Method and device for detecting hydrogen embrittlement resistance of high-entropy alloy based on machine learning driving

Abstract

The invention relates to the technical field of high-entropy alloy hydrogen embrittlement resistance detection, and discloses a high-entropy alloy hydrogen embrittlement resistance detection method and device based on machine learning driving, and the method comprises the steps of calculation of elongation at break, setting of an elongation at break threshold and comparison of the elongation at break and the threshold. According to the method, the brittleness resistance of the high-entropy alloy in the hydrogen environment is evaluated through the unified standard elongation at break, and the detection reliability and comparability can be ensured regardless of the sample size. Compared with the direct comparison of the fracture length, the fracture elongation is not influenced by the sample size, so that the samples with different sizes can be evaluated under the unified standard, and the error caused by the size difference of the samples is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of detecting the hydrogen embrittlement resistance performance of high-entropy alloys, and specifically to a method and device for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning. Background Technique

[0002] Different from traditional alloys, the components of high-entropy alloys are composed of multiple metal elements, and the proportions of these elements are relatively close to avoid a single element from overly dominating. Due to the synergistic effect of multiple elements, high-entropy alloys usually have a high melting point and excellent high-temperature stability. This enables them to have a wider application potential in extreme high-temperature environments, such as the aerospace and nuclear energy fields, etc.

[0003] Hydrogen embrittlement refers to the situation where after hydrogen enters a metal material, it changes its microstructure or causes crack propagation, thereby seriously affecting its mechanical properties, especially under stress conditions such as tension, fatigue, and impact. Detecting the hydrogen embrittlement resistance performance of high-entropy alloys is an important task for evaluating the hydrogen embrittlement resistance performance of high-entropy alloy materials. Therefore, a method and device for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning are proposed here. Summary of the Invention

[0004] Aiming at the problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a method and device for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning, so as to be able to detect the hydrogen embrittlement resistance performance of high-entropy alloys.

[0005] To achieve the above purpose, the present invention provides the following technical solutions: A method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning, including: Step 1, select a high-entropy alloy sample, record its initial length, denoted as the standard length. After recording, place it in a hydrogen environment. After a period of time, take out the high-entropy alloy sample and perform tensile testing on it. The tensile rate is generated by a machine learning model combined with historical data to obtain a suitable rate for tensile testing until fracture. After fracture, record its fracture length. Use the fracture length minus the standard length and then divide by the standard length to obtain the fracture elongation rate of the high-entropy alloy sample; Step 2, set the fracture elongation rate threshold of the high-entropy alloy. The fracture elongation rate threshold is the standard elongation rate of the high-entropy alloy after fracture in the absence of a hydrogen environment; Step 3, compare the fracture elongation rate of the high-entropy alloy sample with the fracture elongation rate threshold. If the fracture elongation rate of the high-entropy alloy sample is less than the fracture elongation rate threshold, it means that the fracture elongation rate of the high-entropy alloy sample has decreased and hydrogen embrittlement has occurred. In this case, the hydrogen embrittlement detection of the high-entropy alloy sample is unqualified; if the fracture elongation rate of the high-entropy alloy sample is greater than or equal to the fracture elongation rate threshold, it means that the fracture elongation rate of the high-entropy alloy sample has not been affected by hydrogen. In this case, the hydrogen embrittlement detection of the high-entropy alloy sample is qualified.

[0006] In some embodiments, when the fracture elongation rate of the high-entropy alloy sample is greater than or equal to the fracture elongation rate threshold, a second fracture elongation rate threshold greater than the fracture elongation rate threshold is set, and the fracture elongation rate of the high-entropy alloy sample is compared with the second fracture elongation rate threshold, and different responses are obtained according to the comparison result.

[0007] In some embodiments, if the fracture elongation rate of the high-entropy alloy sample is greater than the second fracture elongation rate threshold, it indicates that the fracture elongation rate of the high-entropy alloy sample is far from the fracture elongation rate threshold, and the high-entropy alloy sample is not affected by hydrogen. In this case, the high-entropy alloy sample passes the test; if the fracture elongation rate of the high-entropy alloy sample is less than or equal to the second fracture elongation rate threshold, it indicates that the fracture elongation rate of the high-entropy alloy sample is close to the fracture elongation rate threshold, and the high-entropy alloy sample may be affected by hydrogen and not detected. In this case, a secondary test is performed.

