Methods, apparatus, computer equipment, and storage media for optimizing rapid annealing simulation parameters.

Abstract

This application relates to a method and apparatus for rapid annealing simulation parameter optimization. The method involves acquiring a silicon carbide parameter file; parsing the parameter file to read and organize system parameter information; inputting the system parameter information into a graph attention network (GAT) model to form a preliminary heating scheme; combining historical data and process requirements to generate a final heating scheme; and outputting the silicon carbide annealing results. This method solves the problem that existing annealing processes rely on empirical settings, making it difficult to find optimal solutions under different material and process conditions, thus failing to adapt to modern production needs and limiting the improvement of material performance and efficiency optimization. It achieves the technical effect of not only improving the accuracy and efficiency of the annealing process but also providing customized optimization schemes based on actual process requirements and historical data, meeting the needs of different users.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for optimizing rapid annealing simulation parameters. Background Technology

[0002] In modern materials science and semiconductor manufacturing, ion implantation has become a crucial technology for altering material properties and improving microstructure. Ion implantation involves injecting high-energy ions into the surface or interior of a material to modify its physical and chemical properties, thereby optimizing its electrical, thermal, and mechanical properties. However, ion implantation inevitably introduces lattice defects and internal stresses, which must be repaired through subsequent rapid annealing processes. Rapid annealing not only repairs the lattice structure but also promotes uniform ion distribution, enhancing material performance. Traditional annealing processes, lacking specificity and precise control, often result in excessive energy consumption or excessively long processing times. Furthermore, parameters at each stage of annealing, such as heating rate, holding time, and cooling rate, often rely on empirical settings, making it difficult to find optimal solutions under different material and process conditions. With increasing process complexity and material diversity, traditional annealing methods cannot fully meet modern production demands, thus limiting the improvement of material performance and the optimization of process efficiency. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, apparatus, computer equipment, storage medium, and computer program product for optimizing rapid annealing simulation parameters to address the aforementioned technical problems.

[0004] Firstly, this application provides a method for optimizing rapid annealing simulation parameters, the method comprising:

[0005] Obtain the silicon carbide parameter file;

[0006] Parse the parameter file, read and organize the system parameter information in the parameter file;

[0007] The system parameter information is input into the graph attention network model GAT to form a preliminary heating scheme;

[0008] Based on historical data and process requirements, a final heating scheme is generated;

[0009] The silicon carbide material was heated according to the final heating scheme described above;

[0010] Based on the characteristics of the silicon carbide material, process requirements, and industrial data, the heat preservation time is predicted and optimized.

[0011] Based on the status of the silicon carbide system, user requirements, and real data, the cooling path is predicted and optimized, including the cooling temperature and cooling rate.

[0012] Output the silicon carbide annealing results.

[0013] In one implementation, parsing the parameter file and reading and organizing the system parameter information in the parameter file includes:

[0014] The parser function is used to read the parameter file, perform bytecode conversion, and save the system parameter information to a list.

[0015] Read the system parameter information from the list and initialize it.

[0016] In one embodiment, the step of inputting the system parameter information into a graph attention network model to form a preliminary heating scheme includes:

[0017] The system parameter information is standardized.

[0018] Silicon carbide particles are used as nodes in the graph of the graph attention network model, and an adjacency matrix is ​​formed.

[0019] The standardized system parameter information is used as the silicon carbide material state data at multiple moments during the annealing process and input into the graph attention network model.

[0020] In one implementation, generating the final heating scheme by combining historical data and process requirements includes:

[0021] Input the node features and adjacency matrix into the GAT model;

[0022] Calculate the loss based on the model prediction results and the actual annealing results;

[0023] The model parameters are updated by minimizing the loss function, and the training is iterated for multiple epochs until the loss function converges or reaches the predetermined accuracy.

[0024] The annealing data is input into the GAT model to generate the final heating scheme; the final heating scheme includes the optimal heating temperature range, heating rate, and heating curve.

