Simulation method based on machine learning and molecular dynamics and related device

Abstract

The invention provides a simulation method based on machine learning and molecular dynamics and a related device, and is applied to the field of semiconductor manufacturing. For each process condition in the process menu, inputting the process condition into the force field prediction model, and outputting to obtain a machine learning force field under the process condition; and finally, performing molecular dynamics simulation according to the machine learning force field under the process condition to obtain a simulation result under the process condition. Through a machine learning method, high-precision first-principle calculation data is learned, a machine learning force field is generated, and interaction of silicon carbide in an ion implantation process is simulated, so that the ion implantation process is simulated, high-precision and efficient simulation calculation is realized, the influence of different process conditions on a device design process is comprehensively considered, and the device design efficiency is improved. A specific process menu is developed, and an optimization scheme is provided for silicon carbide ion implantation.

Description

Technical Field

[0001] The present application relates to the technical field of semiconductor manufacturing, and in particular to a simulation method and related devices based on machine learning and molecular dynamics. Background Art

[0002] At present, in the field of semiconductor device process simulation, traditional simulation methods such as SRIM use the Monte Carlo method, which is mainly based on existing experience or experimental data. It not only has poor accuracy but also low efficiency in predicting experimental results and studying process mechanisms. Summary of the invention

[0003] In view of this, the present application provides a simulation method and related devices based on machine learning and molecular dynamics to achieve high-precision and efficient simulation calculations.

[0004] The first aspect of the present application provides a simulation method based on machine learning and molecular dynamics, comprising:

[0005] Receive a process menu; wherein the process menu includes at least one process condition; the process condition is divided into an implantation parameter and an annealing parameter; the implantation parameter includes the energy, dose, angle, temperature and crystal orientation of ions implanted into silicon carbide; the annealing parameter includes the annealing temperature, annealing time and temperature control rate;

[0006] For each process condition, the process condition is input into a force field prediction model, and a machine learning force field under the process condition is output; wherein the force field prediction model is obtained by training the machine learning model with a training sample set; and the training sample set includes at least one training sample;

[0007] Molecular dynamics simulation is performed based on the machine learning force field under the process conditions to obtain simulation results under the process conditions.

[0008] Optionally, the method for constructing the force field prediction model includes:

[0009] Constructing a training sample set; wherein the training sample set includes at least one training sample, and the training sample includes physical information of the training sample configuration;

[0010] For each training sample, the atomic structure of the training sample configuration is transformed using the descriptor of the machine learning model to obtain the training sample features;

[0011] Based on the characteristics of the training samples, the machine learning model is trained to obtain the force field prediction model.

[0012] Optionally, constructing a training sample set includes:

[0013] Generate an initial force field through a large force field model; wherein the initial force field includes a plurality of initial configurations;

[0014] Active learning is performed using the initial force field to obtain multiple target configurations;

[0015] For each training sample configuration, a first principle calculation is performed on the training sample configuration to obtain physical information of the training sample configuration; wherein the training sample configuration includes a plurality of initial configurations and a plurality of target configurations.

[0016] Optionally, the physical information of the training sample configuration includes interatomic forces and energy of the training sample configuration.

[0017] The second aspect of the present application provides a simulation device based on machine learning and molecular dynamics, comprising:

[0018] A receiving unit, configured to receive a process menu; wherein the process menu includes at least one process condition; the process condition is divided into an implantation parameter and an annealing parameter; the implantation parameter includes the energy, dose, angle, temperature and crystal orientation of ions implanted into silicon carbide; the annealing parameter includes an annealing temperature, an annealing time and a temperature control rate;

[0019] A machine learning unit, for each process condition, inputs the process condition into a force field prediction model, and outputs a machine learning force field under the process condition; wherein the force field prediction model is obtained by training the machine learning model with a training sample set; and the training sample set includes at least one training sample;

[0020] The simulation unit is used to perform molecular dynamics simulation according to the machine learning force field under the process conditions to obtain simulation results under the process conditions.

