Mechanical property treatment method, device and equipment for austenitic heat-resistant steel

Abstract

The invention discloses a mechanical property treatment method, device and equipment for austenitic heat-resistant steel. The method comprises the following steps: determining mechanical property parameters and related factors of the austenitic heat-resistant steel in a target application scene; obtaining each value interval of each associated factor, and collecting the mechanical property measured value of the austenitic heat-resistant steel with the associated factor value in the value interval; constructing a mechanical property prediction model of the austenitic heat-resistant steel; determining a weight factor of each mechanical property parameter according to the target application scene, and weighting each mechanical property prediction value determined based on the mechanical property prediction model according to the weight factor to obtain a comprehensive mechanical property value; the comprehensive mechanical property values are clustered to obtain a clustering center, and at least two comprehensive mechanical property value intervals are determined according to the minimum performance threshold value of the target application scene and the center mechanical property value corresponding to the clustering center. According to the embodiment of the invention, the prediction precision and quality grading reliability of the comprehensive mechanical properties of the austenitic heat-resistant steel can be improved.

Description

Technical Field

[0001] This invention relates to the field of performance treatment technology, and in particular to a method, apparatus and equipment for treating the mechanical properties of austenitic heat-resistant steel. Background Technology

[0002] Austenitic heat-resistant steel, due to its excellent high-temperature strength, oxidation resistance, and corrosion resistance, is widely used in critical high-temperature and high-pressure equipment such as power plant boilers, aero-engines, and chemical containers. The service safety and reliability of such equipment highly depend on the comprehensive mechanical properties of austenitic heat-resistant steel. Therefore, accurately and comprehensively determining the comprehensive mechanical properties of austenitic heat-resistant steel is a core aspect of material research and development optimization, engineering selection and adaptation, and production quality control.

[0003] However, there are still many technical bottlenecks in the current field of determining the comprehensive mechanical properties of austenitic heat-resistant steel, making it difficult to meet the stringent requirements of high-end equipment for material performance. Traditional determination methods often focus on a single mechanical property parameter, failing to fully consider the complex coupling effects between material composition characteristics, microstructure features, heat treatment process parameters, and multiple mechanical property parameters. Existing determination systems mostly adopt a uniform determination method, failing to consider the differentiated requirements of key mechanical properties for different application scenarios, resulting in insufficient specificity of the determined mechanical property results, and failing to provide accurate support for material selection and safe service under specific working conditions. The accuracy of the determined mechanical properties is insufficient to meet the fine-grained control requirements of high-end equipment for material performance, restricting the application expansion of austenitic heat-resistant steel in high-requirement scenarios. Summary of the Invention

[0004] This invention provides a method, apparatus, and equipment for processing the mechanical properties of austenitic heat-resistant steel, in order to solve the problems of insufficient specificity and low accuracy of existing methods for determining the comprehensive mechanical properties of austenitic heat-resistant steel.

[0005] According to one aspect of the present invention, a method for treating the mechanical properties of austenitic heat-resistant steel is provided, comprising:

[0006] Determine the mechanical property parameters and related factors of austenitic heat-resistant steel in the target application scenario;

[0007] Obtain the value ranges for each related factor, and collect the measured mechanical properties of austenitic heat-resistant steel whose values ​​fall within the value ranges; the value ranges are determined based on the initial value ranges of the related factors and the degree of variation of austenitic heat-resistant steel within the initial value ranges.

[0008] Based on the values ​​of each related factor and the measured values ​​of the mechanical properties, a predictive model for the mechanical properties of austenitic heat-resistant steel is constructed.

[0009] The weighting factors of each mechanical performance parameter are determined according to the target application scenario, and the comprehensive mechanical performance value is obtained by weighting the predicted mechanical performance values ​​determined based on the mechanical performance prediction model according to the weighting factors.

[0010] Clustering is performed on the comprehensive mechanical property values ​​to obtain cluster centers. Based on the minimum performance threshold of the target application scenario and the central mechanical property value corresponding to the cluster center, at least two comprehensive mechanical property value ranges are determined to classify the mechanical properties of austenitic heat-resistant steel.

[0011] According to another aspect of the present invention, a mechanical property treatment apparatus for austenitic heat-resistant steel is provided, comprising:

[0012] The parameter filtering module is used to determine the mechanical property parameters and related factors of austenitic heat-resistant steel in the target application scenario.

[0013] The measured data acquisition module is used to acquire the value ranges of each related factor and collect the measured mechanical properties of austenitic heat-resistant steel whose values ​​of the related factors are within the value ranges; the value ranges are determined based on the initial value ranges of the related factors and the degree of variation of austenitic heat-resistant steel within the initial value ranges.

[0014] The model training module is used to construct a predictive model of the mechanical properties of austenitic heat-resistant steel based on the values ​​of each related factor and the measured values ​​of mechanical properties.

[0015] The weighting module is used to determine the weighting factors of each mechanical performance parameter according to the target application scenario, and to weight the predicted mechanical performance values ​​determined based on the mechanical performance prediction model according to the weighting factors to obtain the comprehensive mechanical performance value.

[0016] The grading interval module is used to cluster the comprehensive mechanical property values ​​to obtain cluster centers. Based on the minimum performance threshold of the target application scenario and the central mechanical property value corresponding to the cluster center, at least two comprehensive mechanical property value intervals are determined to grade the mechanical properties of austenitic heat-resistant steel.

[0017] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the mechanical property treatment method for austenitic heat-resistant steel according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the mechanical property treatment method for austenitic heat-resistant steel according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the mechanical property treatment method for austenitic heat-resistant steel according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer program product is provided, comprising a computer program / instructions that, when executed by a processor, implement the mechanical property treatment method for austenitic heat-resistant steel as described in any embodiment of the present invention.