[0025] In one embodiment, the output silicon carbide annealing result includes:

[0026] Obtain key data during the annealing process;

[0027] The annealing results were evaluated based on the key data mentioned above.

[0028] In one embodiment, the key data includes the repair efficiency of silicon carbide lattice defects, ion energy distribution, residual stress, and strain distribution.

[0029] Secondly, this application also provides a rapid annealing simulation parameter tuning device, the device comprising:

[0030] The file acquisition module is used to acquire silicon carbide parameter files;

[0031] The parsing module is used to parse the parameter file, read and organize the system parameter information in the parameter file;

[0032] The first generation module is used to input the system parameter information into the graph attention network model GAT to form a preliminary heating scheme.

[0033] The second generation module is used to generate the final heating scheme by combining historical data and process requirements;

[0034] A heating module is used to heat the silicon carbide material according to the final heating scheme.

[0035] The insulation module is used to predict and optimize the insulation time based on the characteristics of the silicon carbide material, process requirements, and industrial data.

[0036] The cooling module is used to predict and optimize the cooling path based on the silicon carbide system status, user requirements, and real data. The cooling path includes cooling temperature and cooling rate.

[0037] The output module is used to output the silicon carbide annealing results.

[0038] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0039] Obtain the silicon carbide parameter file;

[0040] Parse the parameter file, read and organize the system parameter information in the parameter file;

[0041] The system parameter information is input into the graph attention network model GAT to form a preliminary heating scheme;

[0042] Based on historical data and process requirements, a final heating scheme is generated;

[0043] The silicon carbide material was heated according to the final heating scheme described above;

[0044] Based on the characteristics of the silicon carbide material, process requirements, and industrial data, the heat preservation time is predicted and optimized.

[0045] Based on the status of the silicon carbide system, user requirements, and real data, the cooling path is predicted and optimized, including the cooling temperature and cooling rate.

[0046] Output the silicon carbide annealing results.

[0047] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0048] Obtain the silicon carbide parameter file;

[0049] Parse the parameter file, read and organize the system parameter information in the parameter file;

[0050] The system parameter information is input into the graph attention network model GAT to form a preliminary heating scheme;

[0051] Based on historical data and process requirements, a final heating scheme is generated;

[0052] The silicon carbide material was heated according to the final heating scheme described above;

[0053] Based on the characteristics of the silicon carbide material, process requirements, and industrial data, the heat preservation time is predicted and optimized.

[0054] Based on the status of the silicon carbide system, user requirements, and real data, the cooling path is predicted and optimized, including the cooling temperature and cooling rate.

[0055] Output the silicon carbide annealing results.

[0056] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0057] Obtain the silicon carbide parameter file;

[0058] Parse the parameter file, read and organize the system parameter information in the parameter file;

[0059] The system parameter information is input into the graph attention network model GAT to form a preliminary heating scheme;

[0060] Based on historical data and process requirements, a final heating scheme is generated;

[0061] The silicon carbide material was heated according to the final heating scheme described above;

[0062] Based on the characteristics of the silicon carbide material, process requirements, and industrial data, the heat preservation time is predicted and optimized.

[0063] Based on the status of the silicon carbide system, user requirements, and real data, the cooling path is predicted and optimized, including the cooling temperature and cooling rate.

[0064] Output the silicon carbide annealing results.

[0065] The aforementioned rapid annealing simulation parameter optimization method, apparatus, computer equipment, storage medium, and computer program products acquire a silicon carbide parameter file; parse the parameter file, read and organize the system parameter information in the parameter file; input the system parameter information into a graph attention network model (GAT) to form a preliminary heating scheme; combine historical data and process requirements to generate a final heating scheme; heat the silicon carbide material according to the final heating scheme; predict and optimize the holding time based on the silicon carbide material characteristics, process requirements, and industrial data; predict and optimize the cooling path, including cooling temperature and cooling rate, based on the silicon carbide system status, user needs, and real data; and output the silicon carbide annealing results. This solves the problem that existing annealing processes rely on empirical settings, making it difficult to find the optimal solution under different material and process conditions, failing to adapt to modern production needs, and limiting the improvement of material performance and efficiency optimization. It not only improves the accuracy and efficiency of the annealing process but also provides customized optimization schemes based on actual process requirements and historical data to meet the needs of different users. Attached Figure Description

[0066] Figure 1 This is a flowchart illustrating a method for optimizing simulation parameters in a fast annealing exercise, as shown in one embodiment.