[0021] Optionally, the construction unit of the force field prediction model includes:

[0022] A training sample set construction unit, used to construct a training sample set; wherein the training sample set includes at least one training sample, and the training sample includes physical information of the training sample configuration;

[0023] A conversion unit, for each training sample, using the descriptor of the machine learning model to convert the atomic structure of the training sample configuration to obtain the training sample feature;

[0024] The training unit is used to train the machine learning model based on the training sample characteristics to obtain the force field prediction model.

[0025] Optionally, the training sample set construction unit includes:

[0026] An initial force field generating unit, used to generate an initial force field through a large force field model; wherein the initial force field includes a plurality of initial configurations;

[0027] An active learning unit, used for performing active learning using the initial force field to obtain multiple target configurations;

[0028] The calculation unit is used to perform first principle calculation on each training sample configuration to obtain physical information of the training sample configuration; wherein the training sample configuration includes multiple initial configurations and multiple target configurations.

[0029] Optionally, the physical information of the training sample configuration includes interatomic forces and energy of the training sample configuration.

[0030] A third aspect of the present application provides an electronic device, including:

[0031] one or more processors;

[0032] a storage device having one or more programs stored thereon;

[0033] When the one or more programs are executed by the one or more processors, the one or more processors implement the simulation method based on machine learning and molecular dynamics as described in any one of the first aspects.

[0034] A fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the simulation method based on machine learning and molecular dynamics as described in any one of the first aspects is implemented.

[0035] From the above scheme, it can be seen that the present application provides a simulation method and related devices based on machine learning and molecular dynamics. After receiving the process menu; for each process condition in the process menu, the process condition is input into the force field prediction model, and the machine learning force field under the process condition is output; finally, molecular dynamics simulation is performed according to the machine learning force field under the process condition to obtain the simulation result under the process condition. Through the machine learning method, high-precision first-principles calculation data is learned, and a machine learning force field is generated to simulate the interaction of silicon carbide during the ion implantation process, thereby simulating the ion implantation process, achieving high-precision and efficient simulation calculation, and then comprehensively considering the impact of different process conditions on the device design process, developing a specific process menu, and providing an optimization solution for silicon carbide ion implantation. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] Figure 1 A specific flow chart of a simulation method based on machine learning and molecular dynamics provided in an embodiment of the present application;

[0038] Figure 2 A specific flow chart of a method for constructing a force field prediction model provided in another embodiment of the present application;

[0039] Figure 3 A specific flow chart of a method for constructing a training sample set provided in another embodiment of the present application;

[0040] Figure 4 A schematic diagram of a simulation device based on machine learning and molecular dynamics provided in another embodiment of the present application;

[0041] Figure 5 A schematic diagram of an electronic device for implementing a simulation method based on machine learning and molecular dynamics provided in another embodiment of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0044] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0045] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0046] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0047] The present application embodiment provides a simulation method based on machine learning and molecular dynamics, such as Figure 1 As shown, the specific steps include:

[0048] S101, receiving a process menu.

[0049] The process menu includes at least one process condition. The process conditions are divided into implantation parameters and annealing parameters; implantation parameters include but are not limited to the energy, dose, angle, temperature, crystal orientation, etc. of ions implanted into silicon carbide, which are not limited here; annealing parameters include annealing temperature, annealing time, temperature control rate, etc., which are not limited here.

[0050] S102. For each process condition, the process condition is input into a force field prediction model, and a machine learning force field under the process condition is output.

[0051] The force field prediction model is obtained by training a machine learning model with a training sample set; the training sample set includes at least one training sample.

[0052] Specifically, the force field prediction model is used to simulate the interactions that occur in silicon carbide during ion implantation, that is, the microscopic atomic reaction process that will occur under the process conditions, thereby assisting the process in improving the process conditions.

[0053] Optionally, in another embodiment of the present application, an implementation method of a method for constructing a force field prediction model is as follows: Figure 2 As shown, including:

[0054] S201: Construct a training sample set.

