Method and system for synthesizing high-frequency nanocrystalline alloy

Abstract

A method and system for synthesizing a high-frequency nanocrystalline alloy. On the basis of an XGBoost algorithm, an alloy component design criterion which involves a low error rate is obtained by means of limiting the selection of alloy elements, and key features such as an electron concentration; by means of the alloy component design criterion, an ultra-thin nanocrystalline soft magnetic alloy strip which has a high amorphous forming capability, a low coercive force and low loss can be obtained, thereby achieving the technical effect of efficiently completing the design of a high-frequency nanocrystalline alloy; and alloy design is performed by using the method for synthesizing a high-frequency nanocrystalline alloy, and the method has the characteristics of having a wide range of application scenarios and being suitable for industrial production.

Description

Synthesis method and system of high-frequency nanocrystalline alloy

[0001] This application claims priority to the Chinese invention patent application filed with the China Patent Office on November 17, 2023, with application number 202311298021.1, and invention name “Method and system for synthesizing high-frequency nanocrystalline alloys”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of nanocrystalline alloys, and more specifically, to a synthesis method, system, electronic device, and computer-readable storage medium for high-frequency nanocrystalline alloys. Background Art

[0003] Iron-based nanocrystalline soft magnetic alloys refer to amorphous precursors that, after nanocrystallization, obtain a dual-phase structure of coupled amorphous and nanocrystalline phases, which has excellent comprehensive soft magnetic properties; it has great application prospects in the fields of new energy vehicles, rail transportation, 5G communications, power electronics, etc. However, a completely disordered amorphous precursor is the key prerequisite for obtaining a fine and uniformly distributed amorphous-nanocrystalline dual-phase structure through nanocrystallization heat treatment. However, in practical applications, the existing amorphous composition design criteria have limitations, and the parameters that measure the amorphous forming ability are difficult to obtain and are not conducive to composition development. Specifically, the design and development of iron-based nanocrystalline soft magnetic alloys still rely mainly on the traditional "trial and error" method, designing the alloy composition based on experience, and then using experimental means to prepare samples and characterize / evaluate the performance for each alloy composition. This has the disadvantages of long experimental cycles, low efficiency, high costs, and a certain degree of randomness.

[0004] When the traditional empirical approach severely restricted the development and growth of new materials and could not meet the needs of modern complex material development, with the rapid development of computer technology, computational materials science based on different theoretical methods has become a new field in materials science today, which can perform simulation calculations at the electronic level, atomic level, microscopic level and macroscopic level. Statistical methods for alloy composition design such as fuzzy identification method, machine learning, and GA (Genetic Algorithm) have been developed. For example, the prior art discloses a method for designing high thermal stability iron-based soft magnetic amorphous alloys using machine learning algorithms (publication number: CN112582032A). The specific steps include: (1) establishing an iron-based amorphous alloy data set; (2) data set preprocessing; (3) establishing a prediction model through machine learning to extract important features; (4) exploring the physical meaning behind the important features and establishing alloy design criteria with high accuracy; (5) experimental verification of the alloy design criteria. Although the saturation magnetic induction intensity (Bs) of 1.59T and the crystallization temperature (T x ) is the alloy composition Fe at 757K81.55 B 14.79 Si 0.9 Zr 2.76。 However, the above alloy design contains the oxidizing element Zr and needs to be prepared in a vacuum, which is not suitable for industrial mass production.

[0005] The prior art discloses a method for designing high-performance iron-based amorphous nano-soft magnetic alloys based on machine learning (publication number: CN112951343A), which includes selecting five elements according to a neural network model to design an alloy composition with a specific saturation magnetic induction intensity, obtaining an alloy composition with a saturation magnetic induction intensity of 1.8T; weighing raw materials according to the alloy composition, and using a vacuum non-consumable arc furnace to melt the raw materials under specific melting conditions to obtain a master alloy, and then preparing an iron-based amorphous alloy thin strip, which is then subjected to XRD testing, TEM testing, and VSM testing. The method achieves simulation prediction results based on the machine learning neural network model, improving the alloy's amorphous forming ability. However, the inventors realized that the above alloy design has high high-frequency losses under high magnetic induction and is not suitable for high-frequency applications.

