A Method for Constructing a Grain Evolution Model of the Entire Hot Manufacturing Process of Nuclear Power Steel Based on High-Throughput Characterization and Data-Driven Approach

Abstract

This invention proposes a method for constructing a grain evolution model for the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approaches. By designing samples with high-throughput grain configurations and performing full-domain high-throughput microstructural characterization, massive amounts of crystallographic information on micro-region structures are obtained, providing parameterized expressions suitable for describing each grain configuration. Through cross-scale multiphysics modeling using rigid-visco-plastic finite element method and crystal plastic finite element method, the distribution law and quantitative description of deformation energy storage in each micro-region of large-size nuclear power austenitic steel under different hot deformation process conditions are investigated. A data-driven model of the relationship between hot deformation, deformation energy storage, and solid solution grain configuration in nuclear power austenitic steel is constructed, forming an active control strategy and method for controlling coarse / mixed grains in nuclear power austenitic steel. This invention can provide theoretical and methodological support for accurate quantitative prediction of grain evolution and active control of abnormal grains throughout the entire hot manufacturing process of key nuclear power components.

Description

Technical Field

[0001] This invention relates to the fields of materials science and engineering technology, and in particular to a method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approaches. Background Technology

[0002] In the field of materials science, particularly in the manufacturing of critical materials such as austenitic steel for nuclear power plants, grain size and uniformity are key factors determining the final service performance of the product. Hot deformation (such as forging and rolling) and heat treatment processes significantly influence the grain configuration of materials. Although scholars both domestically and internationally have conducted extensive research on grain evolution, these studies often focus on grain changes in specific materials at specific process stages (e.g., only during hot deformation or heat treatment), lacking a comprehensive analysis covering the entire thermal manufacturing process.

[0003] Currently, quantitative descriptions of grain evolution mainly rely on phenomenological and physical models. These models fail to fully consider the coupling effects of thermal deformation and heat treatment processes, and have significant shortcomings in coupling grain topology parameters with micro-region energy parameters. Furthermore, they are limited by the number of experimental samples and the combination of process parameters, making it difficult to fully reflect the complexity of grain evolution in actual production. In addition, the accuracy of physical models is limited by the accuracy of basic assumptions and the rationality of parameter selection, which often leads to large calculation errors.

[0004] Therefore, how to comprehensively consider the interaction between multiple processes, explore the intrinsic mechanism from an energy perspective, and establish a data-driven full-process grain evolution model has become an urgent problem to be solved. Summary of the Invention

[0005] To overcome the limitations of existing materials science prediction models in considering the influence of multiple processes and coupling grain topology parameters with micro-region energy parameters, this invention proposes a method for constructing a full-process grain evolution model for the hot manufacturing of nuclear power steel based on high-throughput characterization and data-driven approaches. By designing samples with high-throughput grain configurations and performing full-domain high-throughput microstructural characterization, massive amounts of crystallographic information on micro-region structures are obtained, providing parameterized expressions suitable for describing each grain configuration, and constructing a mapping database of sample micro-region coordinates, hot-deformed grains, and solid-solution grains. Through cross-scale multiphysics modeling using rigid-viscoplastic finite element method and crystal plastic finite element method, the distribution law and quantitative description of deformation energy storage in each micro-region of large-size nuclear power austenitic steel under different hot deformation process conditions are investigated. A data-driven model of the relationship between hot deformation, deformation energy storage, and solid-solution grain configuration in nuclear power austenitic steel is constructed, forming an active control strategy and method for controlling coarse-grained / mixed-grained properties in nuclear power austenitic steel. This invention can provide theoretical and methodological support for the accurate quantitative prediction of grain evolution and active control of abnormal grains in the entire process of thermal manufacturing of key nuclear power components. It is expected to break through the process control bottleneck of grain size and uniformity of nuclear power main pipeline forgings made of large austenitic steel.

[0006] Therefore, the present invention provides the following technical solution:

[0007] This invention discloses a method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approaches, including:

[0008] Several sets of hot deformation and heat treatment experiments were conducted on large-size gradient austenitic steel samples for nuclear power plants with a large strain range. High-throughput characterization was performed on the samples after hot deformation and heat treatment to obtain a large amount of crystallographic data under hot deformation and solid solution conditions.