[0055] The training sample set includes at least one training sample, and the training sample includes physical information of the training sample configuration.

[0056] Optionally, in another embodiment of the present application, an implementation of step S201 is as follows: Figure 3 As shown, including:

[0057] S301, generating an initial force field through a large force field model.

[0058] The initial force field includes multiple initial configurations.

[0059] In the specific implementation process of the present application, the initial force field can be generated using but not limited to the force field large model MPtrj and the force field large model GPTFF, which is not limited here.

[0060] S302: Active learning is performed using the initial force field to obtain multiple target configurations.

[0061] Although the current force field large model has a wide range of applications, can provide high-quality initial force fields, and can be combined with enhanced sampling schemes to more efficiently explore phase space, the force field reasoning speed generated by the existing force field large model is slow and the accuracy for specific vertical fields is poor. Therefore, this application only participates in the construction of the initial training data set through the existing force field large model, and uses active learning technology to generate sufficient and representative training data (target configuration).

[0062] S303: For each training sample configuration, perform first principle calculation on the training sample configuration to obtain physical information of the training sample configuration.

[0063] The training sample configurations include multiple initial configurations and multiple target configurations.

[0064] It should be noted that the first principle calculation can use but is not limited to VASP, DASP, PWmat and other computing software to calculate the interatomic forces and energy of the training sample configuration, so as to obtain the physical information of the training sample configuration.

[0065] It is understandable that due to the many types of defects caused by the implanted ions (such as Al ions) in the silicon carbide (SiC) matrix, these defects also need to be part of the training sample set. In addition, it is also necessary to consider the configurations of ions (such as Al ions) and silicon (Si) ions and carbon (C) at different distances caused by the implanted ions (such as Al ions) to calculate the forces and energies of these configurations as a data set.

[0066] Taking Al as an example, the training sample set can be composed of a large number of defect configurations related to Al-doped SiC. Based on the 4H-SiC crystal structure, a supercell is constructed. Based on the symmetry, various defects and configurations with different Al doping concentrations are fully considered to generate a supercell containing defects and impurities.

[0067] S202. For each training sample, the atomic structure of the training sample configuration is transformed using the descriptor of the machine learning model to obtain the training sample features.

[0068] Among them, descriptors are used to convert atomic structures into mathematical features that neural networks can process. Model training captures multi-body interactions in materials, enabling them to efficiently predict the physical behavior of materials in large-scale molecular dynamics simulations.

[0069] In the actual application process of this application, the machine learning model can be a DP (Deep Potential) model, a NEP (Neuroevolution Potential) model, etc., which is not limited here. In addition, multiple models can be used for training in parallel. After the training is completed, the best model is selected as the final force field prediction model. This ensures the accuracy and scope of application of the machine learning force field output by the final force field prediction model.

[0070] S203. Based on the training sample characteristics, the machine learning model is trained to obtain a force field prediction model.

[0071] Among them, the machine learning model includes multiple iterations and verifications in the training process to ensure that it can generalize to ion (such as Al ion) implantation behavior under different conditions.

[0072] S103. Perform molecular dynamics simulation based on the machine learning force field under the process conditions to obtain simulation results under the process conditions.

[0073] In the specific implementation process of this application, when performing molecular dynamics simulation, Lammps can be used for simulation, but it is not limited to it, and it is not limited here. Since the electron blocking process can be ignored in ion implantation under low energy conditions, the simulation is simplified to bombarding the silicon carbide (SiC) matrix with ions (such as Al) atoms with a certain kinetic energy, simulating the injection path, energy dissipation process, and defect generation and migration mechanism (such as vacancies and interstitial atoms) of ions (such as Al) in SiC. By simulating and analyzing the effects of different injection energy, dose, angle, temperature and other process parameters on the injection depth, distribution and uniformity, as well as defect distribution and evolution, high-precision and efficient simulation calculations are achieved.