[0022] This invention effectively solves the problems of insufficient specificity and disconnect from actual working conditions caused by the generalization and singularity of traditional performance determination methods by integrating the specific needs of the target application scenario into the entire process of determining the comprehensive performance of austenitic heat-resistant steel. Key mechanical performance parameters and related factors are determined based on the application scenario, and the scientific value range of related factors is obtained through verification and optimization based on the degree of variation, ensuring the specificity and representativeness of data collection. The constructed mechanical performance prediction model accurately reflects the coupling effect between multiple parameters. Combined with scenario-based weighting factors, the predicted values ​​are weighted and fused, enabling the comprehensive mechanical performance value to truly reflect the comprehensive performance level of the material, achieving precise quantification of the material's comprehensive performance. By combining cluster analysis with the scenario's minimum performance threshold, performance level ranges that fit actual engineering needs are intelligently divided, reducing subjective experience interference and anchoring the level division to the actual needs of the scenario, avoiding a disconnect between the level standard and application, ensuring the value of the level in determining the applicability of the material to the scenario, and ensuring the accuracy and reliability of the level determination rules. Furthermore, by verifying the conformity rate, the diverse scenarios of materials are covered, further ensuring the universality and accuracy of the level division standard, providing a clear and reliable basis for determining material performance. This provides a reliable, intuitive, and highly scenario-adaptable scientific decision-making basis for the research and development, selection, quality control, and service safety assessment of austenitic heat-resistant steel.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a first flowchart of a method for treating the mechanical properties of austenitic heat-resistant steel according to an embodiment of the present invention;

[0026] Figure 2 This is a second flowchart of a method for treating the mechanical properties of austenitic heat-resistant steel according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of the mechanical property treatment device for austenitic heat-resistant steel provided in an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of an electronic device that implements an embodiment of the present invention. Detailed Implementation

[0029] 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.

[0030] 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 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.

[0031] Figure 1This is a first flowchart of a method for treating the mechanical properties of austenitic heat-resistant steel according to an embodiment of the present invention. This embodiment is applicable to situations where comprehensive mechanical property determination, selection evaluation, quality grading, process optimization, or service safety assessment of austenitic heat-resistant steel materials are performed in specific application scenarios. This method can be executed by a mechanical property treatment device for austenitic heat-resistant steel, which can be implemented in hardware and / or software and can be configured in electronic equipment with corresponding data processing capabilities. Figure 1 As shown, the method includes:

[0032] S110. Determine the mechanical property parameters and related factors of austenitic heat-resistant steel for the target application scenario.

[0033] Based on the target application scenarios of austenitic heat-resistant steel, such as steel for power plant boilers and steel for aero-engines, we determine the mechanical property parameters that affect the comprehensive mechanical properties of austenitic heat-resistant steel in the target application scenarios, and identify the related factors that have a coupling effect with the mechanical property parameters.

[0034] The mechanical property parameters include room temperature tensile strength, room temperature yield strength, high temperature tensile strength, high temperature yield strength, flattening performance, flaring performance, high temperature creep strength, room temperature impact toughness, high temperature creep deformation, tensile and impact fracture modes, and brittle fracture area ratio. The related factors include the compositional characteristics, microstructure features, and heat treatment process parameters of the austenitic heat-resistant steel. The compositional characteristics include the content of elements such as Cr, Ni, Mo, V, Nb, Cu, Co, and W, which can be obtained through chemical analysis. The microstructure features include the microstructure type, grain size, precipitate type, composition, and distribution, which can be obtained using microscopic analysis equipment such as metallographic microscopes, scanning electron microscopes, and transmission electron microscopes. The heat treatment process parameters include solution temperature and aging time.

[0035] S120. Obtain the value range of each related factor, and collect the measured mechanical properties of austenitic heat-resistant steel whose related factor values ​​are within the value range.

[0036] The value range is determined based on the initial value range of the related factors and the degree of variation of austenitic heat-resistant steel within the initial value range.

[0037] Optionally, before obtaining the value ranges of each related factor, the method further includes: selecting target related factors from the related factors based on the significance of the influence of each related factor on the mechanical performance parameters.

[0038] Optionally, before obtaining the value ranges of each related factor, to improve experimental efficiency and focus on key variables, a step of screening related factors based on significance analysis can be included. Considering the actual requirements of austenitic heat-resistant steel for mechanical performance parameters in the target application scenario, the significance of the influence of each related factor on the mechanical performance parameters is calculated. The significance of the influence can be quantified using methods such as analysis of variance, regression analysis, or principal component analysis. According to the reliability requirements of the target application scenario, corresponding significance thresholds are dynamically set. For example, for high-reliability scenarios such as steel used in nuclear power plants, a strict threshold (e.g., 0.01) can be used; for conventional scenarios such as general industrial boilers, a medium threshold (e.g., 0.05) can be used; and for exploratory experiments in the research and development stage of new materials, the threshold can be appropriately relaxed (e.g., 0.1). The calculated significance values ​​of each related factor are compared with the corresponding thresholds. Non-critical related factors with significance below the threshold are eliminated, and related factors with significant coupling effects are retained to determine the target related factors. This screening process can eliminate interfering factors in the early stages of experimental design, concentrate resources on studying the core factors that truly affect the comprehensive mechanical properties of materials, and lay the foundation for subsequent gradient division and value range optimization, thereby improving the efficiency and relevance of the overall process.

[0039] Optionally, the process of determining the value range is as follows: the value of any related factor is divided into gradients to determine each initial value range of the related factor; based on a preset variation threshold, the variation degree of austenitic heat-resistant steel in each initial value range of the related factor is verified, and each initial value range of the related factor is optimized according to the variation degree to determine each value range of the related factor.