[0067] Figure 2 This is a structural block diagram of a rapid annealing simulation parameter optimization device in one embodiment;

[0068] Figure 3 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0069] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0070] This application provides a parameter optimization method and system for simulating rapid annealing of silicon carbide after ion implantation. The aim is to optimize the parameters of the rapid annealing process after silicon carbide ion implantation using a graph attention network (GAT) to achieve optimal control of the heating, holding, and cooling stages. By acquiring relevant system parameters and inputting them into a trained network model, the heating temperature, holding time, and cooling path are predicted and optimized to ensure that the silicon carbide material maintains its optimal physical state during annealing, achieving reasonable ion distribution, lattice repair, and stable material properties. Furthermore, this method can be further optimized based on the trained model and actual industrial data to ensure the scientific validity of the simulation results and their close relevance to actual process requirements. Customized optimization can also be performed according to user needs to achieve annealing schemes with minimal energy or shortest time.

[0071] In one embodiment of this application, such as Figure 1 As shown, a method for optimizing rapid annealing simulation parameters is provided, the method comprising:

[0072] S100, obtain silicon carbide parameter file.

[0073] The system retrieves a user-imported custom silicon carbide input parameter file and reads relevant parameters of the system to be simulated, including system-related information such as the distribution of Si and C elements.

[0074] S200, parse the parameter file, read and organize the system parameter information in the parameter file.

[0075] In one embodiment of this application, S200 further includes the following steps:

[0076] (1) Use the parser function to read the parameter file, perform bytecode conversion, and save the system parameter information to a list.

[0077] The parser function in the initialization module reads the input file containing user-defined system parameters, performs bytecode conversion, and saves the processed system parameters to a list.

[0078] (2) Read the system parameter information in the list and initialize it.

[0079] The system parameter information in the generated list is read using the `read_parameters()` function in the input module and initialized using the `init_parameters()` function. System parameters not set in the input will be assigned default values.

[0080] The main system parameter information includes the concentration and location of different elements in the silicon carbide system, information about different isomers in the material, the initial temperature of the material, the aggregate size and boundary conditions of the system, as well as other simulation-related parameters.

[0081] S300, the system parameter information is input into the graph attention network model GAT to form a preliminary heating scheme.

[0082] Specifically, the system parameter information read from S200 is input into the pre-trained Graph Attention Network (GAT) model. The GAT model performs preliminary analysis based on this system parameter information, generates a preliminary heating scheme, and predicts the optimal heating temperature range.

[0083] In one implementation, S300 includes the following steps:

[0084] (1) Standardize the system parameter information.

[0085] Before inputting system parameter information into the GAT model, the data needs to be standardized using the standard() function to ensure that parameters of different dimensions can be correctly processed by the model and to improve the accuracy of training and prediction.

[0086] (2) Use silicon carbide particles as nodes in the graph in the graph attention network model and form an adjacency matrix.

[0087] Silicon carbide ions are used as nodes in the graph of the GAT model, and edges are established based on inter-ion forces to form an adjacency matrix. Node features include the physical properties of each silicon carbide ion, such as temperature; the edge weights reflect the interaction strength between nodes, such as distance and energy exchange.

[0088] (3) The standardized system parameter information is used as the silicon carbide material state data at multiple moments during the annealing process and input into the graph attention network model.

[0089] The standardized system parameter information is then input into the model as silicon carbide material state data at multiple moments during the annealing process using the gat_layer() function.

[0090] S400, combining historical data and process requirements, generates the final heating scheme.

[0091] In this application, the GAT model combines historical data and actual process requirements to further optimize the material physical changes that may occur during the heating process, ensuring the thermodynamic stability and process accuracy of the annealing process. Specifically, S400 also includes the following steps:

[0092] (1) Input the node features and adjacency matrix into the GAT model.