[0006] Therefore, there is an urgent need for a design method for nanocrystalline soft magnetic alloys with high amorphous forming ability, low ribbon thickness and low coercivity.

[0007] Summary of the Invention

[0008] In view of the above problems, the purpose of this application is to provide a synthesis method, system, electronic device and computer-readable storage medium for high-frequency nanocrystalline alloys to solve at least one of the above technical problems.

[0009] According to one aspect of the present application, a method for synthesizing a high-frequency nanocrystalline alloy is provided, comprising screening key features based on amorphous forming ability, coercivity and characteristic composition data sets, obtaining alloy composition design criteria through SHAP analysis, and designing the nanocrystalline soft magnetic alloy composition in combination with the XGBoost algorithm.

[0010] In order to solve the above problems, the present application also provides a synthesis system for high-frequency nanocrystalline alloys, which includes a data set acquisition module for constructing a data set based on amorphous forming ability, coercivity and characteristics; an alloy composition design criterion acquisition module for screening key features and obtaining alloy composition design criteria through SHAP analysis; and a design module for designing nanocrystalline soft magnetic alloy compositions in combination with the XGBoost algorithm.

[0011] The present application also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps in the above-mentioned synthesis method based on high-frequency nanocrystalline alloy.

[0012] In order to solve the above problems, the present application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned synthesis method based on high-frequency nanocrystalline alloy.

[0013] By utilizing the above-mentioned synthesis method of high-frequency nanocrystalline alloys according to the present application, based on the XGBoost algorithm, an alloy composition design criterion with a low error rate is obtained by limiting the selection of alloying elements and key features such as electron concentration; the alloy composition design criterion of the present application can obtain ultra-thin nanocrystalline soft magnetic alloy strips with high amorphous forming ability, low coercivity, and low loss, thereby achieving the technical effect of efficiently completing the design of high-frequency nanocrystalline alloys; the synthesis method of high-frequency nanocrystalline alloys of the present application has the characteristics of wide application scenarios and is suitable for industrial production.

[0014] To achieve the above and related purposes, one or more aspects of the present application include features that will be described in detail below and particularly pointed out in the claims. The following description and the accompanying drawings set forth certain exemplary aspects of the present application in detail. However, these aspects are merely indicative of some of the various ways in which the principles of the present application may be employed. Furthermore, the present application is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By referring to the following description and claims in conjunction with the accompanying drawings, and with a more comprehensive understanding of the present application, other objects and results of the present application will become more apparent and easier to understand. In the accompanying drawings:

[0016] FIG1 shows a flow chart of a method for synthesizing a high-frequency nanocrystalline alloy according to the present application; and

[0017] Figure 2 shows the relationship between the amorphous forming ability AFA and the non-ferromagnetic electron concentration VEC1 (a), the total electron concentration VEC (b), and the first crystallization temperature T x1 and the second crystallization temperature T x2 SHAP relationship diagram between the temperature range ΔT (c) and the boron content (d);

[0018] FIG3 shows the XRD patterns of the amorphous precursors produced in Examples 1 and 2 of the present application at the critical speed;

[0019] FIG4 shows the DSC graphs of the amorphous precursors produced at the critical speed in Examples 1 and 2 of the present application.

[0020] FIG5 shows a schematic structural diagram of a synthesis system for high-frequency nanocrystalline alloys according to the present application.

[0021] FIG6 shows a schematic structural diagram of an electronic device according to the method for synthesizing high-frequency nanocrystalline alloys of the present application.

[0022] The same reference numerals throughout the drawings indicate similar or corresponding features or functions. DETAILED DESCRIPTION

[0023] In the following description, for illustrative purposes, numerous specific details are set forth to provide a comprehensive understanding of one or more embodiments. However, it will be apparent that the embodiments may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form to facilitate description of one or more embodiments.

[0024] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0025] Example 1

[0026] FIG1 shows a flow chart of a method for synthesizing a high-frequency nanocrystalline alloy according to the present application.

[0027] As shown in Figure 1, S110, based on amorphous forming ability (AFA) and coercive force (H c ) and features constitute the dataset.