[0074] In the actual application process of the present application, a quantitative relationship between the implantation conditions and the defect formation will be established through the generation of a large number of simulation results. The simulation parameters include the implantation parameters and the annealing parameters after the implantation.

[0075] The implantation parameters include implantation energy (e.g. 100-300 keV), dose (e.g. 10 16 -10 17 cm -3 ), angle (e.g. 0-20°), temperature (e.g. 20-600°C) and crystal orientation, etc. are not limited here.

[0076] It should be noted that different implantation energies and doses will significantly affect the movement trajectory, doping depth and defect generation behavior of ions in the material. By comparing the simulation results under different parameter combinations, the effects of different implantation conditions on the defect distribution and structural changes inside the material are evaluated. Changes in the implantation angle and temperature will affect the path and residence position of ions in the material, and thus affect the final doping distribution and defect density. By selecting different crystal orientations, the effects of the anisotropy of the material structure and the channel effect on the ion implantation behavior can be further studied. Based on the simulation results, an optimization scheme for parameters such as implantation energy, dose and angle can be proposed to ensure that the implantation depth and uniformity of the material are maximized while controlling defect generation.

[0077] It is understandable that the control of defects depends on the injection conditions on the one hand, and on the annealing process after injection on the other hand. By comparing different annealing conditions (for example, 1400-1900℃), the relationship between annealing conditions and lattice repair is established to ensure that impurities are effectively electrically activated and improve the performance of SJ devices.

[0078] Since ion implantation and defects are closely related to lattice damage, including atomic dislocation, cascade collision, dislocation formation, vacancy and interstitial atom generation, etc. Based on the simulation results, these physical mechanisms are deeply analyzed, and this application can also clarify which process parameters are most critical for doping and defect control. The physical mechanism analysis will reveal the interaction process between ions (such as Al) and SiC matrix, especially how the initial lattice damage is formed through collision, how the damage area is gradually expanded through collision cascade and energy dissipation, and finally stable defects are formed.

[0079] Therefore, the simulation will focus on the injection path of ions (such as Al), the formation and evolution of defects, including the initial generation of defects, lattice damage during cascade collisions, and the final defect aggregation behavior. Through these analyses, a process menu for optimizing ion implantation will be proposed. Among them, the core of defect control is to ensure that the electrical activation rate of the injected atoms is improved and the lattice defects are repaired while meeting the doping concentration and injection distribution requirements.

[0080] Since the accumulation of lattice defects in the material will lead to a decrease in the electrical performance of the device, such as increasing the on-resistance and reducing the breakdown voltage. Therefore, the generation and evolution mechanism of defects can be analyzed in detail to clarify which process parameters are the key factors affecting defect generation. After ion implantation, the annealing process is a key step in defect control. By adjusting the annealing temperature, annealing time and temperature control rate, point defects in the material can be effectively reduced, lattice repair can be promoted, and thus lattice distortion generated during the doping process can be reduced. The transformation and annihilation mechanism of defects in the annealing process is analyzed through simulation results under different annealing conditions, and the optimal annealing process parameters are proposed.

[0081] From the above scheme, it can be seen that the present application provides a simulation method based on machine learning and molecular dynamics. After receiving the process menu, for each process condition in the process menu, the process condition is input into the force field prediction model, and the machine learning force field under the process condition is output; finally, molecular dynamics simulation is performed based on the machine learning force field under the process condition to obtain the simulation result under the process condition. Through the machine learning method, high-precision first-principles calculation data is learned, a machine learning force field is generated, and the interaction of silicon carbide during the ion implantation process is simulated, thereby simulating the ion implantation process, achieving high-precision and efficient simulation calculations, and then comprehensively considering the impact of different process conditions on the device design process, developing a specific process menu, and providing an optimization solution for silicon carbide ion implantation.

[0082] The present application embodiment provides a simulation device based on machine learning and molecular dynamics, such as Figure 4 As shown, specifically including:

[0083] The receiving unit 401 is used to receive a process menu.