[0040] The values ​​of any related factor are gradient-divided to determine its initial value intervals. Specifically, a combination of equidistant division and gradient optimization is used, with division rules set for different types of related factors: for compositional characteristics, the initial value intervals are divided according to the elemental mass fraction gradient; for microstructure characteristics, the grain size is divided according to ASTM or national standard grain size standards, and the type, composition, and distribution of precipitated phases are indirectly divided by controlling heat treatment process parameters; for heat treatment process parameters, the solution temperature is divided according to a preset temperature gradient, and the aging time is divided according to a preset time gradient. Based on this, a full factorial experimental design method is used to generate an initial experimental matrix containing all related factors and their complete combinations of initial value intervals; the process feasibility and material safety of each combination in this matrix are verified, and invalid combinations that have process conflicts or exceed the material performance safety range are eliminated, forming a set of multi-parameter coupled experimental combination schemes.

[0041] A predetermined proportion (e.g., 10%-20% of the total number of combinations) of test combinations covering all value ranges of each related factor is selected from the set of multi-parameter coupled test combination schemes as the pre-test sample. The pre-test is performed and the mechanical property dataset is obtained. Based on the mechanical property dataset, the degree of variation of austenitic heat-resistant steel under each initial value range of each related factor is calculated. The degree of variation of austenitic heat-resistant steel under any initial value range of any related factor is determined according to the following formula (1).

[0042] (1)

[0043] in, The degree of variation; For the first The specific measured values ​​of each mechanical performance parameter; The standard deviation of the mechanical property parameters; , where is the mean of the mechanical performance parameters; n is the number of mechanical performance parameters.

[0044] The calculated degree of variation is compared with a preset degree of variation threshold (e.g., 12%). If the degree of variation in a certain initial value interval is higher than the threshold, it is determined that the dispersion of each mechanical performance parameter in that initial value interval of the related factor is too high, and the initial value interval division is unreasonable. It needs to be optimized by adjusting the gradient of the value division of the related factor and modifying the initial value interval. This process is iterated repeatedly until the degree of variation in all initial value intervals of the related factor is lower than the threshold. Finally, the optimized initial value interval is used as the value interval of each related factor, thereby ensuring the quality of subsequent measured data in terms of representativeness, stability, and engineering feasibility.

[0045] The measured mechanical properties of austenitic heat-resistant steel with values ​​of related factors within the range were collected, and the measured mechanical properties were preprocessed, including the use of the 3σ criterion to remove outliers and the conversion of mechanical property parameters of different dimensions into values ​​in the range [0,1] to achieve data normalization.

[0046] S130. Based on the values ​​of each related factor and the measured values ​​of the mechanical properties, construct a predictive model for the mechanical properties of austenitic heat-resistant steel.

[0047] The mechanical performance prediction model can be constructed using support vector machines, backpropagation neural networks, or generalized regression neural networks. The values ​​of each associated factor within different ranges are used as input, and the mechanical performance value is used as the output. The mechanical performance prediction model is updated based on the measured mechanical performance values ​​to ensure that the model's output mechanical performance values ​​are as close as possible to the measured values. During training, the dataset is divided into training and validation sets. Iterative optimization ensures that the root mean square error (RMSE) between the model's predicted and measured mechanical performance values ​​is below a preset error threshold, and the model's coefficient of determination (R²) is not lower than a preset accuracy threshold. For example, the dataset can be divided into training and validation sets in a 7:3 ratio. The model parameters are optimized using the training set to ensure that the RMSE between the model's output mechanical performance values ​​and the measured values ​​is less than 0.05. The model accuracy is then verified using the validation set, requiring the model's coefficient of determination (R²) to be ≥ 0.9.

[0048] S140. Determine the weighting factors of each mechanical performance parameter according to the target application scenario, and weight the predicted mechanical performance values ​​determined based on the mechanical performance prediction model according to the weighting factors to obtain the comprehensive mechanical performance value.

[0049] S150. Cluster the comprehensive mechanical property values ​​to obtain cluster centers. Based on the minimum performance threshold of the target application scenario and the central mechanical property value corresponding to the cluster center, determine at least two comprehensive mechanical property value ranges to classify the mechanical properties of austenitic heat-resistant steel.

[0050] Based on the target application scenario (e.g., power plant boilers, aero-engines), weighting factors are determined for each mechanical performance parameter corresponding to that scenario. These weighting factors reflect the relative importance of different performance parameters within that scenario. For example, for steel used in power plant boilers, high-temperature creep deformation or fatigue strength should be a primary focus, while for steel used in aero-engines, high-temperature creep deformation should be a primary focus. Weighting enhances the impact of key performance parameters on overall performance, avoiding the problem of insufficient emphasis on key performance parameters caused by equal weighting of all mechanical performance parameters in traditional comprehensive performance determination processes. The comprehensive mechanical performance value is obtained by weighting the predicted values ​​of each mechanical performance determined through the mechanical performance prediction model according to the weighting factors, thus characterizing the overall performance level of the material. By setting scenario-based weights, the comprehensive mechanical performance value more accurately reflects the material's suitability for the target application scenario, providing a more targeted reference for material selection and quality assessment, and reducing the risk of material service failure due to a lack of emphasis on specific aspects of the comprehensive mechanical performance value.