[0093] Specifically, the node features and adjacency matrix are input into the GAT model through the heating_in() function, and the attention mechanism is used to calculate the weighted sum between each node and its neighboring nodes, thereby updating the feature representation of each node.

[0094] (2) Calculate the loss based on the model prediction results and the actual annealing results.

[0095] Specifically, the loss is calculated based on the model's predicted results and the actual annealing results, and the Adam optimization algorithm is used for backpropagation.

[0096] (3) Update the model parameters by minimizing the loss function and iterate for multiple training cycles until the loss function converges or reaches the predetermined accuracy.

[0097] (4) Input the annealing data into the GAT model and generate the final heating scheme; the final heating scheme includes the optimal heating temperature range, heating rate and heating curve.

[0098] Specifically, the annealing data collected by sensors during the actual process is input into the GAT model through the heating_fact() function for fine-tuning, making the model closer to the actual operating conditions.

[0099] Furthermore, based on the trained GAT model, a scheme including the optimal heating temperature range, heating rate, and heating curve is generated using the heating_plan() function for the next step.

[0100] S500, the silicon carbide material is heated according to the final heating scheme.

[0101] S600 predicts and optimizes the heat preservation time based on the characteristics of the silicon carbide material, process requirements, and industrial data.

[0102] After the heating is completed, the temperature is kept within the optimal range for a period of time. During this time, the GAT model will predict and optimize the holding time based on the material properties and process requirements to ensure that the ion distribution in the system reaches the optimal state, reduce lattice defects, and repair structural damage inside the material.

[0103] Specifically, the S600 includes the following steps:

[0104] (1) After the heating process is completed, the GAT model determines the optimal temperature range for the holding phase based on the generated heating curve.

[0105] (2) Based on the preliminary prediction of holding time, the GAT model uses the GATConv() function to invoke the attention mechanism to identify the key nodes (such as ion concentration or lattice state in specific regions) that have the greatest impact on the internal ion distribution and lattice repair of silicon carbide materials. Combined with process requirements, the GAT model focuses on optimizing these key nodes and dynamically adjusts the holding time. For example, under specific conditions, the GAT model may identify uneven ion distribution or insufficient repair in certain regions, thus requiring an extension or shortening of the holding time to ensure that the silicon carbide ion distribution in the system reaches equilibrium and that lattice defects are repaired to the optimal state. The entire optimization process relies on the GAT model's learning from historical data and the integration of process experience to ensure the accuracy and effectiveness of the silicon carbide annealing process.

[0106] (3) After optimization, the GAT model continuously applies an attention mechanism during the hold time phase to monitor the ion distribution and lattice repair effect inside the silicon carbide material in real time. Through the attention mechanism, the GAT model can focus on the regions with the greatest changes inside the material and dynamically track the ion distribution and lattice repair status of these nodes. If the model identifies uneven ion distribution or lattice repair effect at certain nodes, GAT will automatically adjust the attention level to these nodes and further adjust the overall hold time to ensure that the ion distribution inside the material is homogenized and lattice defects are effectively repaired, thereby optimizing the material performance.

[0107] S700 predicts and optimizes the cooling path based on the silicon carbide system status, user requirements, and real data. The cooling path includes cooling temperature and cooling rate.

[0108] After the temperature holding time ends, the cooling phase begins. The GAT model predicts and optimizes the cooling temperature range and cooling rate based on the current state of the annealing system, ensuring that the material properties of silicon carbide remain stable during cooling and avoiding new defects. Simultaneously, user requirements (such as minimizing energy or time) are input to fine-tune the cooling strategy and find the optimal cooling path and time.

[0109] Specifically, the S700 includes the following steps:

[0110] (1) After the holding time ends, the system enters the cooling phase. The GAT model first determines the starting temperature of the silicon carbide cooling process, i.e., the temperature of the material at the end of the holding phase, through the cooling_info() function. This temperature will serve as the starting condition for cooling, ensuring that cooling begins under suitable conditions.