[0008] In some embodiments, during the secondary test, one of the fracture parts of the high-entropy alloy sample is selected, the number of dimples at the fracture surface of the fracture part is obtained. At the same time, the area of the fracture surface of the fracture part is measured, the dimple density is obtained by dividing the number of dimples by the fracture surface area, and a dimple density threshold in the absence of hydrogen environment influence is set, and the dimple density is compared with the dimple density threshold, and different responses are obtained according to the comparison result.

[0009] In some embodiments, if the dimple density is less than the dimple density threshold, it represents that the dimple density at the fracture surface of the fracture part is low, showing brittle fracture, so hydrogen embrittlement has occurred due to the influence of hydrogen. In this case, the high-entropy alloy sample fails the test; if the dimple density is greater than or equal to the dimple density threshold, it represents that the dimple density at the fracture surface of the fracture part is high, showing ductile fracture, so it is not affected by hydrogen. In this case, the high-entropy alloy sample passes the test.

[0010] In some embodiments, when the dimple density is greater than or equal to the dimple density threshold, the fracture surface of the fracture part is evenly divided into upper and lower regions, the number of dimples in the upper region and the lower region are respectively obtained, the difference in the number of dimples is obtained by subtracting the region with fewer dimples from the region with more dimples, and the difference in the number of dimples is used for re-judgment.

[0011] In some embodiments, when re-judging, a dimple number difference threshold is set, the dimple number difference is compared with the dimple number difference threshold, and different responses are obtained according to the comparison result.

[0012] In some embodiments, if the difference in the number of dimples is less than or equal to the dimple number difference threshold, it indicates that the number of dimples in the upper region is basically the same as that in the lower region. In this case, partial hydrogen embrittlement has not occurred, and the high-entropy alloy sample passes the detection; if the difference in the number of dimples is greater than the dimple number threshold, it indicates that there is a difference in the number of dimples between the upper region and the lower region. In this case, partial hydrogen embrittlement has occurred in the region with fewer dimples in the upper region and the lower region, and the high-entropy alloy sample fails the detection.

[0013] The present invention further provides the following technical solutions:

[0014] The present invention further provides a device for detecting the hydrogen embrittlement resistance of high-entropy alloys driven by machine learning, which is used to execute the method described above, including: an acquisition module, which is used to select a high-entropy alloy sample, record its initial length, denoted as the standard length. After recording, place it in a hydrogen environment. After a period of time, take out the high-entropy alloy sample and perform tensile testing on it until it breaks. After breaking, record its fracture length. Use the fracture length minus the standard length and then divide by the standard length to obtain the fracture elongation rate of the high-entropy alloy sample; a setting module, which is used to set the fracture elongation rate threshold of the high-entropy alloy. The fracture elongation rate threshold is the standard elongation rate of the high-entropy alloy after fracture in the absence of a hydrogen environment; a comparison module, which is used to compare the fracture elongation rate of the high-entropy alloy sample with the fracture elongation rate threshold. If the fracture elongation rate of the high-entropy alloy sample is less than the fracture elongation rate threshold, it represents that the fracture elongation rate of the high-entropy alloy sample has decreased and hydrogen embrittlement has occurred. In this case, the high-entropy alloy sample fails the hydrogen embrittlement resistance detection; if the fracture elongation rate of the high-entropy alloy sample is greater than or equal to the fracture elongation rate threshold, it represents that the fracture elongation rate of the high-entropy alloy sample has not been affected by hydrogen. In this case, the high-entropy alloy sample passes the hydrogen embrittlement resistance detection.

[0015] The present invention further provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the above-mentioned method for detecting the hydrogen embrittlement resistance of high-entropy alloys driven by machine learning.

[0016] The technical solutions provided by the present invention have the following beneficial effects compared with the prior art:

[0017] First, in the present invention, the fracture elongation rate with a unified standard is used to evaluate the hydrogen embrittlement resistance of high-entropy alloys in a hydrogen environment. Regardless of the sample size, the reliability and comparability of the detection can be ensured. Compared with the direct comparison of the fracture length, the fracture elongation rate is not affected by the sample size, enabling samples of different sizes to be evaluated under a unified standard, thus avoiding errors caused by sample size differences.