[0051] Cluster analysis is performed on the comprehensive mechanical property values ​​calculated from all samples to automatically identify several representative cluster centers. Considering actual engineering needs, a minimum performance threshold required by the target application scenario is introduced as a grading benchmark. Based on this minimum performance threshold and the corresponding mechanical property values ​​of each cluster center, at least two comprehensive mechanical property value intervals are defined. These intervals constitute a quantitative standard for grading the mechanical properties of austenitic heat-resistant steel (e.g., excellent, good, qualified, unqualified), thus providing a direct and objective decision-making basis for material research and development, quality control, and engineering selection. The core mechanical property value is determined based on the comprehensive mechanical property values ​​belonging to the current cluster center.

[0052] Optionally, the method further includes: selecting at least two sets of verification samples from austenitic heat-resistant steels of different production batches, composition systems, and heat treatment processes; obtaining the values ​​of each related factor of the verification samples, and determining the predicted values ​​of each mechanical property parameter of the verification samples based on the values ​​of each related factor and the mechanical property prediction model; determining the predicted performance level of the verification samples based on the predicted values ​​of each mechanical property parameter of the verification samples, the weighting factor, and the comprehensive mechanical property value range; conducting standard mechanical property tests on the verification samples to determine the actual performance level of the verification samples; calculating the agreement rate between the predicted performance level and the actual performance level; and determining that the mechanical property prediction model and the comprehensive mechanical property value range division of each performance level are valid if the agreement rate reaches or exceeds a preset verification threshold.

[0053] One hundred sets of verification samples can be selected from austenitic heat-resistant steels of different production batches, with diverse composition systems and undergoing different heat treatment processes. Optionally, each set of verification samples includes at least two parallel samples; for example, each set of verification samples includes five parallel samples. The specific values ​​of the verification samples for various related factors (such as chemical composition and process parameters) are obtained, and the values ​​of various related factors are input into the constructed mechanical property prediction model to obtain the predicted values ​​of each mechanical property parameter for each verification sample.

[0054] Based on the pre-determined weighting factors of each mechanical performance parameter in the target application scenario, the predicted values ​​of each mechanical performance parameter are weighted and calculated to obtain the comprehensive mechanical performance prediction value of the verification specimen. The comprehensive mechanical performance prediction value is compared with the pre-divided comprehensive mechanical performance value range to determine the corresponding predicted performance level of the verification specimen (e.g., excellent, good, qualified, etc.).

[0055] Standard mechanical property tests (such as high temperature tensile test, room temperature impact test, high temperature creep test, etc.) are conducted on parallel samples in the same batch of verification samples. Based on the test results and with reference to relevant standards or expert experience, the actual performance level of each verification sample is comprehensively determined.

[0056] By comparing the predicted performance levels of all verification samples with their actual performance levels, the proportion of samples that match is calculated, i.e., the agreement rate. A verification threshold (e.g., 90%) is pre-set. If the calculated agreement rate reaches or exceeds this threshold, it indicates that the constructed mechanical property prediction model can accurately reflect the material performance characteristics, and that the weighting factors and the defined comprehensive mechanical property value ranges are reasonable and effective, and can be used to determine the comprehensive mechanical properties and quality classification of materials in actual engineering. Conversely, it suggests that the model parameters or classification criteria need to be retrospectively reviewed and optimized. This verification process ensures accurate prediction of the comprehensive mechanical properties of austenitic heat-resistant steel.

[0057] This invention effectively solves the problems of insufficient specificity and disconnect from actual working conditions caused by the generalization and simplification of traditional performance determination methods by integrating the specific requirements of the target application scenario into the entire process of determining the comprehensive performance and classifying the quality grade of austenitic heat-resistant steel. Based on application scenarios, key mechanical performance parameters and related factors are identified. The scientific value ranges of these factors are then determined through validation and optimization based on the degree of variation, ensuring the targeted and representative nature of data collection. The constructed mechanical performance prediction model accurately reflects the coupling effects between multiple parameters. Combined with scenario-based weighting factors, the predicted values ​​are weighted and fused, enabling the comprehensive mechanical performance values ​​to truly reflect the overall performance level of the material, achieving precise quantification of its comprehensive performance. By combining cluster analysis with scenario-based minimum performance thresholds, performance level ranges that align with actual engineering needs are intelligently defined, reducing subjective experience interference and ensuring that the level classification is anchored to actual scenario requirements. This avoids a disconnect between level standards and applications, guaranteeing the value of level assessments for material scenario applicability and ensuring the accuracy and reliability of level determination rules. Furthermore, by verifying the consistency rate and covering diverse material scenarios, the universality and accuracy of the level classification standards are further guaranteed, providing a clear and credible basis for material performance determination and selection. This provides a reliable, intuitive, and highly scenario-adaptable scientific decision-making basis for the research, selection, quality control, and service safety assessment of austenitic heat-resistant steel.

[0058] Figure 2 This is a second flowchart of a method for treating the mechanical properties of austenitic heat-resistant steel according to an embodiment of the present invention. This embodiment is an optimization and improvement based on the above embodiment. Figure 2 As shown, the method includes:

[0059] S210. Determine the mechanical property parameters and related factors of austenitic heat-resistant steel in the target application scenario.

[0060] S220. Obtain the value range of each related factor, and collect the measured mechanical properties of austenitic heat-resistant steel whose related factor values ​​are within the value range.

[0061] The value range is determined based on the initial value range of the related factors and the degree of variation of austenitic heat-resistant steel within the initial value range.

[0062] S230. Based on the values ​​of each related factor and the measured values ​​of the mechanical properties, construct a predictive model for the mechanical properties of austenitic heat-resistant steel.

[0063] S240: Extract the importance weights of each mechanical performance parameter from open source data.