[0111] (2) Based on the physical properties (such as thermal conductivity, coefficient of thermal expansion, melting point, etc.) and process requirements extracted in step (1), the GAT model analyzes the performance of silicon carbide material at different cooling rates using the cooling_performance() function. By analyzing the properties of silicon carbide, the model can assess whether new defects will be generated in silicon carbide during the cooling process, and formulate a cooling strategy based on this using the cooling_plan() function.

[0112] (3) Based on the determined cooling temperature range and cooling rate, the model will input the user's specific needs (such as minimizing energy, minimizing time, or optimizing material properties) into the model through the userneed_in() function, and then perform customized tuning of the cooling strategy: if the user prioritizes the shortest cooling time, the model will speed up the cooling rate; if minimizing energy consumption is the primary goal, the cooling rate will be reduced to reduce energy consumption.

[0113] (4) During steps (2) and (3), the model will monitor the state of the material in real time, such as temperature changes, internal structural stress and strain. If performance instability or inappropriate cooling rate occurs during the cooling process, the neural network will automatically adjust the cooling path and speed through the cooling_adjust() function to ensure the stability of the final material performance.

[0114] (5) During the cooling process, the model monitors the state of silicon carbide material in real time through the cooling_monitor() function, such as temperature changes, internal structural stress and strain. If performance instability or inappropriate cooling rate occurs during the cooling process, the model will automatically adjust the cooling path and speed to ensure the stability of the final material performance.

[0115] (6) After the completion of step (5), the neural network will output the final silicon carbide cooling scheme through the cooling_plan() function. The scheme includes the cooling start temperature, cooling temperature range, cooling rate, and the detection results of material properties during the cooling process to ensure that the material remains stable during the cooling stage and avoid the emergence of new defects.

[0116] S800 outputs the silicon carbide annealing results.

[0117] After cooling is complete, the system outputs the final results of silicon carbide annealing, including lattice defect repair efficiency, ion energy distribution, residual stress, and strain distribution. Using this data, the GAT model further optimizes the entire annealing process, assesses whether the expected process objectives have been achieved, and makes necessary optimizations and adjustments based on the results, providing feedback and guidance for subsequent process optimization.

[0118] Specifically, the S800 includes the following steps:

[0119] (1) Obtain key data during the annealing process. Key data include the repair efficiency of silicon carbide lattice defects, ion energy distribution, residual stress, and strain distribution.

[0120] After cooling is complete, the system outputs key data from the entire annealing process via the sys_output() function. This data includes the repair efficiency of silicon carbide lattice defects, ion energy distribution, residual stress, and strain distribution.

[0121] (2) Evaluate the annealing results based on the key data.

[0122] The GAT model uses data from the annealing process and the sys_analyze() function for comprehensive analysis to assess whether the expected process goals have been achieved. It focuses on whether lattice defects have been effectively repaired, whether ion energy is uniformly distributed, and whether new residual stress and strain have been generated within the material. If any indicators fail to meet expectations, the system will identify possible causes and record the problem points.

[0123] Therefore, this application provides a method for optimizing rapid annealing simulation parameters. It utilizes a graph attention network (GAT) to optimize the parameters of the rapid annealing process after silicon carbide ion implantation, achieving optimal control of the heating, holding, and cooling stages. By acquiring relevant system parameters and inputting them into a trained network model, the method predicts and optimizes the heating temperature, holding time, and cooling path, ensuring that the silicon carbide material maintains its optimal physical state during annealing, achieving reasonable ion distribution, lattice repair, and stable material properties. Furthermore, this method can be further optimized based on the trained model and actual industrial data, ensuring the scientific validity of the simulation results and their close relevance to actual process requirements. It can also be customized according to user needs to achieve annealing schemes with minimal energy or shortest time.

