Method for determining components of Mo alloy material, preparation method of Mo alloy material and Mo alloy material

By establishing the composition and performance data set of Mo alloy materials and training and correcting predetermined models, the problem that traditional methods are difficult to determine components to achieve expected performance is solved, and efficient and accurate component determination and performance prediction are achieved, reducing R&D costs.

CN119956184APending Publication Date: 2025-05-09CHINA INSTITUTE OF ATOMIC ENERGY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510135722.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-07
Publication Date
2025-05-09

AI Technical Summary

Technical Problem

Traditional methods of determining the composition of Mo alloy materials are difficult to effectively integrate data information and establish a relationship between components and performance, resulting in the inability to efficiently and accurately determine the components to achieve the expected performance.

Method used

By establishing the composition and performance data set of Mo alloy materials, using the data set to train and correct the predetermined model, the modified model determines the performance based on the components, and by comparing the expected performance to determine the appropriate components.

Benefits of technology

The coverage of the combination of Mo alloy material components on mechanical properties is improved, and the components are efficiently and accurately determined when needed to achieve the expected performance, reducing the cost of developing new materials.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119956184A_ABST
    Figure CN119956184A_ABST
Patent Text Reader

Abstract

The embodiment of the invention relates to the technical field of machine learning, in particular to a method for determining components of a Mo alloy material, a preparation method of the Mo alloy material and the Mo alloy material. In the first aspect, the embodiment of the invention provides a method for determining the components of the Mo alloy material, in the second aspect, the embodiment of the invention provides a preparation method of the Mo alloy material, and in the third aspect, the embodiment of the application provides the Mo alloy material prepared through the method of the embodiment of the second aspect. Through the method provided by the invention, the performance of the Mo alloy material corresponding to each component can be accurately predicted according to the components of the Mo alloy material in the data set, and the coverage degree of the component combination of the existing Mo alloy material on the mechanical performance of the Mo alloy is improved, so that the expected performance is compared with the performance determined by using the predetermined model, and the mechanical performance of the Mo alloy is improved. The components of the Mo alloy material capable of achieving the expected performance are determined, and the cost of research and development of new materials is effectively reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of machine learning technology, and specifically to a method for determining the composition of a Mo alloy material, a method for preparing a Mo alloy material, and a Mo alloy material. Background Art

[0002] The statements herein merely provide background information related to the present application and do not necessarily constitute prior art.

[0003] The composition design of Mo alloy materials needs to be precisely controlled according to the actual desired performance. By adding different alloying elements and controlling their ratio with other alloying elements, Mo alloys with different mechanical properties can be prepared. Summary of the invention

[0004] A brief overview of the present application is provided below in order to provide a basic understanding of certain aspects of the present application. It should be understood that this overview is not an exhaustive overview of the present application. It is not intended to identify the key or important parts of the present application, nor is it intended to limit the scope of the present application. Its purpose is merely to present certain concepts in a simplified form as a prelude to a more detailed description discussed later.

[0005] In a first aspect, an embodiment of the present application provides a method for determining the composition of a Mo alloy material, comprising: S00: determining a data set of the Mo alloy material; S10: processing data on mechanical properties of the Mo alloy material that are missing and data on alloy composition of the Mo alloy material that are missing in the data set; S20: using a predetermined model, according to the composition of the Mo alloy material in the data set after processing in step S10, determining the performance of the Mo alloy material corresponding to the composition of the Mo alloy material; S30: training the predetermined model, and correcting the predetermined model according to the training result to obtain a corrected predetermined model; S40: using the predetermined model revised in step S30, according to the composition of the Mo alloy material in the data set, determining the performance of the Mo alloy material corresponding to the composition of the Mo alloy material; S50: determining the expected performance of the Mo alloy material; S60: determining the composition of the Mo alloy material according to the performance determined in step S40 and the expected performance, so that the Mo alloy material can reach the expected performance.

[0006] In a second aspect, an embodiment of the present application further provides a method for preparing a Mo alloy material, comprising: determining the composition of the Mo alloy material by any method of the first aspect of the embodiment of the present application, and preparing the Mo alloy material according to the composition of the Mo alloy material.