[0018] Second, in the present invention, by comparing the dimple density with the dimple density threshold in a hydrogen-free environment, it is possible to effectively determine whether the material is affected by hydrogen embrittlement. This method combines the fracture elongation rate and the dimple density, which can improve the accuracy of detection, avoid errors that may be caused by relying solely on a single index, and ensure that the hydrogen embrittlement resistance of the high-entropy alloy can be reliably evaluated.

[0019] Third, in the present invention, when the dimple density is greater than or equal to the dimple density threshold, the dimple distribution of the fractured part is further subdivided to improve the detection accuracy. Through the local distribution analysis of the dimple quantity, the problem that local hydrogen embrittlement may be missed by the overall dimple density is compensated, making the hydrogen embrittlement resistance detection more rigorous and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic flow chart of the steps of the present invention;

[0021] Figure 2 is a schematic diagram of the module structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0023] It can be understood that the term "one" should be understood as "at least one" or "one or more". That is, in one embodiment, the number of one element can be one, and in other embodiments, the number of this element can be multiple. The term "one" cannot be understood as a limitation on the quantity.

[0024] The method for detecting the hydrogen embrittlement resistance of high-entropy alloys driven by machine learning provided by the present invention, as Figure 1 and Figure 2 shown, includes:

[0025] First step, select a suitable high-entropy alloy sample and ensure that its size meets the detection requirements. The initial length of the high-entropy alloy sample needs to be accurately recorded. Select a tensile specimen shape that meets the standards, such as cylindrical, rectangular, or a standard tensile specimen. The recorded initial length serves as the standard length, which is the basis for calculating the fracture elongation rate in the subsequent steps. Next, place the high-entropy alloy sample in a hydrogen environment for exposure. The parameters of the hydrogen environment are set according to the detection design and the requirements of the target material. The exposure time in the hydrogen environment is controlled between several hours and several days to ensure that hydrogen can fully penetrate into the material and interact with the elements in the high-entropy alloy. After the hydrogen exposure is completed, remove the high-entropy alloy sample from the hydrogen environment and immediately place it in a tensile testing machine for a tensile test. The tensile testing machine operates according to the standard tensile test procedure, continuously applying a uniaxial tensile force during the tensile process until the sample fractures. It should be noted that the tensile speed has a certain impact on the test results, and a standardized tensile rate, such as 1 - 5 mm / min, needs to be selected. The specific tensile rate is obtained through a comprehensive machine learning model based on historical records, such as a linear regression model. Measure and record the fracture length of the high-entropy alloy sample after fracture. Divide the difference between the fracture length and the standard length by the standard length to obtain the fracture elongation rate of the high-entropy alloy sample.

[0026] Second step, set the fracture elongation rate threshold for this high-entropy alloy according to the parameter information of the high-entropy alloy sample. This fracture elongation rate threshold is the standard elongation rate of this high-entropy alloy after fracture in the absence of a hydrogen environment. Here, it verifies why the fracture elongation rate is selected instead of the fracture length. The reason for choosing the fracture elongation rate is that as long as the composition of the high-entropy alloy is the same, its fracture elongation rate is the same and will not vary due to different sizes. If the fracture length is used for judgment, for high-entropy alloy samples of different sizes, the fracture length threshold cannot be determined according to the standard. Only by selecting multiple high-entropy alloy samples of the same size and conducting a large number of tests in the absence of a hydrogen environment can the fracture length threshold be obtained. This method will make the detection more complex. Therefore, considering all aspects, the fracture elongation rate is selected for judgment.