[0064] Multi-source extraction and consistency verification based on open-source data are performed, including: obtaining the weighted evaluation values ​​of each mechanical performance parameter in the target application scenario from at least two independent public data sources (such as standard literature, academic papers, or engineering databases); aggregating the evaluation values ​​from different data sources to form a preliminary importance weight vector; calculating the consistency ratio of this weight vector and comparing it with a preset consistency judgment threshold. If the consistency ratio does not meet the standard, the data is optimized by removing the data source with the highest dispersion or by weighted smoothing of conflicting data, and then recalculated until the importance weights that pass the verification are obtained. This ensures the reliability of the weight data and provides a stable input for subsequent weight fusion.

[0065] S250. Construct a demand judgment matrix based on the target application scenario and calculate the application demand weights of each mechanical performance parameter.

[0066] By constructing a demand judgment matrix and solving for its eigenvectors, the application demand weights of each mechanical performance parameter are calculated, quantitatively integrating the actual engineering requirements of the target application scenario into the weighting system. Specifically, based on the specific service conditions of the target application scenario (such as operating temperature, stress state, and environmental medium) and engineering design requirements (such as safety factor, life requirements, and failure modes), the pairwise importance of each mechanical performance parameter is compared to construct a demand judgment matrix. The largest eigenvalue and its corresponding eigenvector of this judgment matrix are then solved. This eigenvector represents the relative importance of each mechanical performance parameter in meeting the scenario requirements. The eigenvector is then normalized so that the sum of its components is 1, and the result is the application demand weight of each mechanical performance parameter. This transformation of qualitative engineering experience into quantitative weights ensures that the weight allocation closely aligns with the actual needs of the scenario.

[0067] S260. Based on the measured mechanical property data set, the objective weight of each mechanical property parameter is calculated using the entropy weight method.

[0068] Based on a dataset of measured mechanical properties, the entropy weight method is used to calculate the objective weights of each mechanical property parameter, aiming to uncover the differences in the objective importance of each parameter from the actual data itself. Specifically, the dataset of measured mechanical properties is standardized to eliminate the influence of different dimensions and orders of magnitude of each parameter, resulting in a standardized matrix. For each mechanical property parameter, the proportion of each sample value under that parameter is calculated, and the information entropy of that parameter is calculated based on this proportion. Information entropy reflects the amount of information a parameter contains in the dataset; the smaller the entropy value, the higher the discriminative power of the parameter and the more concentrated the information it provides. The difference coefficient of each parameter is calculated based on the information entropy. The difference coefficient is complementary to the information entropy; the smaller the entropy value, the larger the difference coefficient, indicating a more significant impact of the parameter on the overall mechanical properties. The calculated difference coefficients of each parameter are normalized so that the sum of all coefficients is 1. The normalized result is the objective weight of each mechanical property parameter. Determining the weights based on the statistical characteristics of the data itself effectively avoids the interference of subjective factors, ensuring the objectivity and data-driven nature of the weight allocation.

[0069] S270. The importance weight, application requirement weight, and objective weight are weighted and fused according to a preset ratio of the target application scenario to obtain the weight factor.

[0070] Based on a preset weighting ratio for the target application scenario of austenitic heat-resistant steel, the importance weight, application requirement weight, and objective weight are weighted and fused to obtain a weighting factor. For example, if the target application scenario is a high-reliability scenario, the preset weighting ratio is importance weight: application requirement weight: objective weight = 2:3:5; if the target application scenario is a conventional industrial scenario, the preset weighting ratio is importance weight: application requirement weight: objective weight = 3:3:4.

[0071] S280. The comprehensive mechanical performance value is obtained by weighting each predicted mechanical performance value determined based on the mechanical performance prediction model according to the weighting factor.

[0072] S290. Cluster the comprehensive mechanical property values ​​to obtain cluster centers. Based on the minimum performance threshold of the target application scenario and the central mechanical property value corresponding to the cluster center, determine at least two comprehensive mechanical property value ranges to classify the mechanical properties of austenitic heat-resistant steel.

[0073] Optionally, the step of clustering the comprehensive mechanical performance values ​​to obtain cluster centers, and determining at least two comprehensive mechanical performance value intervals based on the minimum performance threshold of the target application scenario and the central mechanical performance value corresponding to the cluster centers, includes: calculating the clustering inertia error under different preset cluster numbers; selecting the cluster number corresponding to the inflection point of the curve formed by the change of the clustering inertia error with the number of clusters as the target cluster number, and determining the number of performance levels based on the target cluster number; executing a clustering algorithm based on the target cluster number to obtain cluster centers; and determining at least two comprehensive mechanical performance value intervals based on the minimum performance threshold of the target application scenario and the central mechanical performance value corresponding to the cluster centers.

[0074] Calculate the clustering inertia error (intra-cluster sum of squares, used to measure the "compactness" of a clustering model) under different preset cluster numbers. Analyze the curve formed by the change of the inertia error with the number of clusters, and select the cluster number corresponding to the inflection point of the curve as the target cluster number. The target cluster number is the basis for classifying performance levels. Based on the determined target cluster number, execute a clustering algorithm (such as the K-means algorithm) to analyze all comprehensive mechanical performance values, obtain the corresponding cluster centers, and determine the central mechanical performance value of each cluster center. Based on the minimum performance threshold of the target application scenario and the central mechanical performance value corresponding to the cluster center, determine at least two comprehensive mechanical performance value intervals.

[0075] Optionally, the performance levels include: unqualified, qualified, good, and excellent; determining at least two comprehensive mechanical performance value ranges based on the minimum performance threshold of the target application scenario and the central mechanical performance value corresponding to the cluster center includes: using the minimum performance threshold as the upper limit of the comprehensive mechanical performance value range for the unqualified level; using a preset proportion of the maximum value among the central mechanical performance values ​​corresponding to each cluster center as the lower limit of the comprehensive mechanical performance value range for the excellent level; and, based on the sorting and spacing of the central mechanical performance values ​​corresponding to each cluster center, sequentially defining the comprehensive mechanical performance value ranges for the qualified and good levels between the upper limit of the unqualified level and the lower limit of the excellent level.