[0007] In a third aspect, an embodiment of the present application further provides a Mo alloy material, and the Mo alloy material is obtained by the preparation method of the second aspect of the embodiment of the present application.

[0008] The method in the embodiments of the present application establishes a data set of the composition of the Mo alloy material and the performance of the Mo alloy material corresponding to the composition, uses the data set to train and correct the predetermined model, and uses the corrected predetermined model to accurately predict the performance of the Mo alloy material corresponding to each component according to the composition of the Mo alloy material in the data set, thereby improving the coverage of the mechanical properties of the Mo alloy by the composition combination of the existing Mo alloy material. Therefore, when it is necessary to process a Mo alloy with expected performance, by comparing the expected performance with the performance determined by using the predetermined model, the composition of the Mo alloy material that can achieve the expected performance is determined, thereby effectively reducing the cost of researching and developing new materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Other objects and advantages of the present application will become apparent from the following description of the embodiments of the present application with reference to the accompanying drawings, and will help to provide a comprehensive understanding of the present application.

[0010] Figure 1 The figure is a flow chart of a method for determining the composition of a Mo alloy material according to one embodiment of the present application.

[0011] It should be noted that the drawings are not necessarily drawn to scale, but are merely shown in a schematic manner that does not affect the reader's understanding. DETAILED DESCRIPTION

[0012] Exemplary embodiments of the present application will be described below in conjunction with the accompanying drawings. For the sake of clarity and conciseness, not all features of the actual implementation are described in the specification. However, it should be understood that many implementation-specific decisions must be made in the process of developing any such actual implementation in order to achieve the developer's specific goals, such as meeting those constraints related to the system and business, and these constraints may vary from implementation to implementation. In addition, it should be understood that although the development work may be very complex and time-consuming, it is only a routine task for those skilled in the art who benefit from the content of this application.

[0013] It is also necessary to explain here that, in order to avoid obscuring the present application due to unnecessary details, only the device structure and / or processing steps closely related to the scheme according to the present application are shown in the accompanying drawings, while other details that are not very relevant to the present application are omitted.

[0014] The inventors of the present application have found that the traditional method of determining the composition of Mo alloy materials is difficult to effectively integrate data information and establish the relationship between the composition of Mo alloy materials and the performance of Mo alloy materials corresponding to the composition, and thus it is impossible to efficiently and accurately determine the composition of Mo alloy materials according to the expected performance to be achieved.

[0015] Based on this, the embodiment of the present application provides a method for determining the composition of the Mo alloy material, such as Figure 1 As shown, Figure 1 A flow chart showing a method for determining the composition of a Mo alloy material according to an embodiment of the present application is shown. The method includes the following steps S00 to S60.

[0016] S00: Determine the data set of Mo alloy materials.

[0017] S10: Processing the data of mechanical properties of Mo alloy materials missing from the data set and the data of alloy composition of Mo alloy materials missing from the data set.

[0018] S20: using a predetermined model, according to the composition of the Mo alloy material in the data set after the processing in step S10, determining the performance of the Mo alloy material corresponding to the composition of the Mo alloy material.

[0019] S30: training a predetermined model, and modifying the predetermined model according to the training result to obtain a modified predetermined model.

[0020] S40: using the predetermined model corrected in step S30, and according to the composition of the Mo alloy material in the data set, determining the performance of the Mo alloy material corresponding to the composition of the Mo alloy material.

[0021] S50: Determine the expected properties of Mo alloy materials.

[0022] S60: According to the performance determined in step S40 and the expected performance, the composition of the Mo alloy material is determined so that the Mo alloy material can achieve the expected performance.

[0023] The method provided in the embodiments of the present application establishes a data set of the composition of the Mo alloy material and the performance of the Mo alloy material corresponding to the composition, and uses the data set to train and correct the predetermined model, so as to use the corrected predetermined model to accurately predict the performance of the Mo alloy material corresponding to each component according to the composition of the Mo alloy material in the data set, thereby improving the coverage of the mechanical properties of the Mo alloy by the composition combination of the existing Mo alloy material. Therefore, when it is necessary to process a Mo alloy with expected performance, by comparing the expected performance with the performance determined by using the predetermined model, the composition of the Mo alloy material that can achieve the expected performance can be efficiently and accurately determined, thereby effectively reducing the cost of researching and developing new materials.