[0124] In addition, this application has the following advantages over the prior art:

[0125] (1) This application precisely controls the heating stage in the rapid annealing simulation process of silicon carbide. By inputting system parameters into GAT and combining historical data of silicon carbide with actual process requirements, the optimal heating scheme is generated. The model accurately predicts and optimizes the heating process, ensuring the thermodynamic stability of the material during the heating stage and avoiding physical stress or structural damage caused by improper temperature changes, thereby greatly improving the overall accuracy of the annealing process and making the process more controllable and stable;

[0126] (2) This application optimizes the holding time during the rapid annealing simulation process. The model predicts and fine-tunes the holding time based on material properties and process requirements to ensure uniform ion distribution within the silicon carbide material, reduce lattice defects, and repair structural damage. This optimization significantly improves lattice repair efficiency, enabling the material to undergo sufficient repair at the holding temperature and ensuring a significant performance improvement at the microstructural level.

[0127] (3) This application effectively controls the cooling stage during the rapid annealing simulation of silicon carbide. The GAT model optimizes the cooling temperature range and cooling rate based on the current state of the annealing system to ensure that no new stress or defects are generated during the cooling process. By optimizing the cooling strategy, the cooling path and time are optimally configured to ensure the stable performance of the material during the cooling stage, avoid unevenness or new defects in the material after annealing, and meet the user's energy or time requirements.

[0128] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0129] Based on the same inventive concept, this application also provides a device for optimizing rapid annealing simulation parameters as described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more embodiments of the rapid annealing simulation parameter optimization device provided below can be found in the limitations of the rapid annealing simulation parameter optimization method described above, and will not be repeated here.

[0130] In one embodiment, such as Figure 2 As shown, a rapid annealing simulation parameter tuning device is provided, comprising:

[0131] The file acquisition module 100 is used to acquire silicon carbide parameter files.

[0132] The parsing module 200 is used to parse the parameter file and read and organize the system parameter information in the parameter file.

[0133] The first generation module 300 is used to input the system parameter information into the graph attention network model GAT to form a preliminary heating scheme.

[0134] The second generation module 400 is used to generate the final heating scheme by combining historical data and process requirements.

[0135] The heating module 500 is used to heat the silicon carbide material according to the final heating scheme.

[0136] The insulation module 600 is used to predict and optimize the insulation time based on the characteristics of the silicon carbide material, process requirements, and industrial data.

[0137] The cooling module 700 is used to predict and optimize the cooling path based on the status of the silicon carbide system, user requirements and real data. The cooling path includes cooling temperature and cooling rate.

[0138] Output module 800 is used to output the silicon carbide annealing results.

[0139] In one embodiment, the parsing module 200 is further configured to:

[0140] The parser function is used to read the parameter file, perform bytecode conversion, and save the system parameter information to a list.

[0141] Read the system parameter information from the list and initialize it.

[0142] In one embodiment, the first generation module 300 is further configured to:

[0143] The system parameter information is standardized.

[0144] Silicon carbide particles are used as nodes in the graph of the graph attention network model, and an adjacency matrix is ​​formed.

[0145] The standardized system parameter information is used as the silicon carbide material state data at multiple moments during the annealing process and input into the graph attention network model.

[0146] In one embodiment, the second generation module 400 is further configured to:

[0147] Input the node features and adjacency matrix into the GAT model;

[0148] Calculate the loss based on the model prediction results and the actual annealing results;

[0149] The model parameters are updated by minimizing the loss function, and the training is iterated for multiple epochs until the loss function converges or reaches the predetermined accuracy.

[0150] The annealing data is input into the GAT model to generate the final heating scheme; the final heating scheme includes the optimal heating temperature range, heating rate, and heating curve.

[0151] In one embodiment, the output module 800 is further configured to:

[0152] Obtain key data during the annealing process;

[0153] The annealing results were evaluated based on the key data mentioned above.

[0154] In one embodiment, the key data includes the repair efficiency of silicon carbide lattice defects, ion energy distribution, residual stress, and strain distribution.

[0155] Each module in the aforementioned rapid annealing simulation parameter tuning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0156] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores preset data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a fast annealing simulation parameter tuning method.

[0157] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0158] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described fast annealing simulation parameter tuning method.

