4) Transmitting the material information extracted in the step (1) and the material attribute obtained in the step (3) to an artificial intelligent module, searching the relation between the chemical formula, the crystal structure and the required material attribute by using the artificial intelligent module, and screening the chemical formula and the crystal structure according to the material attribute required by a user;
(5) And (5) saving the result of the step (4) to a database module.
The technical scheme provided by the embodiment of the application can comprise the following beneficial effects:
according to the embodiment, the parameter transmission among multiple scales is performed through artificial intelligence, and calculation simulation software with different scales is integrated into the same material platform. The technical problems of weak connectivity and difficult intercommunication among different scale computing simulation software are solved, so that the effect of simply and lightly realizing multi-scale computing in the same platform only by means of some basic information (such as material properties required to be simulated, external environment required to be simulated and the like) is realized.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic diagram illustrating a multi-scale material intelligent computing platform incorporating artificial intelligence according to an exemplary embodiment.
FIG. 2 is a flow chart of a method for searching multiferroic materials stably existing at room temperature by combining microscopic first property principle calculation and mesoscopic phase field method in an embodiment of the application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
FIG. 1 is a schematic diagram of a multi-scale material intelligent computing platform incorporating artificial intelligence, as shown in FIG. 1, according to an exemplary embodiment, the platform may include:
the computing module consists of a high-performance CPU computing cluster and comprises first sexual principle computing software (VASP, abinit), molecular dynamics computing software (LAMMPS), second sexual principle computing software (Multibinit), mesoscale phase field simulation software (Comsol), macroscopic scale finite element computing software (ANSYS) and the like.
In specific implementation, the user selects the required calculation scale and the software to be adopted, inputs calculation parameters, so that analog calculation under different scales is performed, and the required CPU core number and the required time can be selected before calculation is performed if necessary.
The simulation scale which can be selected by the calculation module comprises first principle calculation of a microscopic level, molecular dynamics, phase field simulation of a mesoscale, finite element analysis of a macroscopic level and the like. And according to different simulation scales, different simulation software is adopted, and a calculation script for generating different software input files according to the input material information is also contained in the calculation module.
Specifically, the calculation parameters required to be input by the calculation module vary according to the selected simulation scale. For example, on a microscopic level, the first sexual principle calculates required pseudopotential, crystal structure, cut-off energy, potential functions required by molecular dynamics, lang energy coefficients and gradient energy coefficients required by mesoscopic phase field simulation, unit information required by macroscopic finite element analysis, and the like. In a specific implementation, the calculation module may extract the required parameters from the database module by combining with it.
The database module consists of a large-capacity storage unit, and the main task of the database module is to store information of various materials. These information include: (1) Conventional material information such as Young's modulus, poisson's ratio, curie temperature, dielectric constant, magnetism, etc.; (2) Transfer parameters between multiple scales generated by the artificial intelligence module, such as various potential functions constructed based on first sexual principle calculation, parameters in a phase field simulation obtained by fitting the first sexual principle calculation, and the like.
And the artificial intelligent module consists of a GPU computing cluster and comprises an AI library and an intelligent computing module. The AI library comprises a BP neural network and a convolutional neural network which are respectively used for parameter transmission and material attribute analysis among multiple scales. The intelligent computing module can be further divided into a multi-scale transmission module responsible for transmitting parameters among the multiple scales and a material property research module for analyzing material properties.