[0024] In some embodiments, step S00 may further include:

[0025] S01: Determine the composition of the Mo alloy material.

[0026] S02: Determine the processing method of Mo alloy material.

[0027] S03: Processing the components determined in step S01 according to the processing method determined in step S02 to obtain a Mo alloy.

[0028] S04: Determine the mechanical properties of the Mo alloy obtained in step S03.

[0029] In this embodiment, the compositions of multiple Mo alloy materials and multiple processing methods are determined, and the compositions of the multiple Mo alloy materials are processed using the multiple processing methods to obtain multiple Mo alloys, so as to determine the mechanical properties of the multiple Mo alloys, thereby establishing the composition of the Mo alloy materials and the performance data set of the Mo alloys corresponding to the compositions.

[0030] Specifically, in step S04, when determining the mechanical properties of the plurality of Mo alloys determined in step S03, it is ensured that the properties cover multiple aspects such as hardness, toughness, strength and fatigue strength of the Mo alloy, so as to enhance the integrity of the data set.

[0031] In some embodiments, the data set is composed of the composition of the Mo alloy material, the test conditions for conducting the test to obtain the mechanical properties, and the mechanical properties corresponding to the alloy composition. Step S10 may also include the following steps:

[0032] S11: Delete the missing mechanical properties data of Mo alloy materials in the dataset.

[0033] S12: For the missing alloy component data in the Mo alloy material in the data set, use 0 value to fill.

[0034] S13: For data values ​​of alloy components in the Mo alloy material in the data set that are within a predetermined range, a maximum value in the predetermined range is taken as the value of the alloy component.

[0035] In this embodiment, the data in the data set is processed to ensure the data volume in the data set, avoid data shortage, and simplify the data information in the data set, thereby ensuring the training effect and correction accuracy of the predetermined model.

[0036] In some embodiments, in step S20, the predetermined model may be a commonly used model in the field of artificial intelligence, and technicians in the relevant technical field may select it according to actual conditions and needs.

[0037] In some embodiments, step S20 may also include the following steps: inputting all features of the alloy components into a predetermined model, determining the evaluation index of the predetermined model, wherein all features include N sub-components; inputting N-1 sub-components into the predetermined model, determining the evaluation index of the model, wherein the evaluation index represents the influence of the sub-components not input into the predetermined model on the predetermined model; determining the influence of all sub-components on the predetermined model; deleting the sub-components that cause the evaluation index to rise; and using the remaining sub-components determined as the input set of the predetermined model. Thus, the data of the input set of the predetermined model is screened, the representativeness of the input set data is improved, the sub-components that cause the evaluation index to rise are excluded, and the deviation caused by abnormal values ​​is reduced.

[0038] In some embodiments, step S20 may also include: dividing the data set into a test set and a training set, determining a model whose performance in the test set and the training set meets the expected requirements as a predetermined model, and using the data set to screen the predetermined model to improve the degree of adaptation of the model to the data features in the data set, thereby improving the model accuracy.

[0039] In some embodiments, the composition of the Mo alloy material may include a single-element material composition, a two-element material composition, and a three-element material composition. According to the number of elements in the material composition, the input set of the predetermined model is determined to facilitate establishing the relationship between each element in the Mo alloy material composition with different element quantities and the performance of the Mo alloy material, and determining the influence of each element on the performance, thereby further processing the data of the input set of the predetermined model to ensure the training effect and correction accuracy of the predetermined model.

[0040] In some embodiments, when determining that an element in a material composition is a single element, a predetermined number of values ​​within a predetermined interval between the maximum value and the minimum value are determined as an input set for a predetermined model based on the maximum value and the minimum value of the value range of the element content.

[0041] For example, when it is determined that the element in the material composition is element C, according to the value range of the element C content, 500 equally spaced data values ​​are generated at a predetermined interval between the maximum value and the minimum value as an input set of the predetermined model.

[0042] In some embodiments, when it is determined that the elements in the material composition are two elements, the predetermined number of values ​​of each element within a predetermined interval between the maximum value and the minimum value are determined based on the maximum value and the minimum value of the value range of the content of each element; the predetermined number of values ​​of one element are multiplied by the predetermined number of values ​​of another element as the input set of the predetermined model.