[0027] In the third step, compare the elongation at fracture of the high-entropy alloy sample with the elongation at fracture threshold, and draw different responses based on the comparison results. If the elongation at fracture of the high-entropy alloy sample is less than the elongation at fracture threshold, it means that the elongation at fracture of the high-entropy alloy sample has decreased, indicating that hydrogen embrittlement has occurred and reduced the elongation at fracture of the high-entropy alloy sample. In this case, the hydrogen embrittlement resistance test of the high-entropy alloy sample fails. If the elongation at fracture of the high-entropy alloy sample is greater than or equal to the elongation at fracture threshold, it means that the elongation at fracture of the high-entropy alloy sample has not been affected by hydrogen. In this case, the hydrogen embrittlement resistance test of the high-entropy alloy sample passes. This is because the diffusion and aggregation of hydrogen atoms damage the plastic deformation ability of the material. Hydrogen atoms are extremely small and can quickly diffuse into the lattice, dislocations, grain boundaries, and interfaces of the second-phase particles of the high-entropy alloy, resulting in hydrogen-enhanced local plasticity effects or hydrogen-induced cracking mechanisms under stress. In the hydrogen-enhanced local plasticity mechanism, hydrogen reduces the interaction between dislocations, making it easier for dislocations to slip, resulting in enhanced local plasticity, but this local deformation is uneven and can trigger microcracks; while in the hydrogen-induced cracking mechanism, hydrogen accumulates at grain boundaries and defects, weakening the atomic bonding force and promoting brittle cracking. In addition, hydrogen may also cause hydrogen-induced phase transformation, promoting the transformation of some stable phases in the high-entropy alloy into more brittle phases. Under the combined action, the plastic deformation ability of the high-entropy alloy drops significantly, making it more likely to fracture prematurely during the tensile process, resulting in a significant reduction in the elongation at fracture and showing brittle fracture characteristics. The greatest advantage of this method for testing the hydrogen embrittlement resistance of high-entropy alloys is that it evaluates the brittleness resistance of high-entropy alloys in a hydrogen environment through a unified standard elongation at fracture. Regardless of the sample size, it can ensure the reliability and comparability of the test. Compared with the direct comparison of the fracture length, the elongation at fracture is not affected by the sample size, enabling samples of different sizes to be evaluated under a unified standard, thus avoiding errors caused by sample size differences. In addition, this method is simple and easy to implement, can quickly quantify the impact of hydrogen on the properties of high-entropy alloys, and provides an intuitive evaluation basis for the improvement of high-entropy alloy materials. By comparing with the elongation at fracture threshold, it is possible to clearly determine whether hydrogen embrittlement has occurred in the high-entropy alloy, and it is easy to implement and repeat, making it suitable for large-scale screening and quality control of the hydrogen embrittlement resistance of high-entropy alloys.