[0009] Based on the massive crystallographic data of grains under the aforementioned hot deformation and solid solution conditions, the grain configuration shape characteristics are digitally expressed to form a micro-area process parameter and grain configuration dataset.

[0010] Based on the massive crystallographic data of grains under the aforementioned hot deformation and solid solution conditions, the micro-region energy under the full-range hot deformation of large-size samples is calculated, and the deformation energy storage corresponding to the grain configuration of each micro-region in the full range is obtained.

[0011] The micro-region process parameters, grain configuration dataset, and deformation energy storage dataset are used to form an austenitic steel dataset.

[0012] A data-driven model for hot deformation-deformation energy storage-solution grain configuration of austenitic steel for nuclear power is constructed using the austenitic steel dataset. The input of the model is the micro-region process parameters and the grain configuration dataset, and the output of the model is the strain range generated by coarse grains / mixed grains at each deformation temperature. The model uses a clustering algorithm to identify the local domains of the austenitic steel data, uses Gaussian process regression to establish a corresponding local prediction model for each local domain, integrates the various local models through a finite mixing mechanism, and uses ensemble learning to combine and weight the various local models to obtain the final prediction result.

[0013] Furthermore, high-throughput experiments were conducted on large-size gradient austenitic steel samples for nuclear power plants with a wide strain range, and the experimental results of high-throughput characterization were obtained, including:

[0014] Samples were taken from forged austenitic steel specimens for nuclear power, and high-temperature stress-strain curves and thermophysical parameters of the material were obtained using thermal / mechanical simulation equipment. Constitutive equations for austenitic steel for nuclear power were constructed for finite element simulation of temperature and strain fields after hot deformation.

[0015] Design a double-wedge-shaped specimen and perform 950°C testing. o C~1200 o In the hot deformation experiment within the range of C, a sample with gradient strain along the long axis was obtained. After cutting the sample along the long axis profile of the hot-deformed sample, electron backscatter diffraction (EBSD) was performed to prepare the sample. The large-area splicing module was used to quickly and with high throughput acquire the sample to obtain grain information in the entire range.

[0016] Furthermore, it also includes:

[0017] Based on the experimental results of high-throughput characterization, the grain evolution law of the entire hot manufacturing process of austenitic steel for nuclear power was analyzed.

[0018] Furthermore, based on the experimental results of high-throughput characterization, the grain evolution law of the entire hot manufacturing process of austenitic steel for nuclear power was analyzed, including:

[0019] Finite element simulations were performed on the temperature and strain fields of the specimen after hot deformation to obtain the strain and temperature distribution along the long axis. Strain and temperature contour maps were plotted over the entire range after hot deformation to study the evolution of microstructure within the continuous strain range after hot deformation and solution treatment.

[0020] Furthermore, based on the experimental results, the grain configuration shape characteristics are digitally represented to form a grain configuration dataset, including:

[0021] Based on the shape characteristics of the grain configuration after thermal deformation in the experimental results, each grain configuration is expressed parametrically.

[0022] By combining the parameterized expression of each grain configuration and the micro-region coordinates of the sample, the two-dimensional topological structure of the grain configuration after hot deformation is digitized, forming a sample micro-region coordinate-hot-deformed grain configuration mapping database.

[0023] Based on the characteristics of equiaxed grains after solution treatment in the experimental results, the morphological features of the grain configuration after solution treatment were determined.

[0024] By combining the sample micro-area coordinate-thermal deformation grain configuration mapping database and the solid solution grain configuration shape characteristics, a micro-area coordinate-thermal deformation grain-solid solution grain mapping database is formed.

[0025] Furthermore, based on the experimental results, the micro-region energy under global thermal deformation of the large-size sample is calculated to obtain the deformation energy storage corresponding to the grain configuration of each micro-region across the entire range, including:

[0026] The temperature and strain fields of large-size wedge-shaped austenitic steel for nuclear power plants under macroscopic thermal load conditions were calculated using the rigid-visco-plastic finite element method.

[0027] Based on the high-throughput EBSD characterization results, a large-size, multi-scale microstructure mean-field model based on dislocation density is constructed. Thermal stress components, free parameters, and average activation energy are introduced to calculate the energy barrier parameters that control the thermal motion of dislocations. The control equations for dislocation motion at high temperatures are established, and then a large-size, multi-scale crystal plasticity model based on dislocation density is constructed under high-temperature deformation conditions.