[0159] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described fast annealing simulation parameter tuning method.

[0160] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described fast annealing simulation parameter tuning method.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for optimizing rapid annealing simulation parameters, characterized in that, The method includes: Obtain the silicon carbide parameter file; Parse the parameter file, read and organize the system parameter information in the parameter file; The system parameter information is input into the graph attention network model GAT to form a preliminary heating scheme; Based on historical data and process requirements, a final heating scheme is generated; The silicon carbide material was heated according to the final heating scheme described above; Based on the characteristics of the silicon carbide material, process requirements, and industrial data, the heat preservation time is predicted and optimized. Based on the status of the silicon carbide system, user requirements, and real data, the cooling path is predicted and optimized, including the cooling temperature and cooling rate. Output the silicon carbide annealing results; The step of inputting the system parameter information into the graph attention network model (GAT) to form a preliminary heating scheme includes: The system parameter information is standardized. Silicon carbide particles are used as nodes in the graph of the graph attention network model, forming an adjacency matrix; silicon carbide ions are used as nodes in the graph of the GAT model, and edges are established based on inter-ion forces to form an adjacency matrix; node features include the physical properties of each silicon carbide ion; the weight of the edge reflects the interaction strength between nodes. The standardized system parameter information is used as the silicon carbide material state data at multiple moments during the annealing process and input into the graph attention network model. The process of combining historical data and process requirements to generate the final heating scheme includes: Input the node features and adjacency matrix into the GAT model; Calculate the loss based on the model prediction results and the actual annealing results; The model parameters are updated by minimizing the loss function, and the training is iterated for multiple epochs until the loss function converges or reaches the predetermined accuracy. The annealing data is input into the GAT model to generate the final heating scheme; the final heating scheme includes the optimal heating temperature range, heating rate, and heating curve.

2. The method according to claim 1, characterized in that, The process of parsing the parameter file and reading and organizing the system parameter information in the parameter file includes: The parser function is used to read the parameter file, perform bytecode conversion, and save the system parameter information to a list. Read the system parameter information from the list and initialize it.

3. The method according to claim 1, characterized in that, The output silicon carbide annealing results include: Obtain key data during the annealing process; The annealing results were evaluated based on the key data mentioned above.

4. The method according to claim 3, characterized in that The key data include the repair efficiency of silicon carbide lattice defects, ion energy distribution, residual stress, and strain distribution.

5. A rapid annealing simulation parameter tuning device, characterized in that, The device includes: The file acquisition module is used to acquire silicon carbide parameter files; The parsing module is used to parse the parameter file, read and organize the system parameter information in the parameter file; The first generation module is used to input the system parameter information into the graph attention network model GAT to form a preliminary heating scheme. The second generation module is used to generate the final heating scheme by combining historical data and process requirements; A heating module is used to heat the silicon carbide material according to the final heating scheme. The insulation module is used to predict and optimize the insulation time based on the characteristics of the silicon carbide material, process requirements, and industrial data. The cooling module is used to predict and optimize the cooling path based on the silicon carbide system status, user requirements, and real data. The cooling path includes cooling temperature and cooling rate. The output module is used to output the silicon carbide annealing results; The first generation module is further configured to: standardize the system parameter information; use silicon carbide particles as nodes in the graph of the graph attention network model and form an adjacency matrix; use silicon carbide ions as nodes in the graph of the GAT model and establish edges based on inter-ion forces to form an adjacency matrix; node features include the physical properties of each silicon carbide ion; edge weights reflect the interaction strength between nodes; and input the standardized system parameter information as silicon carbide material state data at multiple moments during the annealing process into the graph attention network model. The second generation module is also used to input node features and adjacency matrix into the GAT model; calculate loss based on model prediction results and actual annealing results; update model parameters by minimizing the loss function and iterate for multiple training cycles until the loss function converges or reaches a predetermined accuracy; input annealing data into the GAT model and generate a final heating scheme; the final heating scheme includes the optimal heating temperature range, heating rate and heating curve.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images