[0028] Set a second threshold for the fracture elongation rate, which is slightly greater than the threshold for the fracture elongation rate. For example, the threshold for the fracture elongation rate is 10%, and the second threshold for the fracture elongation rate is 12%. Under this condition, when the fracture elongation rate of the high-entropy alloy sample is greater than or equal to the threshold for the fracture elongation rate, compare the fracture elongation rate of the high-entropy alloy sample with the second threshold for the fracture elongation rate, and different responses can be obtained according to the comparison results. If the fracture elongation rate of the high-entropy alloy sample is greater than the second threshold for the fracture elongation rate, it indicates that the fracture elongation rate of the high-entropy alloy sample is significantly higher than the threshold for the fracture elongation rate, and the high-entropy alloy sample is not affected by hydrogen. In this case, the high-entropy alloy sample passes the test. If the fracture elongation rate of the high-entropy alloy sample is less than or equal to the second threshold for the fracture elongation rate, it indicates that the fracture elongation rate of the high-entropy alloy sample is close to the threshold for the fracture elongation rate, and the high-entropy alloy sample may be affected by hydrogen and not detected. In this case, a secondary test is performed. During the secondary test, when the high-entropy alloy sample is fractured into two parts, select one of the fractured parts, and obtain the number of dimples at the fracture surface of the fractured part through a sensor. At the same time, measure the area of the fracture surface of the fractured part. Divide the number of dimples by the fracture surface area to obtain the dimple density. Set the dimple density threshold under the influence of a hydrogen-free environment according to the parameter information of the high-entropy alloy sample, compare the dimple density with the dimple density threshold, and different responses can be obtained according to the comparison results. If the dimple density is less than the dimple density threshold, it means that the dimple density at the fracture surface of the fractured part is low, showing brittle fracture, so hydrogen embrittlement has occurred under the influence of hydrogen. In this case, the high-entropy alloy sample fails the test. If the dimple density is greater than or equal to the dimple density threshold, it means that the dimple density at the fracture surface of the fractured part is high, showing ductile fracture, so it is not affected by hydrogen. In this case, the high-entropy alloy sample passes the test. Because in the above process, when the fracture elongation rate of the high-entropy alloy sample is greater than or equal to the threshold for the fracture elongation rate, it is considered that the fracture elongation rate of the high-entropy alloy sample is not affected by hydrogen. However, if the fracture elongation rate of the high-entropy alloy sample is very close to the threshold for the fracture elongation rate, it is necessary to consider whether the influence of hydrogen is not detected. Because there is a certain time interval between taking the high-entropy alloy sample out of the hydrogen environment and performing the tensile test. During this period, the high-entropy alloy sample that may be affected by hydrogen has a certain degree of recovery. In addition, for the case close to the threshold for the fracture elongation rate, it is already on the verge of hydrogen embrittlement. Therefore, to ensure the quality of the high-entropy alloy sample, a secondary test is carried out here. The secondary test mainly judges whether it is affected by hydrogen according to the density of the dimples. When the high-entropy alloy undergoes plastic fracture, it usually shows a fracture surface with a high dimple density, while in brittle fracture, the number of dimples is small or even absent. When hydrogen penetrates into the high-entropy alloy, hydrogen atoms will accumulate at grain boundaries, dislocations and defects, weakening the interatomic bonding force, resulting in effects such as hydrogen-induced cracking or hydrogen-enhanced local plasticity, reducing the plastic deformation ability of the material, and showing a decrease in dimple density.Therefore, after the tensile test, if the dimple density of the high-entropy alloy sample is low, it indicates that its fracture mode tends to brittle fracture, suggesting that hydrogen has affected the ductility of the material and hydrogen embrittlement has occurred; conversely, if the dimple density is high, it means that the material still mainly undergoes plastic fracture and is not significantly affected by hydrogen. Through the quantitative analysis of the dimple density, the possible errors solely relying on the fracture elongation can be effectively compensated, improving the accuracy of the hydrogen embrittlement resistance performance detection. Generally speaking, this detection method determines whether the high-entropy alloy sample is affected by hydrogen by setting a fracture elongation threshold and a second threshold. First, when the fracture elongation is greater than or equal to the fracture elongation threshold, it is compared with the second fracture elongation threshold. If the fracture elongation is higher than the second fracture elongation threshold, it indicates that the sample is not affected by hydrogen and the detection is qualified; if the fracture elongation is less than or equal to the second fracture elongation threshold, it may not detect the influence of hydrogen and a secondary detection is required. The secondary detection confirms whether hydrogen embrittlement has occurred by analyzing the dimple density of the fractured part. When the high-entropy alloy undergoes plastic fracture, the fracture surface will exhibit a relatively high dimple density, while for brittle fracture, the dimple density is low. The infiltration of hydrogen usually reduces the formation of dimples, resulting in a brittle fracture appearance. By comparing the dimple density with the dimple density threshold in a hydrogen-free environment, it can effectively determine whether the material is affected by hydrogen embrittlement. This method combines the fracture elongation and the dimple density, which can improve the detection accuracy, avoid the errors that may be brought by relying on a single index alone, and ensure the reliable evaluation of the hydrogen embrittlement resistance performance of the high-entropy alloy.