[0028] For each local micro-region selected at uniform intervals in a large-sized wedge block, the temperature and strain data of the local micro-regions are extracted as inputs to the crystal plasticity model to obtain the dislocation density of the local micro-regions.

[0029] according to Calculate the deformation energy storage of a local micro-region, where, For dislocation density, It is the shear modulus. It is a Bergman vector; , It is a constant;

[0030] The dislocation motion control equation under high temperature conditions is governed by the following equation:

[0031] (1)

[0032] (2)

[0033] In equation (1), the dislocation densities of each term correspond to the generation of singlet dislocation density and the reduction of dislocation density caused by dipole formation, respectively; where: The time derivative of the dislocation density represents the rate of change of the dislocation density with time, i.e., the evolution of the dislocation density. Grain size; Shear strain rate; The diffusion coefficient is related to dislocations; The mean free path; This is the dislocation slip distance;

[0034] In equation (2), the dislocation densities of each term correspond to the formation of dislocation dipoles, the spontaneous annihilation of dipoles, and the annihilation of dipoles due to dislocation climb, respectively; where: and These represent the maximum and minimum values ​​of the dislocation slip distance;

[0035] High-temperature thermal stress and high-temperature shear rate are derived from equations (3) and (4):

[0036] (3)

[0037] (4)

[0038] (5)

[0039] in, This represents the shear strain rate in the α dislocation system; This represents the dislocation density in a dislocation system. The reference velocity for dislocations; This represents the number of times a dislocation attempts to cross the energy barrier per second during thermal activation. It is a constant related to dislocation motion;

[0040] The activation free energy constant for dislocation motion; It is an Arrhenius factor, representing the energy barrier that the system overcomes at a given temperature T. The probability of; is the Boltzmann constant. This represents the total shear stress in the 𝛼 dislocation system; This represents the shear stress determined by the dislocation density and microstructure of the material. Indicates the thermally activated stress term; Indicates the reference stress; Indicates temperature; An empirical index representing stress and thermal activation;

[0041] Based on the crystal plasticity model, the crystal plasticity constitutive equation is used to obtain the deformation energy storage between adjacent microregions through linear interpolation, and then the deformation energy storage corresponding to the grain configuration of each microregion in the whole domain is obtained.

[0042] Furthermore, the micro-area process parameters, grain configuration dataset, and deformation energy storage are combined to form an austenitic steel dataset, including:

[0043] By integrating micro-region process parameters, grain configuration datasets, and deformable energy storage, a multi-modal perturbation mechanism is used to randomly sample the data, add noise, or artificially change the data to generate different data modes.

[0044] Furthermore, it also includes: constructing an adaptive update module incremental update prediction model, enabling the model to be updated online based on newly acquired austenitic steel data.

[0045] Furthermore, it also includes: model validation;

[0046] The model validation includes:

[0047] Hot deformation and solution treatment experiments were conducted with different combinations of process parameters within the hot deformation temperature range of 950℃ to 1200℃ and the strain range of 0 to 1.39. The grain size of the sample after solution treatment was obtained, and the actual value was compared with the model prediction value to verify the accuracy of the model and to correct the model.

[0048] Furthermore, it also includes:

[0049] The strain range of coarse / mixed grains generated at various deformation temperatures is determined using the model. A three-dimensional process range diagram of abnormal grain growth is drawn to clarify the relationship between abnormal grain growth and hot deformation process parameters and deformation energy storage. The correlation between the physical mechanism of coarse / mixed grain formation and process parameters is explored. A safe processing range to avoid abnormally grown grains is established. Abnormal grains are controlled throughout the hot manufacturing process of austenitic steel for nuclear power based on the safe processing range.

[0050] Advantages and positive effects of the present invention:

[0051] (1) In this invention, by designing high-throughput samples and performing full-domain high-throughput microstructure characterization, a large amount of crystallographic information of micro-region structure is obtained. These data provide a solid foundation for subsequent modeling and analysis. Furthermore, by using a data-driven fusion modeling method, a data-driven model of the hot deformation-deformation energy storage-solid solution grain configuration relationship of austenitic steel for nuclear power is constructed. This model can comprehensively consider the influence of multiple manufacturing processes on the grain evolution of the material, effectively describe and predict the grain evolution of the material under different process conditions, and improve the accuracy and practicality of the model prediction.