The multi-scale transmission module utilizes the existing BP neural network, can obtain input parameters required by micro-computation such as molecular dynamics, second sexual principle computation and the like and mesoscopic computation such as phase field simulation and the like on the basis of first sexual principle computation, and can also obtain parameters required by macro-computation such as finite element computation and the like on the basis of phase field simulation. The module comprises a prepared BP neural network algorithm, a crystal structure, energy and interatomic acting force obtained by first sexual principle calculation are used as inputs of the BP neural network, and a potential function required by molecular dynamics and a potential function required by second sexual principle calculation are used as outputs, so that the connection between the first sexual principle calculation and the molecular dynamics and the second sexual principle calculation is realized. The module also comprises a BP neural network which is suitable for obtaining phase field parameters, the obtained polarization, energy, the Boen effective charge and phonon spectrum are calculated by the first sexual principle and used as the input of the BP neural network, and parameters of field simulation such as Lang energy coefficient, gradient energy coefficient, electrostriction coefficient and the like are used as the output, so that the connection between the first sexual principle calculation and the phase field simulation is realized. The module also comprises a BP neural network which is suitable for obtaining finite element calculation parameters, wherein the elasticity property and the dielectric property under different mesoscopic domain structures obtained by phase field simulation are used as the input of the BP neural network, and the finite element calculation parameters such as the elasticity constant and the dielectric constant are used as the output, so that the connection between the phase field simulation and the finite element calculation is realized.
In the material property research module, a corresponding convolutional neural network can be built according to the requirement. And analyzing the relation between the material components, the structure and the material performance by utilizing the input information under different simulation scales, so that proper components are selected, and the material structure is designed. The attribute of the material can be derived from a database module under the platform or a calculation module under the platform.
Based on the study of the material properties, various intrinsic information of the material, such as structure-activity relationship, transport relationship, data equation and the like, can be analyzed according to the output of the part.
When the platform is built, parameters and performances of a known material system are calculated through high flux, and the existing data in the literature are combined to build a training data set, so that the training of the BP neural network and the convolutional neural network is realized.
The application also provides a multi-scale material intelligent computing method based on the multi-scale material intelligent computing platform combined with artificial intelligence, which comprises the following steps:
(1) Extracting relevant information of materials to be simulated by a user from a database, including, but not limited to, chemical formulas, crystal structures, elastic constants and the like;
(2) Converting the extracted material information into an input file required by first sexual principle computing software VASP under a micro scale by utilizing a conversion script of a computing module, wherein the input file comprises INCAR, KPOINTS, POSCAR, POTCAR, or the input file required by first sexual principle computing software Abinit comprises Abinit, files, abinit, xml (representing different element symbols according to different chemical formulas), and computing by utilizing first sexual principle computing software VASP or Abinit to obtain values of energy and force under different structures;
(3) According to the scale of the required simulation, correspondingly selecting software required by micro, meso or macro simulation calculation, and transmitting the parameters obtained in the step (2) to each software in the step by utilizing an artificial intelligent module, wherein after each level of calculation, the obtained parameters are stored in a database module and are transmitted to corresponding software as transmission parameters of the next level until the required material properties are obtained;
(4) And (3) transmitting the material information extracted in the step (1) and the material attribute obtained in the step (3) to an artificial intelligent module, searching the relation between a chemical formula, a crystal structure and the like and the required material attribute by using a material attribute research module in the artificial intelligent module, and screening the chemical formula and the crystal structure according to the material attribute required by a user.
(5) And (5) saving the result of the step (4) to a database module.
The following describes the process of searching multiferroic materials which can exist stably at room temperature by combining microscopic first-principle calculation and mesoscopic phase field method with the attached figure 2, so as to further describe the method.
S101, extracting relevant information of the multiferroic material through a database module, wherein the relevant information comprises the following specific steps: chemical formula, elastic constant, electric polarization, dielectric constant, magnetism, crystal structure;
s102, selecting first sexual principle calculation and phase field simulation as calculation methods according to calculation task requirements, wherein corresponding software is VASP and COMSOL;
s103, based on the material information extracted from the database, generating a first principle calculation input file, specifically four INCAR, KPOINTS, POSCAR, POTCAR files;
s104, calculating by using first sexual principle calculation software to obtain force and energy under different configurations;
s105, transmitting the force and energy under different configurations to a multi-scale transmission module of the artificial intelligent module, obtaining phase field parameters by using a BP neural network, transmitting the phase field parameters to a calculation module for calculation of the next step, and transmitting the parameters to a database module for profiling;
s106, ferroelectric and ferromagnetic properties at a limited temperature are obtained by using phase field simulation and are transmitted to an artificial intelligent module;
s107, screening and analyzing based on the obtained ferroelectric and ferromagnetic properties at the limited temperature by utilizing an artificial intelligent module and combining field knowledge to obtain a required material;
s108, feeding the artificial intelligence screening result back to the database, and performing gear establishment.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof.