[0076] When determining the comprehensive mechanical performance value range for each performance level, engineering requirements and data distribution must be considered. Optionally, performance levels can be predefined as unqualified, qualified, good, and excellent. The minimum performance threshold required by the target application scenario is set as the upper limit of the comprehensive mechanical performance value range for the "unqualified" level. The maximum value among the central mechanical performance values ​​corresponding to each cluster center, multiplied by a preset scaling factor (e.g., 80%), is set as the lower limit of the comprehensive mechanical performance value range for the "excellent" level.

[0077] Between the upper limit of the "unacceptable" grade and the lower limit of the "excellent" grade, specific intervals for the "acceptable" and "good" grades are defined based on the ranking and relative position of the mechanical performance values ​​corresponding to each cluster center. One feasible rule is to use the midpoint of the line connecting the two middle cluster centers, or a dividing point determined on that line according to another preset ratio, as the boundary between the acceptable and good grade intervals. Through these steps, an objective and quantitative performance grade classification standard can be established that conforms to the inherent distribution patterns of the data and meets the minimum requirements of engineering.

[0078] This invention addresses key issues in traditional methods for determining the mechanical properties of austenitic heat-resistant steel. It establishes a scenario-driven, data- and knowledge-integrated, and self-verifying comprehensive mechanical property determination and quality assessment system. This system fundamentally solves these problems by addressing issues such as generality bias, strong subjectivity, low efficiency, and disconnect from actual operating conditions inherent in traditional methods. Instead of simply listing and evaluating single performance parameters, it starts with specific application scenarios, reverse-engineering to identify key mechanical property parameter groups affecting service safety and reliability. It also identifies strongly coupled factors such as material composition, microstructure, and processing, ensuring that the mechanical property determination and quality assessment system is closely aligned with engineering requirements. During the data acquisition phase, through scientific definition of the value ranges of related factors and dynamic optimization based on the degree of variation, it systematically collects measured mechanical property data that accurately reflects the parameter coupling effect, laying a high-quality and representative data foundation for subsequent modeling.

[0079] In the model building and weight determination stages, a triple-integrated weight determination mechanism of "open-source knowledge extraction, scenario requirement quantification, and measured data-driven approach" is adopted. This mechanism not only extracts universally applicable importance weights from public standards and literature and verifies their consistency, but also transforms qualitative engineering requirements into quantitative application requirement weights by constructing a judgment matrix. Furthermore, it objectively calculates weights based on the information entropy of the measured dataset itself, and finally performs weighted fusion according to scenario characteristics. This mechanism absorbs domain consensus, incorporates the specific requirements of specific scenarios, and respects the statistical regularities of the data itself, improving the accuracy, relevance, and interpretability of the final comprehensive mechanical performance determination results. The constructed mechanical performance prediction model can accurately capture the evolution law of material properties under multi-factor coupling, achieving accurate prediction of individual properties.

[0080] In the final quality assessment and grading stage, the conventional approach of relying on fixed thresholds or experience-based classification was abandoned. Instead, cluster analysis was performed on the comprehensive mechanical property values ​​to automatically discover the inherent distribution patterns of the data levels. Combined with the mandatory minimum performance thresholds for the target scenario, performance level ranges were intelligently and objectively defined. The resulting grading standards are data-driven and controlled by engineering baselines, ensuring both the scientific rigor of the grading and that all qualified materials meet the minimum service requirements. By introducing a conformity verification step based on multi-source verification samples, the effectiveness and reliability of the model and grading standards were further guaranteed. This provides a data-driven, fully quantifiable, traceable, and verifiable solution for the research, selection, process optimization, and service assessment of austenitic heat-resistant steel, improving the accuracy, efficiency, and engineering applicability of material quality assessment.

[0081] In one optional implementation, the method further includes: determining the mechanical performance parameters and related factors affecting the comprehensive mechanical properties of austenitic heat-resistant steel in the current application scenario; determining the predicted mechanical properties of the austenitic heat-resistant steel under test based on the values ​​of the related factors in the current application scenario and a pre-constructed mechanical performance prediction model; and weighting the predicted mechanical properties of the austenitic heat-resistant steel under test according to weighting factors to obtain the comprehensive mechanical performance prediction value. Based on a preset range of comprehensive mechanical performance values ​​corresponding to each performance level in the current application scenario, determining the performance level to which the comprehensive mechanical performance prediction value belongs. Based on the comprehensive mechanical performance prediction value, the performance level, and each mechanical performance prediction value, calling a pre-stored report template, automatically filling in the result data, and generating a standardized evaluation document containing data tables and level conclusions; wherein the mechanical performance prediction model, weighting factors, and comprehensive mechanical performance value ranges for each performance level are all obtained according to the mechanical performance processing method of austenitic heat-resistant steel described in any of the preceding embodiments, thereby ensuring the systematic nature of the evaluation process and the credibility of the conclusions.

[0082] By generating evaluation documents based on the predicted mechanical properties of austenitic heat-resistant steel, the comprehensive predicted mechanical properties, and the corresponding performance grades, the quality assessment results of the material become intuitive and clear. This allows engineers to quickly grasp the comprehensive performance level of the material, providing scientific decision support for the research and development, improvement, production quality control, and engineering application selection of austenitic heat-resistant steel, thereby enhancing the safety and reliability of material applications.