[0052] (2) In this invention, a systematic data management method is established by constructing a mapping database of sample micro-region coordinates-hot deformation grains-solution grains, which provides strong support for material performance prediction and process optimization.

[0053] (3) In this invention, a multi-scale multi-physics modeling scheme integrating rigid-visco-plastic finite element method and crystal plastic finite element method is proposed, which provides an effective means for studying the deformation energy storage corresponding to the grain configuration of each micro-region in the whole domain of large-size sample. It can explore the distribution law of deformation energy storage in each micro-region under different hot deformation process conditions of large-size nuclear power austenitic steel and make a quantitative description.

[0054] (4) Based on model analysis, this invention proposes an active control strategy and method for coarse / mixed grains in austenitic steel for nuclear power, providing a scientific basis for improving material uniformity and performance. This invention can provide theoretical and methodological support for accurate quantitative prediction of grain evolution and active control of abnormal grains throughout the entire thermal manufacturing process of key nuclear power components. It is expected to break through the process control bottleneck of grain size and uniformity in large austenitic steel forgings for nuclear power main pipelines, thereby improving the safety and reliability of nuclear power equipment. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a flowchart of a method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approaches, as described in an embodiment of the present invention.

[0057] Figure 2 This is a flowchart of material parameter acquisition and high-throughput experimental characterization in an embodiment of the present invention;

[0058] Figure 3 This is a flowchart illustrating the process of establishing a database for extracting grain feature parameters and mapping grain configuration in an embodiment of the present invention.

[0059] Figure 4 This is a flowchart illustrating the calculation of micro-region energy under global thermal deformation of a large-size sample in an embodiment of the present invention.

[0060] Figure 5 This is a schematic diagram of the grain evolution model of the entire hot manufacturing process of nuclear power steel, as described in this embodiment of the invention.

[0061] Figure 6 This is a flowchart illustrating the abnormal grain control process in an embodiment of the present invention. Detailed Implementation

[0062] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0063] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0064] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven methods, comprising:

[0065] S1. Several sets of hot deformation and heat treatment experiments were conducted on large-size gradient austenitic steel samples for nuclear power with a large strain range. High-throughput characterization was performed on the samples after hot deformation and heat treatment to obtain a large amount of crystallographic data under hot deformation and solid solution conditions.

[0066] In specific implementation, such as Figure 2 As shown, the acquisition of material parameters and high-throughput experimental characterization include:

[0067] Samples were taken from forged austenitic steel specimens for nuclear power applications, and high-temperature stress-strain curves and thermophysical parameters were obtained using thermal / mechanical simulation equipment. Constitutive equations for the austenitic steel for nuclear power applications were constructed for finite element simulation of the temperature and strain fields after hot deformation. Double-wedge specimens were designed and subjected to 950°C testing. o C~1200 o In the hot deformation experiment within the range of C, a sample with gradient strain along the long axis was obtained. After cutting the sample along the long axis profile of the hot-deformed sample, electron backscatter diffraction (EBSD) was performed to prepare the sample. The large-area splicing module was used to quickly and with high throughput acquire the sample to obtain grain information in the entire range.

[0068] Furthermore, based on the experimental results of high-throughput characterization, the grain evolution law of the entire hot manufacturing process of austenitic steel for nuclear power can be analyzed. Specifically, finite element simulations are performed on the temperature and strain fields of the samples after hot deformation to obtain the strain and temperature distribution along the long axis. Strain and temperature contour maps are plotted over the entire range after hot deformation to study the microstructure evolution law within the continuous strain range after hot deformation and solution treatment (the dependence of recrystallization mechanism on strain at different deformation temperatures; quantitative expression of the critical conditions for initiation of different recrystallization types; the characteristic distribution law of grains after solution treatment; the correlation between hot-deformed grains and solution-treated grains).

[0069] S2. Based on the massive crystallographic data of grains obtained under hot deformation and solid solution conditions, the grain configuration shape characteristics are digitally expressed to form a micro-area process parameter and grain configuration dataset.

[0070] In specific implementation, such as Figure 3 As shown, a database for extracting grain feature parameters and mapping grain configurations is established, including:

[0071] S21. Based on the shape characteristics of the grain configuration after thermal deformation in the experimental results, each grain configuration is expressed parametrically.