Claims (8)
1. The multi-scale material intelligent computing platform combining the artificial intelligence is characterized by comprising a computing module, a database module and an artificial intelligence module;
the computing module comprises first sexual principle computing software of a microscale, molecular dynamics computing software, phase field simulation software of a mesoscale and finite element computing software of a macroscale, and is used for selecting a required computing scale and software and performing simulation computation under different scales according to computing parameters acquired from the database module;
the artificial intelligence module is used for transmitting parameters among multiple scales and analyzing material characteristics;
the database module is used for storing material information and transmission parameters among multiple scales generated by the artificial intelligence module.
2. The multi-scale material intelligent computing platform incorporating artificial intelligence of claim 1, wherein the computing module further comprises a conversion script for generating different software input files from the input material information.
3. The artificial intelligence combined multi-scale material intelligent computing platform of claim 1, wherein transferring parameters between the multi-scales comprises:
(1) Taking a calculation result of the first sexual principle calculation software as input, calculating a required potential function of molecular dynamics obtained through a BP neural network and a required potential function of a second sexual principle;
(2) Taking a calculation result of the first sexual principle calculation software as input, and obtaining parameters required by phase field simulation through a BP neural network;
(3) And taking the elastic properties and dielectric properties under different mesoscopic domain structures obtained by the phase field simulation software as input, and calculating required parameters through finite elements obtained by the BP neural network.
4. The multi-scale material intelligence computing platform incorporating artificial intelligence of claim 1, wherein the artificial intelligence module analyzes material composition and relationships between structure and material properties using material properties through convolutional neural networks, wherein the material properties are obtained by output results of the computing module or the database module.
5. The intelligent computing platform for multi-scale materials combined with artificial intelligence according to claim 1, wherein in the step of (1) taking the computing result of the first sexual principle computing software as input, the computing result is a crystal structure, energy and interatomic acting force in the step of computing the required potential function of molecular dynamics and the required potential function of the second sexual principle obtained through a BP neural network.
6. The intelligent computing platform for multi-scale materials combined with artificial intelligence according to claim 1, wherein in the calculation result of the first principle computing software of (2) is input, the calculation result is polarization, energy, born effective charge, phonon spectrum, and the parameters required for phase field simulation obtained through a BP neural network include langerhans energy coefficient, gradient energy coefficient, electrostriction coefficient.
7. The artificial intelligence-combined multi-scale material intelligent computing platform according to claim 1, wherein in the step (3) of taking the elastic properties and the dielectric properties under different mesoscopic domain structures obtained by the phase field simulation software as input, finite elements obtained by a BP neural network calculate required parameters, wherein the finite elements calculate required parameters such as an elastic constant and a dielectric constant.