[0029] When the dimple density is greater than or equal to the dimple density threshold, the fracture part of the fracture surface is evenly divided into upper and lower regions. The dimple numbers of the upper region and the lower region are obtained respectively. The dimple number difference is obtained by subtracting the region with fewer dimples from the region with more dimples. Assuming that the upper region has more dimples, the dimple number difference is obtained by subtracting the dimple number of the lower region from the dimple number of the upper region. According to the high-entropy alloy parameter information and the total area of the fracture surface, a dimple number difference threshold is set. The dimple number difference threshold represents the magnitude of the dimple number difference between the upper region and the lower region. If it is less than or equal to the dimple number difference threshold, it means that the dimple number difference between the two regions is basically the same. If it is greater than the dimple number difference threshold, it means that there is a difference in the dimple number difference between the two regions. Under this condition, the dimple number difference is compared with the dimple number difference threshold, and different responses are obtained according to the comparison results. If the dimple number difference is less than or equal to the dimple number difference threshold, it indicates that the dimple numbers of the upper region and the lower region are basically the same. In this case, partial hydrogen embrittlement has not occurred, and the high-entropy alloy sample passes the test. If the dimple number difference is greater than the dimple number threshold, it indicates that there is a difference in the dimple numbers of the upper region and the lower region. In this case, partial hydrogen embrittlement has occurred in the region with fewer dimples among the upper region and the lower region, and the high-entropy alloy sample fails the test. Because in the above process, when the dimple density is greater than or equal to the dimple density threshold, it represents a high dimple density at the fracture surface of the fracture part, showing ductile fracture. This dimple density reflects the overall density at the fracture surface of the fracture part. If the dimples are concentrated in a certain region of the fracture surface and there are no or relatively few dimples in other regions, then for the entire fracture surface, the region with fewer or no dimples has also undergone hydrogen embrittlement, that is, partial hydrogen embrittlement has occurred at the fracture surface of the fracture part. For a high-entropy alloy sample with partial hydrogen embrittlement, its test cannot be considered qualified because in the actual use process, once a certain part starts to undergo hydrogen embrittlement, it will gradually spread to other regions. Therefore, the dimple number difference between the upper region and the lower region is used for re-judgment. This detection method further subdivides the dimple distribution of the fracture part when the dimple density is greater than or equal to the dimple density threshold to improve the detection accuracy. First, the fracture part is evenly divided into upper and lower regions, and the dimple numbers of each region are calculated respectively. Then, the dimple number difference is obtained by subtracting the region with fewer dimples from the region with more dimples, and it is compared with the preset dimple number difference threshold. If the dimple number difference is less than or equal to the dimple number difference threshold, it indicates that the dimples are evenly distributed on the entire fracture surface, the material has not undergone partial hydrogen embrittlement, and the test is qualified; if the dimple number difference is greater than the dimple number difference threshold, it indicates that the dimples are unevenly distributed in the fracture region, and the dimple number in a certain region is significantly reduced, meaning that partial hydrogen embrittlement may have occurred in this region, and the test is unqualified. The appearance of partial hydrogen embrittlement indicates that the material has been locally affected by hydrogen, and hydrogen embrittlement has the characteristic of diffusion and may deteriorate further during use. Therefore, such samples cannot be considered qualified.This method analyzes the local distribution of the number of dimples, making up for the problem that the overall dimple density may miss local hydrogen embrittlement, and making the hydrogen embrittlement resistance detection more rigorous and reliable.

[0030] In the embodiments disclosed by the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. The embodiments disclosed by the present invention include a computer program product, which includes a computer program carried on a computer-readable medium. The computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit, the above-mentioned functions defined in the methods of the present application are executed. It should be noted that the above-mentioned computer-readable medium in the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wire segments, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or combined with an instruction execution system, device, or component. In the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which the computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or combined with an instruction execution system, device, or component. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: a wireless segment, a wire segment, an optical cable, RF, etc., or any suitable combination of the above.

[0031] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0032] Those skilled in the art should understand that the above description is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application.

Claims

1. A method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning, characterized in that, Including: Step 1: Select a high-entropy alloy sample, record its initial length, denoted as the standard length. After recording, place it in a hydrogen environment. After a period of time, take out the high-entropy alloy sample and perform tensile testing on it. The tensile rate is generated by a machine learning model combined with historical data to obtain an appropriate rate for tensile testing until fracture. After fracture, record its fracture length. Subtract the standard length from the fracture length and then divide by the standard length to obtain the fracture elongation rate of the high-entropy alloy sample. Step 2: Set the fracture elongation rate threshold for the high-entropy alloy. The fracture elongation rate threshold is the standard elongation rate of the high-entropy alloy after fracture in the absence of a hydrogen environment. Step 3: Compare the fracture elongation rate of the high-entropy alloy sample with the fracture elongation rate threshold. If the fracture elongation rate of the high-entropy alloy sample is less than the fracture elongation rate threshold, it indicates that the fracture elongation rate of the high-entropy alloy sample has decreased and hydrogen embrittlement has occurred. In this case, the anti-hydrogen embrittlement test of the high-entropy alloy sample fails. If the fracture elongation rate of the high-entropy alloy sample is greater than or equal to the fracture elongation rate threshold, it indicates that the fracture elongation rate of the high-entropy alloy sample has not been affected by hydrogen. In this case, the anti-hydrogen embrittlement test of the high-entropy alloy sample passes.

2. The method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning according to claim 1, wherein, When the fracture elongation rate of the high-entropy alloy sample is greater than or equal to the fracture elongation rate threshold, set a second threshold for the fracture elongation rate greater than the fracture elongation rate threshold. Compare the fracture elongation rate of the high-entropy alloy sample with the second threshold for the fracture elongation rate, and different responses are obtained according to the comparison results.