[0072] S22. Combining the parameterized expression of each grain configuration and the micro-region coordinates of the sample, the two-dimensional topological structure of the grain configuration after hot deformation is digitized to form a sample micro-region coordinate-hot-deformed grain configuration mapping database.

[0073] S23. Based on the characteristics of equiaxed grains after solid solution in the experimental results, determine the grain configuration shape characteristics after solid solution.

[0074] S24. Combining the sample micro-area coordinate-hot-deformed grain configuration mapping database and the grain configuration shape characteristics after solid solution, a micro-area coordinate-hot-deformed grain-solid solution grain mapping database is formed.

[0075] S3. Based on the massive crystallographic data of grains obtained under hot deformation and solid solution conditions, the energy of micro-regions under full-domain hot deformation of large-size samples is calculated to obtain the deformation energy storage corresponding to the grain configuration of each micro-region in the full domain.

[0076] In specific implementation, such as Figure 4 As shown, the calculation of micro-region energy under global thermal deformation of a large-size specimen includes:

[0077] S31. The temperature and strain fields of large-size wedge-shaped austenitic steel for nuclear power plants under macroscopic thermal load conditions are calculated using the rigid-visco-plastic finite element method.

[0078] S32. Based on the high-throughput EBSD characterization results, construct a large-size, multi-scale microstructure mean-field model based on dislocation density. Introduce thermal stress components, free parameters, and average activation energy to calculate the energy barrier parameter ΔF that controls the thermal motion of dislocations. Establish the dislocation motion control equation under high temperature and then construct a large-size, multi-scale crystal plasticity model based on dislocation density under high temperature deformation conditions.

[0079] Crystal plasticity models refer to theoretical frameworks used to describe the plastic deformation behavior of materials at the microscale (such as crystal structure and dislocation motion). Crystal plasticity models consider the microstructural characteristics and deformation mechanisms of materials, typically including descriptions of phenomena such as slip systems, twinning, and phase transitions. They provide a foundation for understanding the anisotropy, hardening behavior, and deformation mechanisms of materials.

[0080] S33. For each local micro-region selected at uniform intervals in a large-sized wedge block, extract the temperature and strain data of the local micro-region as input to the crystal plasticity model to obtain the dislocation density of the local micro-region.

[0081] S34, according to Calculate the deformation energy storage of a local micro-region, where, For dislocation density, It is the shear modulus. It is a Bergman vector; , It is a constant;

[0082] The dislocation motion control equation under high temperature conditions is governed by the following equation:

[0083] (1)

[0084] (2)

[0085] In equation (1), the dislocation densities of each term correspond to the generation of singlet dislocation density and the reduction of dislocation density caused by dipole formation, respectively; where: The time derivative of the dislocation density represents the rate of change of the dislocation density with time, i.e., the evolution of the dislocation density. Grain size; Shear strain rate; It is the Burgers vector; The diffusion coefficient is related to dislocations; The mean free path; This is the dislocation slip distance;

[0086] In equation (2), the dislocation densities of each term correspond to the formation of dislocation dipoles, the spontaneous annihilation of dipoles, and the annihilation of dipoles due to dislocation climb, respectively; where: and These represent the maximum and minimum values ​​of the dislocation slip distance;

[0087] High-temperature thermal stress and high-temperature shear rate are derived from equations (3) and (4):

[0088] (3)

[0089] (4)

[0090] (5)

[0091] in, This represents the shear strain rate in the α dislocation system; This represents the dislocation density in a dislocation system. The reference velocity for dislocations; This represents the number of times a dislocation attempts to cross the energy barrier per second during thermal activation. It is a constant related to dislocation motion; The activation free energy constant for dislocation motion; It is an Arrhenius factor, representing the energy barrier that the system overcomes at a given temperature T. The probability of; is the Boltzmann constant. This represents the total shear stress in the 𝛼 dislocation system; This represents the shear stress determined by the dislocation density and microstructure of the material. Indicates the thermally activated stress term; Indicates the reference stress; Indicates temperature; An empirical index representing stress and thermal activation.

[0092] S35. Based on the crystal plasticity model, the crystal plasticity constitutive equation is used to obtain the deformation energy storage between adjacent micro-regions through linear interpolation, and then the deformation energy storage corresponding to the grain configuration of each micro-region in the whole domain is obtained, thus solving the calculation problem of large-size models.