[0084] The process menu includes at least one process condition. The process conditions are divided into implantation parameters and annealing parameters; implantation parameters include but are not limited to the energy, dose, angle, temperature, crystal orientation, etc. of ions implanted into silicon carbide, which are not limited here; annealing parameters include annealing temperature, annealing time, temperature control rate, etc., which are not limited here.

[0085] The machine learning unit 402 is used to input the process conditions into the force field prediction model for each process condition, and output the machine learning force field under the process conditions.

[0086] The force field prediction model is obtained by training a machine learning model with a training sample set; the training sample set includes at least one training sample.

[0087] Optionally, in another embodiment of the present application, an implementation of a construction unit of a force field prediction model includes:

[0088] The training sample set construction unit is used to construct the training sample set.

[0089] The training sample set includes at least one training sample, and the training sample includes physical information of the training sample configuration.

[0090] The conversion unit is used to convert the atomic structure of the training sample configuration using the descriptor of the machine learning model for each training sample to obtain the training sample features.

[0091] The training unit is used to train the machine learning model based on the training sample characteristics to obtain the force field prediction model.

[0092] For the specific working process of the units disclosed in the above embodiments of the present application, please refer to the corresponding method embodiments, such as Figure 2 As shown, no further description is given here.

[0093] Optionally, in another embodiment of the present application, an implementation of the training sample set construction unit includes:

[0094] The initial force field generation unit is used to generate the initial force field through the force field large model, wherein the initial force field includes a plurality of initial configurations.

[0095] The active learning unit is used to perform active learning using the initial force field to obtain multiple target configurations.

[0096] The computing unit is used to perform first principle calculation on each training sample configuration to obtain physical information of the training sample configuration.

[0097] The training sample configuration includes multiple initial configurations and multiple target configurations. The physical information of the training sample configuration includes the interatomic forces and energy of the training sample configuration.

[0098] For the specific working process of the units disclosed in the above embodiments of the present application, please refer to the corresponding method embodiments, such as Figure 3 As shown, no further description is given here.

[0099] The simulation unit 403 is used to perform molecular dynamics simulation according to the machine learning force field under the process conditions to obtain the simulation results under the process conditions.

[0100] For the specific working process of the units disclosed in the above embodiments of the present application, please refer to the corresponding method embodiments, such as Figure 1 As shown, no further description is given here.

[0101] From the above scheme, it can be seen that the present application provides a simulation device based on machine learning and molecular dynamics. After the receiving unit 401 receives the process menu; wherein, the machine learning unit 402 inputs the process conditions into the force field prediction model for each process condition in the process menu, and outputs the machine learning force field under the process conditions; finally, the simulation unit 403 performs molecular dynamics simulation based on the machine learning force field under the process conditions to obtain the simulation results under the process conditions. Through the machine learning method, high-precision first-principles calculation data is learned, a machine learning force field is generated, and the interaction of silicon carbide during the ion implantation process is simulated, thereby simulating the ion implantation process, achieving high-precision and efficient simulation calculations, and then comprehensively considering the impact of different process conditions on the device design process, developing a specific process menu, and providing an optimization solution for silicon carbide ion implantation.

[0102] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0103] Another embodiment of the present application provides an electronic device, such as Figure 5 As shown, including:

[0104] One or more processors 501 .

[0105] The storage device 502 stores one or more programs.

[0106] When the one or more programs are executed by the one or more processors 501, the one or more processors 501 implement the simulation method based on machine learning and molecular dynamics as described in any one of the above embodiments.

[0107] Another embodiment of the present application provides a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, a simulation method based on machine learning and molecular dynamics as described in any one of the above embodiments is implemented.

[0108] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0109] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0110] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0111] Another embodiment of the present application provides a computer program product, which, when executed, is used to perform the above-mentioned simulation method based on machine learning and molecular dynamics.

[0112] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0113] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in this application is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing this application.