[0043] For example, when it is determined that the elements in the material composition are the Ti-Zr element pair, according to the value range of the element content of the Ti element and the Zr element, 100 equally spaced data values ​​are generated between the maximum value and the minimum value of the value range at a predetermined interval to form two data sets, and the 10,000 data values ​​generated by multiplying the two data sets are used as the input set of the predetermined model.

[0044] In some embodiments, when it is determined that the elements in the material composition are three elements, the predetermined number of values ​​of each element within a predetermined interval between the maximum value and the minimum value are determined based on the maximum value and the minimum value of the value range of the content of each element; the predetermined number of values ​​of the three elements are multiplied together as the input set of the predetermined model.

[0045] For example, when determining that the elements in the material composition are a CON element combination, according to the value ranges of the element contents of the C element, the O element, and the N element, 50 equally spaced data values ​​are generated at predetermined intervals between the maximum value and the minimum value of the value range to form three data sets. The 125,000 data values ​​generated by multiplying the three data sets are used as the input set of the predetermined model.

[0046] The second aspect of the embodiments of the present application also provides a method for preparing a Mo alloy material, which comprises: determining the composition of the Mo alloy material by the method provided in any embodiment of the first aspect of the embodiments of the present application, and preparing the Mo alloy material according to the composition of the Mo alloy material.

[0047] An embodiment of the present application further provides a Mo alloy material, which is obtained by the method provided in the second aspect of the present application.

[0048] The process of determining the composition of the Mo alloy material in the present application is further explained below with specific examples.

[0049] The composition and processing method of the Mo alloy material are determined, the composition of the determined Mo alloy material is processed by the determined processing method to obtain the Mo alloy, the mechanical properties of the obtained Mo alloy are determined, and a data set including the composition of the Mo alloy material, the test conditions for obtaining the mechanical properties, and the mechanical properties corresponding to the alloy composition is obtained. The data of missing mechanical properties in the Mo alloy material in the data set is deleted, and the data of missing alloy composition in the Mo alloy material in the data set is filled with a value of 0, and for the data value of the alloy composition in the Mo alloy material in the data set within a predetermined range, the maximum value of the predetermined range is used as the value of the alloy composition. The data set is divided into a test set and a training set, and the model that meets the expected requirements in the test set and the training set is determined as the predetermined model; all the characteristics of the components of the Mo alloy material are input into the predetermined model, and the evaluation index of the predetermined model is determined, and all the characteristics include N sub-components; N-1 sub-components are input into the predetermined model, and the evaluation index of the model is determined, and the evaluation index represents the influence of the sub-components that are not input into the predetermined model on the predetermined model; the influence of all sub-components on the predetermined model is determined, and the sub-components that cause the evaluation index to increase are deleted, and the remaining sub-components determined are used as the input set of the predetermined model; and when the element in the material component is a single element, according to the maximum and minimum values ​​of the value range of the element content, Determine a predetermined number of values ​​in a predetermined interval between the maximum value and the minimum value as an input set of the predetermined model; when there are two elements in the material composition, determine the predetermined number of values ​​in the predetermined interval between the maximum value and the minimum value of each element according to the maximum value and the minimum value of the value range of the content of each element, and multiply the predetermined number of values ​​of one element by the predetermined number of values ​​of another element as the input set of the predetermined model; when there are three elements in the material composition, determine the predetermined number of values ​​in the predetermined interval between the maximum value and the minimum value of each element according to the maximum value and the minimum value of the value range of the content of each element, and multiply the predetermined number of values ​​of the three elements as the input set of the predetermined model. Using the predetermined model, determine the performance of the Mo alloy material corresponding to the composition of the Mo alloy material according to the input set. Train the predetermined model, and modify the predetermined model according to the training result to obtain the modified predetermined model. Using the modified predetermined model, determine the performance of the Mo alloy material corresponding to the composition of the Mo alloy material according to the composition of the Mo alloy material in the data set. Determine the expected performance of the Mo alloy material. Based on the properties determined using the modified predetermined model and the expected properties, the composition of the Mo alloy material is determined so that the Mo alloy material can achieve the expected properties.