[0093] The crystal plasticity constitutive equation is the mathematical expression of the crystal plasticity model, which specifies the stress-strain relationship of a material under external loading. It is usually given in the form of an equation, describing the flow behavior, hardening or softening properties of the material under different conditions.

[0094] In this embodiment of the invention, after establishing a crystal plasticity model, the energy stored in micro-region deformation is calculated. The crystal plasticity constitutive equation is solved accurately and quickly using the fast Fourier transform equation method and the augmented Lagrange algorithm. Then, the constitutive equation is used to expand the energy stored in micro-region deformation to the macroscopic scale, forming a cross-scale modeling method.

[0095] S4. Combine the micro-region process parameters, grain configuration dataset, and deformation energy storage data to form an austenitic steel dataset.

[0096] Based on the above steps, micro-region process parameters, grain configuration datasets, and deformation energy storage are obtained. The micro-region process parameters, deformation energy storage, and grain configuration datasets are integrated, and a multi-modal perturbation mechanism is used to randomly sample the data, add noise, or artificially change it to generate different data modes, so as to increase the diversity of training data.

[0097] S5. Construct a data-driven model of hot deformation-deformation energy storage-solution grain configuration for austenitic steel used in nuclear power using austenitic steel dataset;

[0098] The model's input consists of micro-region process parameters and grain configuration datasets, while its output is the strain range generated by coarse grains / mixed grains at each deformation temperature. The model uses a clustering algorithm to identify local domains of austenitic steel data, uses Gaussian process regression to establish a corresponding local prediction model for each local domain, integrates the various local models through a finite mixing mechanism, and employs ensemble learning to combine and weight the various local models to obtain the final prediction result.

[0099] Furthermore, an adaptive update module incremental update prediction model can be constructed, enabling the model to be updated online based on newly acquired austenitic steel data.

[0100] Furthermore, verification experiments were designed to conduct hot deformation and solution treatment experiments with different combinations of process parameters within the hot deformation temperature range of 950℃ to 1200℃ and the strain range of 0 to 1.39. The grain size of the sample after solution treatment was obtained, and the actual values ​​were compared with the model prediction values ​​to verify the accuracy of the hot deformation process parameters (temperature, strain)-deformation energy storage-grain configuration mapping model. The model was then corrected to realize the prediction of grain evolution throughout the hot manufacturing process of austenitic steel for nuclear power.

[0101] In the above embodiments, high-throughput global characterization technology and cross-scale modeling and simulation are combined to construct a data-driven model for predicting grain size in the hot deformation-solution process of austenitic steel for nuclear power plants. Its technical advantages are:

[0102] (1) In view of the actual hot deformation process characteristics of austenitic steel for nuclear power, a high-throughput experiment and full-domain EBSD characterization were innovatively proposed to obtain the crystallographic feature information of grains corresponding to a large number of process parameter combinations, providing a big data foundation for the establishment of the mapping model.

[0103] (2) Considering the mutual influence between multiple processes, we can explore the internal causes from the perspective of energy, quantify the relationship between hot deformation process parameters and grain structure and deformation energy storage, and hope to form a new method for predicting grain evolution under complex multi-physics fields and multiple processes, thus breaking through the bottleneck of related theoretical research.

[0104] (3) Couple grain topology parameters with micro-region energy parameters to construct a data-driven thermal deformation-solution grain prediction model. The model clarifies the relationship between abnormal grain growth and thermal deformation process parameters such as deformation temperature and strain, as well as deformation energy storage.

[0105] In another embodiment, the data-driven model constructed in the above embodiments can be used for abnormal grain control, specifically, as follows: Figure 5 As shown, the strain range of coarse / mixed grains generated at various deformation temperatures is determined using a model, a three-dimensional process range diagram of abnormal grain growth is drawn, the relationship between abnormal grain growth and hot deformation process parameters and deformation energy storage is clarified, the correlation between the physical mechanism of coarse / mixed grain formation and process parameters is explored, a safe processing range to avoid abnormally grown grains is established, and abnormal grains are controlled throughout the hot manufacturing process of austenitic steel for nuclear power based on the safe processing range.