[0114] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present application. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0115] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A simulation method based on machine learning and molecular dynamics, characterized in that: include: Receive a process menu; wherein the process menu includes at least one process condition; the process condition is divided into an implantation parameter and an annealing parameter; the implantation parameter includes the energy, dose, angle, temperature and crystal orientation of ions implanted into silicon carbide; the annealing parameter includes the annealing temperature, annealing time and temperature control rate; For each process condition, the process condition is input into a force field prediction model, and a machine learning force field under the process condition is output; wherein the force field prediction model is obtained by training the machine learning model with a training sample set; and the training sample set includes at least one training sample; Molecular dynamics simulation is performed based on the machine learning force field under the process conditions to obtain simulation results under the process conditions.

2. The simulation method based on machine learning and molecular dynamics according to claim 1, characterized in that: The method for constructing the force field prediction model comprises: Constructing a training sample set; wherein the training sample set includes at least one training sample, and the training sample includes physical information of the training sample configuration; For each training sample, the atomic structure of the training sample configuration is transformed using the descriptor of the machine learning model to obtain the training sample features; Based on the characteristics of the training samples, the machine learning model is trained to obtain the force field prediction model.

3. The simulation method based on machine learning and molecular dynamics according to claim 2, characterized in that: The step of constructing a training sample set includes: Generate an initial force field through a large force field model; wherein the initial force field includes a plurality of initial configurations; Active learning is performed using the initial force field to obtain multiple target configurations; For each training sample configuration, a first principle calculation is performed on the training sample configuration to obtain physical information of the training sample configuration; wherein the training sample configuration includes a plurality of initial configurations and a plurality of target configurations.

4. The simulation method based on machine learning and molecular dynamics according to claim 3, characterized in that: The physical information of the training sample configuration includes the interatomic forces and energy of the training sample configuration.

5. A simulation device based on machine learning and molecular dynamics, characterized in that: include: A receiving unit, configured to receive a process menu; wherein the process menu includes at least one process condition; the process condition is divided into an implantation parameter and an annealing parameter; the implantation parameter includes the energy, dose, angle, temperature and crystal orientation of ions implanted into silicon carbide; the annealing parameter includes an annealing temperature, an annealing time and a temperature control rate; A machine learning unit, for each process condition, inputs the process condition into a force field prediction model, and outputs a machine learning force field under the process condition; wherein the force field prediction model is obtained by training the machine learning model with a training sample set; and the training sample set includes at least one training sample; The simulation unit is used to perform molecular dynamics simulation according to the machine learning force field under the process conditions to obtain simulation results under the process conditions.

6. The simulation device based on machine learning and molecular dynamics according to claim 5, characterized in that: The construction unit of the force field prediction model includes: A training sample set construction unit, used to construct a training sample set; wherein the training sample set includes at least one training sample, and the training sample includes physical information of the training sample configuration; A conversion unit, for each training sample, using the descriptor of the machine learning model to convert the atomic structure of the training sample configuration to obtain the training sample feature; The training unit is used to train the machine learning model based on the training sample characteristics to obtain the force field prediction model.

7. The simulation device based on machine learning and molecular dynamics according to claim 6, characterized in that: The training sample set construction unit comprises: An initial force field generating unit, used to generate an initial force field through a large force field model; wherein the initial force field includes a plurality of initial configurations; An active learning unit, used for performing active learning using the initial force field to obtain multiple target configurations; The calculation unit is used to perform first principle calculation on each training sample configuration to obtain physical information of the training sample configuration; wherein the training sample configuration includes multiple initial configurations and multiple target configurations.

8. The simulation device based on machine learning and molecular dynamics according to claim 7, characterized in that: The physical information of the training sample configuration includes the interatomic forces and energy of the training sample configuration.

9. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the simulation method based on machine learning and molecular dynamics as described in any one of claims 1 to 4.

10. A computer storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the simulation method based on machine learning and molecular dynamics as claimed in any one of claims 1 to 4 is implemented.

Images