[0083] Figure 3 This is a schematic diagram of a mechanical property treatment device for austenitic heat-resistant steel provided in an embodiment of the present invention. Figure 3 As shown, the device includes:

[0084] The parameter filtering module 310 is used to determine the mechanical property parameters and related factors of austenitic heat-resistant steel in the target application scenario.

[0085] The measured data acquisition module 320 is used to acquire the value ranges of each related factor and collect the measured mechanical properties of austenitic heat-resistant steel whose values ​​of the related factors are within the value ranges; the value ranges are determined based on the initial value ranges of the related factors and the degree of variation of austenitic heat-resistant steel within the initial value ranges.

[0086] The model training module 330 is used to construct a predictive model of the mechanical properties of austenitic heat-resistant steel based on the values ​​of each related factor and the measured values ​​of mechanical properties.

[0087] The weighting module 340 is used to determine the weighting factors of each mechanical performance parameter according to the target application scenario, and to weight the predicted mechanical performance values ​​determined based on the mechanical performance prediction model according to the weighting factors to obtain the comprehensive mechanical performance value.

[0088] The grading interval module 350 is used to cluster the comprehensive mechanical property values ​​to obtain cluster centers. Based on the minimum performance threshold of the target application scenario and the central mechanical property value corresponding to the cluster center, at least two comprehensive mechanical property value intervals are determined to grade the mechanical properties of austenitic heat-resistant steel.

[0089] The mechanical property treatment device for austenitic heat-resistant steel provided in this embodiment of the invention can execute the mechanical property treatment method for austenitic heat-resistant steel provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0090] Optionally, the process of determining the value range is as follows: the value of any related factor is divided into gradients to determine each initial value range of the related factor; based on a preset variation threshold, the variation degree of austenitic heat-resistant steel in each initial value range of the related factor is verified, and each initial value range of the related factor is optimized according to the variation degree to determine each value range of the related factor.

[0091] Optional weighted modules include:

[0092] The first weighting unit is used to extract the importance weights of each mechanical performance parameter from the open source data;

[0093] The second weighting unit is used to construct a demand judgment matrix based on the target application scenario and calculate the application demand weight of each mechanical performance parameter.

[0094] The third weighting unit is used to calculate the objective weight of each mechanical performance parameter based on the measured mechanical performance data set using the entropy weighting method.

[0095] The weight fusion unit is used to weight and fuse importance weight, application requirement weight and objective weight according to a preset ratio of the target application scenario to obtain weight factors.

[0096] Optionally, the level division interval module includes:

[0097] The performance level quantity determination unit is used to calculate the clustering inertia error under different preset clustering quantities; based on the curve formed by the change of clustering inertia error with the number of clusters, the clustering quantity corresponding to the inflection point of the curve is selected as the target clustering quantity, and the performance level quantity is determined based on the target clustering quantity;

[0098] The cluster center determination unit is used to execute a clustering algorithm to obtain cluster centers based on the target number of clusters;

[0099] The interval determination unit is used to determine at least two comprehensive mechanical performance value intervals based on the minimum performance threshold of the target application scenario and the central mechanical performance value corresponding to the cluster center.

[0100] Optionally, the performance levels include: unqualified, qualified, good, and excellent; the interval determination unit is specifically used to: use the lowest performance threshold as the upper limit of the comprehensive mechanical performance value interval for the unqualified level; use a preset proportion of the maximum value among the central mechanical performance values ​​corresponding to each cluster center as the lower limit of the comprehensive mechanical performance value interval for the excellent level; and, based on the sorting and spacing of the central mechanical performance values ​​corresponding to each cluster center, sequentially define the comprehensive mechanical performance value intervals for the qualified and good levels between the upper limit of the unqualified level and the lower limit of the excellent level.

[0101] Optionally, it also includes: a verification module, used to select at least two sets of verification samples from austenitic heat-resistant steels of different production batches, composition systems, and heat treatment processes; obtain the values ​​of each related factor of the verification sample; determine the predicted values ​​of each mechanical property parameter of the verification sample based on the values ​​of each related factor and the mechanical property prediction model; determine the predicted performance level of the verification sample based on the predicted values ​​of each mechanical property parameter, weighting factors, and comprehensive mechanical property value range; conduct standard mechanical property tests on the verification sample to determine the actual performance level of the verification sample; calculate the consistency rate between the predicted performance level and the actual performance level; if the consistency rate reaches or exceeds a preset verification threshold, then the mechanical property prediction model and the division of the comprehensive mechanical property value range of each performance level are deemed valid.

[0102] The austenitic heat-resistant steel mechanical property treatment device further described can also perform the austenitic heat-resistant steel mechanical property treatment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0103] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0104] Figure 4 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0105] like Figure 4 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory 42 or a random access memory 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 42 or loaded from storage unit 48 into the random access memory 43. The random access memory 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, read-only memory 42, and random access memory 43 are interconnected via a bus 44. An input / output interface 45 is also connected to the bus 44.

[0106] Multiple components in electronic device 40 are connected to input / output interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0107] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as the mechanical property treatment methods for austenitic heat-resistant steel.

[0108] In some embodiments, the mechanical property treatment method for austenitic heat-resistant steel can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 40 via read-only memory 42 and / or communication unit 49. When the computer program is loaded into random access memory 43 and executed by processor 41, one or more steps of the mechanical property treatment method for austenitic heat-resistant steel described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to perform the mechanical property treatment method for austenitic heat-resistant steel by any other suitable means (e.g., by means of firmware).

[0109] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), payload programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube, liquid crystal display, or monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0113] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0114] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual private servers, such as high management difficulty and weak business scalability.