[0106] In the above embodiments, based on the constructed grain prediction data-driven model of the hot deformation-solution process of austenitic steel for nuclear power, an active control strategy for coarse-grained / mixed-grained structural defects in the whole-process hot manufacturing of austenitic steel for nuclear power is formed, providing theoretical and methodological support for accurate quantitative prediction of grain evolution and control of abnormal grain growth in the whole-process hot manufacturing of large forgings.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approach, characterized in that, include: Several sets of hot deformation and heat treatment experiments were conducted on large-size gradient austenitic steel samples for nuclear power plants with a large strain range. High-throughput characterization was performed on the samples after hot deformation and heat treatment to obtain a large amount of crystallographic data under hot deformation and solid solution conditions. Based on the massive crystallographic data of grains under the aforementioned hot deformation and solid solution conditions, the grain configuration shape characteristics are digitally expressed to form a micro-area process parameter and grain configuration dataset. Based on the massive crystallographic data of grains under the aforementioned hot deformation and solid solution conditions, the micro-region energy under the full-range hot deformation of large-size samples is calculated, and the deformation energy storage corresponding to the grain configuration of each micro-region in the full range is obtained. The micro-region process parameters, grain configuration dataset, and deformation energy storage dataset are used to form an austenitic steel dataset. A data-driven model for hot deformation-deformation energy storage-solution grain configuration of austenitic steel for nuclear power is constructed using the austenitic steel dataset. The input of the model is the micro-region process parameters and the grain configuration dataset, and the output of the model is the strain range generated by coarse grains / mixed grains at each deformation temperature. The model uses a clustering algorithm to identify the local domains of the austenitic steel data, uses Gaussian process regression to establish a corresponding local prediction model for each local domain, integrates the various local models through a finite mixing mechanism, and uses ensemble learning to combine and weight the various local models to obtain the final prediction result.

2. The method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approach, as described in claim 1, is characterized in that... High-throughput experiments were conducted on large-size gradient austenitic steel samples for nuclear power plants with a wide strain range, and the experimental results of high-throughput characterization were obtained, including: Samples were taken from forged austenitic steel specimens for nuclear power, and high-temperature stress-strain curves and thermophysical parameters of the material were obtained using thermal / mechanical simulation equipment. Constitutive equations for austenitic steel for nuclear power were constructed for finite element simulation of temperature and strain fields after hot deformation. Design a double-wedge-shaped specimen and perform 950°C testing. o C~1200 o In the hot deformation experiment within the range of C, a sample with gradient strain along the long axis was obtained. After cutting the sample along the long axis profile of the hot-deformed sample, electron backscatter diffraction (EBSD) was performed to prepare the sample. The large-area splicing module was used to quickly and with high throughput acquire the sample to obtain grain information in the entire range.

3. The method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approach, as described in claim 2, is characterized in that... Also includes: Based on the experimental results of high-throughput characterization, the grain evolution law of the entire hot manufacturing process of austenitic steel for nuclear power was analyzed.

4. The method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approach, as described in claim 3, is characterized in that... Based on experimental results from high-throughput characterization, the grain evolution law of the entire hot manufacturing process of austenitic steel for nuclear power is analyzed, including: Finite element simulations were performed on the temperature and strain fields of the specimen after hot deformation to obtain the strain and temperature distribution along the long axis. Strain and temperature contour maps were plotted over the entire range after hot deformation to study the evolution of microstructure within the continuous strain range after hot deformation and solution treatment.

5. The method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approach, as described in claim 2, is characterized in that... Based on the experimental results, the grain configuration shape characteristics are digitally represented to form a grain configuration dataset, including: Based on the shape characteristics of the grain configuration after thermal deformation in the experimental results, each grain configuration is expressed parametrically. By combining the parameterized expression of each grain configuration and the micro-region coordinates of the sample, the two-dimensional topological structure of the grain configuration after hot deformation is digitized, forming a sample micro-region coordinate-hot-deformed grain configuration mapping database. Based on the characteristics of equiaxed grains after solution treatment in the experimental results, the morphological features of the grain configuration after solution treatment were determined. By combining the sample micro-area coordinate-thermal deformation grain configuration mapping database and the solid solution grain configuration shape characteristics, a micro-area coordinate-thermal deformation grain-solid solution grain mapping database is formed.