[0050] Regarding the embodiments of the present application, it should also be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other to obtain new embodiments.

[0051] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for determining the composition of a Mo alloy material, characterized in that: It includes: S00: determining a data set of the Mo alloy material; S10: processing the data of mechanical properties of the Mo alloy material missing and the data of alloy composition of the Mo alloy material missing in the data set; S20: using a predetermined model, according to the composition of the Mo alloy material in the data set after processing in step S10, determining the performance of the Mo alloy material corresponding to the composition of the Mo alloy material; S30: training the predetermined model, and modifying the predetermined model according to the training result to obtain a modified predetermined model; S40: using the predetermined model revised in step S30, and determining the performance of the Mo alloy material corresponding to the composition of the Mo alloy material according to the composition of the Mo alloy material in the data set; S50: Determine the expected performance of Mo alloy materials; S60: Determine the composition of the Mo alloy material according to the performance determined in step S40 and the expected performance, so that the Mo alloy material can achieve the expected performance.

2. The method according to claim 1, characterized in that In step S00, it also includes: S01: Determine the composition of Mo alloy material; S02: Determine the processing method of Mo alloy material; S03: Processing the components determined in step S01 according to the processing method determined in step S02 to obtain a Mo alloy; S04: Determine the mechanical properties of the Mo alloy obtained in step S03.

3. The method according to claim 1, characterized in that The data set is composed of the composition of the Mo alloy material, the test conditions for conducting the test to obtain the mechanical properties, and the mechanical properties corresponding to the alloy composition; The step S10 includes: S11: deleting the data of missing mechanical properties of the Mo alloy material in the data set; S12: Filling the missing alloy component data in the Mo alloy material in the data set with a value of 0; S13: When the data value of the alloy component in the Mo alloy material in the data set is within a predetermined range, a maximum value of the predetermined range is used as the value of the alloy component.

4. The method according to claim 3, characterized in that The step S20 also includes the steps of: Inputting all characteristics of the alloy composition into the predetermined model to determine evaluation indicators of the predetermined model, wherein the all characteristics include N sub-components; Inputting N-1 subcomponents into the predetermined model, and determining an evaluation index of the model, wherein the evaluation index represents the influence of the subcomponents that are not input into the predetermined model on the predetermined model; determining the impact of all subcomponents on the predetermined model; Delete the subcomponents that cause the evaluation index to increase; The determined remaining subcomponents serve as an input set for the predetermined model.

5. The method according to claim 1, characterized in that In step S20, the following steps are also included: Divide the data set into a test set and a training set, A model whose performance in the test set and the training set meets the expected requirements is determined as the predetermined model.

6. The method according to claim 1, characterized in that The composition of the Mo alloy material includes a single-element material composition, a two-element material composition, and a three-element material composition. The input set of the predetermined model is determined according to the number of elements in the material composition.

7. The method according to claim 6, characterized in that Determine that the element in the material composition is a single element, According to the maximum value and the minimum value of the value range of the content of the element, a predetermined number of values ​​with a predetermined interval between the maximum value and the minimum value are determined as an input set of the predetermined model.

8. The method according to claim 6, characterized in that Determine that the elements in the material composition are two elements, Determine, according to the maximum value and the minimum value of the value range of the content of each element, the value of each element within a predetermined interval and a predetermined number of values ​​between the maximum value and the minimum value; A predetermined number of values ​​of one of the elements are multiplied by a predetermined number of values ​​of another of the elements as an input set of the predetermined model.

9. The method according to claim 6, characterized in that Determine that the elements in the material composition are three elements, Determine, according to the maximum value and the minimum value of the value range of the content of each element, the value of each element within a predetermined interval and a predetermined number of values ​​between the maximum value and the minimum value; A predetermined number of values ​​of the three elements are multiplied together respectively as an input set of the predetermined model.

10. A method for preparing a Mo alloy material, characterized in that: include: Determine the composition of the Mo alloy material by the method according to any one of claims 1 to 9; The Mo alloy material is prepared according to the composition of the Mo alloy material.

11. A Mo alloy material, characterized in that: The Mo alloy material is obtained by the preparation method according to claim 10.