[0115] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0116] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for treating the mechanical properties of austenitic heat-resistant steel, characterized in that, The method includes: Determine the mechanical property parameters and related factors of austenitic heat-resistant steel for the target application scenario; Obtain the value ranges for each related factor, and collect the measured mechanical properties of austenitic heat-resistant steel whose values ​​fall within the value ranges; the value ranges are determined based on the initial value ranges of the related factors and the degree of variation of austenitic heat-resistant steel within the initial value ranges. Based on the values ​​of each related factor and the measured values ​​of the mechanical properties, a predictive model for the mechanical properties of austenitic heat-resistant steel is constructed. The weighting factors of each mechanical performance parameter are determined according to the target application scenario, and the comprehensive mechanical performance value is obtained by weighting the predicted mechanical performance values ​​determined based on the mechanical performance prediction model according to the weighting factors. Clustering is performed on the comprehensive mechanical property values ​​to obtain cluster centers. Based on the minimum performance threshold of the target application scenario and the central mechanical property value corresponding to the cluster center, at least two comprehensive mechanical property value ranges are determined to classify the mechanical properties of austenitic heat-resistant steel.

2. The method according to claim 1, characterized in that, The process for determining the value range is as follows: Gradient partitioning is performed on the values ​​of any related factor to determine the initial value ranges of the related factor; Based on a preset threshold for the degree of variation, the degree of variation of austenitic heat-resistant steel within each initial value interval of the associated factors is verified, and each initial value interval of the associated factors is optimized according to the degree of variation to determine each value interval of the associated factors.

3. The method according to claim 1, characterized in that, The determination of weighting factors for each mechanical performance parameter based on the target application scenario includes: Extract importance weights for each mechanical performance parameter from open-source data; Construct a demand judgment matrix based on the target application scenario, and calculate the application demand weight of each mechanical performance parameter; Based on the measured mechanical property data set, the objective weights of each mechanical property parameter are calculated using the entropy weight method. The importance weight, application requirement weight, and objective weight are weighted and fused according to a preset ratio for the target application scenario to obtain the weight factor.

4. The method according to claim 1, characterized in that, The process involves clustering the comprehensive mechanical performance values ​​to obtain cluster centers. Based on the minimum performance threshold of the target application scenario and the central mechanical performance value corresponding to each cluster center, at least two comprehensive mechanical performance value intervals are determined, including: Calculate the clustering inertia error under different preset cluster numbers; Based on the curve formed by the change of clustering inertia error with the number of clusters, the number of clusters corresponding to the inflection point of the curve is selected as the target number of clusters, and the number of performance levels is determined based on the target number of clusters. Based on the target number of clusters, a clustering algorithm is executed to obtain cluster centers; Based on the minimum performance threshold of the target application scenario and the central mechanical performance value corresponding to the cluster center, at least two comprehensive mechanical performance value ranges are determined.

5. The method according to claim 4, characterized in that, The performance levels include: unqualified, qualified, good, and excellent; the determination of at least two comprehensive mechanical performance value ranges based on the minimum performance threshold of the target application scenario and the central mechanical performance value corresponding to the cluster center includes: The minimum performance threshold is used as the upper limit of the comprehensive mechanical performance value range for the unqualified grade; The preset proportion of the maximum value among the mechanical performance values ​​of each cluster center is used as the lower limit of the comprehensive mechanical performance value range for the excellent level. Based on the ranking and spacing of the mechanical performance values ​​corresponding to each cluster center, the comprehensive mechanical performance value ranges for qualified and good grades are sequentially defined between the upper limit of the unqualified grade and the lower limit of the excellent grade.

6. The method according to claim 1, characterized in that, The method further includes: Select at least two sets of verification samples from austenitic heat-resistant steels of different production batches, composition systems and heat treatment processes; Obtain the values ​​of each related factor of the verification sample, and determine the predicted values ​​of each mechanical property parameter of the verification sample based on the values ​​of each related factor and the mechanical property prediction model; Based on the predicted values ​​of each mechanical property parameter of the verification specimen, the weighting factor and the range of comprehensive mechanical property values ​​determine the predicted performance level of the verification specimen. The verification specimen was subjected to standard mechanical property tests to determine its actual performance level. Calculate the agreement rate between the predicted performance level and the actual performance level; If the matching rate reaches or exceeds the preset verification threshold, the mechanical performance prediction model and the division of the comprehensive mechanical performance value range for each performance level are deemed valid.

7. A device for treating the mechanical properties of austenitic heat-resistant steel, characterized in that, The device includes: The parameter filtering module is used to determine the mechanical property parameters and related factors of austenitic heat-resistant steel in the target application scenario. The measured data acquisition module is used to acquire the value ranges of each related factor and collect the measured mechanical properties of austenitic heat-resistant steel whose values ​​of the related factors are within the value ranges; the value ranges are determined based on the initial value ranges of the related factors and the degree of variation of austenitic heat-resistant steel within the initial value ranges. The model training module is used to construct a predictive model of the mechanical properties of austenitic heat-resistant steel based on the values ​​of each related factor and the measured values ​​of mechanical properties. The weighting module is used to determine the weighting factors of each mechanical performance parameter according to the target application scenario, and to weight the predicted mechanical performance values ​​determined based on the mechanical performance prediction model according to the weighting factors to obtain the comprehensive mechanical performance value. The grading interval module is used to cluster the comprehensive mechanical property values ​​to obtain cluster centers. Based on the minimum performance threshold of the target application scenario and the central mechanical property value corresponding to the cluster center, at least two comprehensive mechanical property value intervals are determined to grade the mechanical properties of austenitic heat-resistant steel.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the mechanical property treatment method for austenitic heat-resistant steel according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the mechanical property treatment method for the austenitic heat-resistant steel according to any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements a method for treating the mechanical properties of austenitic heat-resistant steel according to any one of claims 1-6.

Images