6. The method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approach, as described in claim 2, is characterized in that... Based on the experimental results, the micro-region energy under global thermal deformation of large-size samples was calculated, and the deformation energy storage corresponding to the grain configuration of each micro-region within the global range was obtained, including: The temperature and strain fields of large-size wedge-shaped austenitic steel for nuclear power plants under macroscopic thermal load conditions were calculated using the rigid-visco-plastic finite element method. Based on the high-throughput EBSD characterization results, a large-size, multi-scale microstructure mean-field model based on dislocation density is constructed. Thermal stress components, free parameters, and average activation energy are introduced to calculate the energy barrier parameters that control the thermal motion of dislocations. The control equations for dislocation motion at high temperatures are established, and then a large-size, multi-scale crystal plasticity model based on dislocation density is constructed under high-temperature deformation conditions. For each local micro-region selected at uniform intervals in a large-sized wedge block, the temperature and strain data of the local micro-regions are extracted as inputs to the crystal plasticity model to obtain the dislocation density of the local micro-regions. according to Calculate the deformation energy storage of a local micro-region, where, For dislocation density, It is the shear modulus. It is a Bergman vector; , It is a constant; The dislocation motion control equation under high temperature conditions is governed by the following equation: (1) (2) In equation (1), the dislocation densities of each term correspond to the generation of singlet dislocation density and the reduction of dislocation density caused by dipole formation, respectively; where: The time derivative of the dislocation density represents the rate of change of the dislocation density with time, i.e., the evolution of the dislocation density. Grain size; Shear strain rate; The diffusion coefficient is related to dislocations; The mean free path; This is the dislocation slip distance; In equation (2), the dislocation densities of each term correspond to the formation of dislocation dipoles, the spontaneous annihilation of dipoles, and the annihilation of dipoles due to dislocation climb, respectively; where: and These represent the maximum and minimum values ​​of the dislocation slip distance; High-temperature thermal stress and high-temperature shear rate are derived from equations (3) and (4): (3) (4) (5) in, This represents the shear strain rate in the α dislocation system; This represents the dislocation density in a dislocation system. The reference velocity for dislocations; This represents the number of times a dislocation attempts to cross the energy barrier per second during thermal activation. It is a constant related to dislocation motion; The activation free energy constant for dislocation motion; It is an Arrhenius factor, representing the energy barrier that the system overcomes at a given temperature T. The probability of; Boltzmann's constant; This represents the total shear stress in the 𝛼 dislocation system; This represents the shear stress determined by the dislocation density and microstructure of the material. Indicates the thermally activated stress term; Indicates the reference stress; Indicates temperature; An empirical index representing stress and thermal activation; Based on the crystal plasticity model, the crystal plasticity constitutive equation is used to obtain the deformation energy storage between adjacent microregions through linear interpolation, and then the deformation energy storage corresponding to the grain configuration of each microregion in the whole domain is obtained.

7. The method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approach, as described in claim 1, is characterized in that... The micro-area process parameters, grain configuration dataset, and deformation energy storage are used to form an austenitic steel dataset, including: By integrating micro-region process parameters, grain configuration datasets, and deformable energy storage, a multi-modal perturbation mechanism is used to randomly sample the data, add noise, or artificially change the data to generate different data modes.

8. The method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven approach, as described in claim 1, is characterized in that... Also includes: An adaptive update module incremental update prediction model is constructed to enable the model to be updated online based on newly acquired austenitic steel data.

9. A method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven methods, as described in any one of claims 1 to 8, characterized in that, It also includes: model validation; The model validation includes: Hot deformation and solution treatment experiments were conducted with different combinations of process parameters within the hot deformation temperature range of 950℃ to 1200℃ and the strain range of 0 to 1.

39. The grain size of the sample after solution treatment was obtained, and the actual value was compared with the model prediction value to verify the accuracy of the model and to correct the model.

10. A method for constructing a grain evolution model of the entire hot manufacturing process of nuclear power steel based on high-throughput characterization and data-driven methods, as described in any one of claims 1 to 8, characterized in that, Also includes: The strain range of coarse / mixed grains generated at various deformation temperatures is determined using the model. A three-dimensional process range diagram of abnormal grain growth is drawn to clarify the relationship between abnormal grain growth and hot deformation process parameters and deformation energy storage. The correlation between the physical mechanism of coarse / mixed grain formation and process parameters is explored. A safe processing range to avoid abnormally grown grains is established. Abnormal grains are controlled throughout the hot manufacturing process of austenitic steel for nuclear power based on the safe processing range.

Images