3. The method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning according to claim 2, wherein If the fracture elongation rate of the high-entropy alloy sample is greater than the second threshold for the fracture elongation rate, it indicates that the fracture elongation rate of the high-entropy alloy sample is far from the fracture elongation rate threshold and the high-entropy alloy sample has not been affected by hydrogen. In this case, the high-entropy alloy sample passes the test. If the fracture elongation rate of the high-entropy alloy sample is less than or equal to the second threshold for the fracture elongation rate, it indicates that the fracture elongation rate of the high-entropy alloy sample is close to the fracture elongation rate threshold and the high-entropy alloy sample may have been affected by hydrogen but not detected. In this case, a secondary test is performed.

4. The method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning according to claim 3, wherein, During the secondary test, select one of the fracture parts of the high-entropy alloy sample, obtain the number of dimples at the fracture surface of the fracture part. At the same time, measure the area of the fracture surface of the fracture part. Divide the number of dimples by the fracture surface area to obtain the dimple density, and set the dimple density threshold in the absence of the influence of the hydrogen environment. Compare the dimple density with the dimple density threshold, and different responses are obtained according to the comparison results.

5. The method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning according to claim 4, wherein, If the dimple density is less than the dimple density threshold, it represents that the dimple density at the fracture surface of the fracture part is low, showing brittle fracture, so hydrogen embrittlement has occurred due to the influence of hydrogen. In this case, the high-entropy alloy sample fails the test. If the dimple density is greater than or equal to the dimple density threshold, it represents that the dimple density at the fracture surface of the fracture part is high, showing ductile fracture, so it has not been affected by hydrogen. In this case, the high-entropy alloy sample passes the test.

6. The method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning according to claim 5, wherein, When the dimple density is greater than or equal to the dimple density threshold, divide the fracture surface of the fracture part into upper and lower regions equally, respectively obtain the number of dimples in the upper region and the lower region, subtract the number of dimples in the region with fewer dimples from the number of dimples in the region with more dimples to obtain the difference in the number of dimples, and use the difference in the number of dimples in the two regions to make another judgment.

7. The method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning according to claim 6, wherein, When making a judgment again, set the threshold of the difference in the number of dimples, compare the difference in the number of dimples with the threshold of the difference in the number of dimples, and obtain different responses according to the comparison results.

8. The method for detecting the hydrogen embrittlement resistance performance of high-entropy alloys driven by machine learning according to claim 7, characterized in that, If the difference in the number of dimples is less than or equal to the threshold of the difference in the number of dimples, it indicates that the number of dimples in the upper region is basically the same as that in the lower region. In this case, partial hydrogen embrittlement has not occurred and the detection of the high-entropy alloy sample is qualified; if the difference in the number of dimples is greater than the threshold of the number of dimples, it indicates that there is a difference in the number of dimples between the upper region and the lower region. In this case, partial hydrogen embrittlement has occurred in the region with fewer dimples in the upper region and the lower region, and the detection of the high-entropy alloy sample is unqualified.

9. A machine learning-driven high-entropy alloy hydrogen embrittlement resistance performance detection device for performing the method according to any one of claims 1-8, characterized in that, Including: An acquisition module, which is used to select a high-entropy alloy sample, record its initial length, denoted as the standard length. After recording, place it in a hydrogen environment. After a period of time, take out the high-entropy alloy sample and perform tensile testing on it until it breaks. After breaking, record its fracture length, and use the fracture length minus the standard length and then divide by the standard length to obtain the fracture elongation rate of the high-entropy alloy sample; A setting module, which is used to set the threshold of the fracture elongation rate of the high-entropy alloy. The threshold of the fracture elongation rate is the standard elongation rate of the high-entropy alloy after fracture in the absence of a hydrogen environment; A comparison module, which is used to compare the fracture elongation rate of the high-entropy alloy sample with the threshold of the fracture elongation rate. If the fracture elongation rate of the high-entropy alloy sample is less than the threshold of the fracture elongation rate, it means that the fracture elongation rate of the high-entropy alloy sample has decreased and hydrogen embrittlement has occurred. In this case, the anti-hydrogen embrittlement detection of the high-entropy alloy sample is unqualified; if the fracture elongation rate of the high-entropy alloy sample is greater than or equal to the threshold of the fracture elongation rate, it means that the fracture elongation rate of the high-entropy alloy sample has not been affected by hydrogen. In this case, the anti-hydrogen embrittlement detection of the high-entropy alloy sample is qualified.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a method for detecting the anti-hydrogen embrittlement performance of high-entropy alloys according to any one of claims 1-8 above.

Images