8. A method of intelligent computation of a multi-scale material, based on the artificial intelligence combined multi-scale material intelligent computation platform of any of claims 1-7, comprising:
(1) Extracting relevant information of the required simulation materials from a database, wherein the relevant information comprises chemical formulas, crystal structures and elastic constants;
(2) Converting the extracted material information into an input file required by first sexual principle computing software under a microscale by using a conversion script of a computing module, and performing operation by using the first sexual principle computing software to obtain values of energy and force under different structures;
(3) According to the scale of the required simulation, correspondingly selecting software required by micro, meso or macro simulation calculation, and transmitting the parameters obtained in the step (2) to each software in the step by utilizing an artificial intelligent module, wherein after each level of calculation, the obtained parameters are stored in a database module and are transmitted to corresponding software as transmission parameters of the next level until the required material properties are obtained;
(4) Transmitting the material information extracted in the step (1) and the material attribute obtained in the step (3) to an artificial intelligent module, searching the relation between the chemical formula, the crystal structure and the required material attribute by using the artificial intelligent module, and screening the chemical formula and the crystal structure according to the material attribute required by a user;
(5) And (5) saving the result of the step (4) to a database module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310796986.7A CN116861736A (en) | 2023-06-30 | 2023-06-30 | Multi-scale material intelligent computing platform combining artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310796986.7A CN116861736A (en) | 2023-06-30 | 2023-06-30 | Multi-scale material intelligent computing platform combining artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116861736A true CN116861736A (en) | 2023-10-10 |
Family
ID=88233371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310796986.7A Pending CN116861736A (en) | 2023-06-30 | 2023-06-30 | Multi-scale material intelligent computing platform combining artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116861736A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117524386A (en) * | 2024-01-04 | 2024-02-06 | 之江实验室 | Method and device for calculating magnetic alloy permeability based on micromagnetism and machine learning |
-
2023
- 2023-06-30 CN CN202310796986.7A patent/CN116861736A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117524386A (en) * | 2024-01-04 | 2024-02-06 | 之江实验室 | Method and device for calculating magnetic alloy permeability based on micromagnetism and machine learning |
| CN117524386B (en) * | 2024-01-04 | 2024-06-04 | 之江实验室 | Method and device for calculating magnetic alloy permeability based on micromagnetism and machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jia et al. | Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning | |
| Neelakandan et al. | Large scale optimization to minimize network traffic using MapReduce in big data applications | |
| CN107609141B (en) | Method for performing rapid probabilistic modeling on large-scale renewable energy data | |
| WO2006017247A2 (en) | Method and apparatus for designing electronic circuits using optimization | |
| CN108667069B (en) | Short-term wind power prediction method based on partial least squares regression | |
| CN116861736A (en) | Multi-scale material intelligent computing platform combining artificial intelligence | |
| CN114492814B (en) | Method, device and medium for calculating energy of simulation target system based on quanta | |
| CN112330078B (en) | Power consumption prediction method and device, computer equipment and storage medium | |
| Mergos et al. | Flower pollination algorithm parameters tuning | |
| CN114492815B (en) | Method, device and medium for calculating target system energy based on quantum chemistry | |
| CN114528996B (en) | Method, device and medium for determining initial parameters of target system test state | |
| Andreta et al. | A novel automated design methodology for power electronics converters | |
| CN113901679B (en) | Reliability analysis method and device for power system and computer equipment | |
| CN111241076A (en) | Stream data increment processing method and device based on tensor chain decomposition | |
| Archibald et al. | Integrating deep learning in domain sciences at exascale | |
| Yang et al. | Integral matching-based nonlinear grey Bernoulli model for forecasting the coal consumption in China | |
| US8655630B2 (en) | Apparatus, system, and method for construction of a design workflow | |
| Zhang et al. | Building energy consumption prediction based on temporal-aware attention and energy consumption states | |
| Knight et al. | Coarse-graining away electronic structure: a rigorous route to accurate condensed phase interaction potentials | |
| WO2023047843A1 (en) | Model generation method, data presentation method, data generation method, inference method, model generation device, data presentation device, data generation device, and inference device | |
| CN114519429B (en) | Method, device and medium for obtaining observability quantity of target system | |
| CN116682506A (en) | Data processing method, training method, determining method, designing method and device | |
| CN114512194B (en) | Method and device for acquiring target system test state in quantum chemistry simulation | |
| CN114237548A (en) | Method and system for complex dot product operation based on nonvolatile memory array | |
| Song et al. | Hardware-aware neural architecture search for stochastic computing-based neural networks on tiny devices |
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 |