[0028] The characteristics include elemental characteristics, thermodynamic characteristics and calculation characteristics.

[0029] For example, Mo has antioxidant properties that can improve the amorphous forming ability of nanocrystalline precursors. A small amount of addition can also increase the amount of a-Fe(Si) phase precipitation and improve high-frequency soft magnetic properties. Ga is a low-melting-point metal element. The preparation of ultra-thin nanocrystalline precursors requires consideration of both viscosity and fluidity. High viscosity and poor fluidity can easily cause nozzle blockage or ribbon breakage during ultra-thin ribbon preparation. Adding a small amount of Ga can appropriately improve melt fluidity. A small amount of Ge can lower the crystallization temperature of the primary phase, increase the precipitation temperature of the secondary phase, stabilize the precipitation temperature range of the a-Fe(Si) phase, improve the stability of the residual amorphous phase, and inhibit the further growth of nanocrystal grains.

[0030] Specifically, in order to reduce the inspection error rate of the alloy composition design criteria, it is necessary to limit the selection of alloying elements and key features such as electron concentration. The original feature pool includes the above 15 alloying elements, composition ratios, and the total electron concentration (VEC), non-ferromagnetic electron concentration (VEC1), first crystallization temperature (T x1 ), the second crystallization temperature (T x2 ), the first crystallization temperature T x1 and the second crystallization temperature T x2 The present application constructs a rationally designed feature pool to limit the target performance of alloying elements to the aforementioned 22 features, thereby reducing the error rate of the verification of alloy composition design criteria.

[0031] Specifically, the elemental characteristics relate to Fe, Co, Ni, Si, P, B, C, Cu, Nb, Al, Cr, Mn, Mo, Ga and Ge. The thermodynamic characteristics include T x1 、T x2 , ΔT. The calculated features are VEC1, VEC, ΔS and χ.

[0032] Compared with the existing alloy composition design method that uses 52 elements in the periodic table as model elements, this application accurately limits the selection of alloy elements to 15 elements: Fe, Co, Ni, Si, P, B, C, Cu, Nb, Al, Cr, Mn, Mo, Ga and Ge. While maintaining computing power, it can quickly and accurately find suitable alloy components, improve the efficiency of component screening, and greatly reduce the inspection error rate of alloy composition design criteria. Obtain the data of each soft magnetic property characteristic corresponding to each alloy element and the AFA and H corresponding to each alloy element. c There are 393 data in total, which constitute the data set.

[0033] S120, screen key features and obtain alloy composition design criteria through SHAP analysis.

[0034] The key features are the atomic percentages of VEC1, VEC, and B elements, and ΔT. The alloy composition design criteria are VEC1>0.71, VEC<7.29, ΔT>121° C., and the atomic percentage of B element is 6.85 at % to 11.54 at %.

[0035] The data set obtained in S110 is divided into 70% of the data as a training set and 30% of the data as a test set. In the specific implementation process, the goodness of fit R of the test set and the training set of the AFA prediction model is 2reached 0.959 and 0.964 respectively; R 2 It measures the ability of the model to explain the variance of the dependent variable, R 2 The value of R is between negative infinity and 1; 2 The closer the value is to 1, the better the model fitting effect is.

[0036] It should be noted that in the specific implementation, the AFA prediction model is implemented using the XGBoost algorithm. However, this is not limiting. Other machine learning algorithms, such as linear regression and neural networks, can also be used for regression fitting, in addition to support vector regression (SVR), gradient boosting regression (GBR), and random forest (RF). Hyperparameters for the AFA prediction model include the (maximum) learning rate, initial values ​​for parameter tuning, the max_depth parameter, and the min_child_weight parameter.

[0037] In this application, 22 features are used as inputs to the AFA prediction model; AFA and H c As a goal, the importance of the above features is screened; the SHAP analysis method is used to interpret the above optimal AFA prediction model; that is, the influence of the first few important key features on the model prediction function is obtained, and then the importance of each feature is calculated based on the SHAP analysis to determine the impact on AFA and H c The ones with greater influence are VEC1, VEC, B content, and ΔT. Then the correlation between key features and AFA is obtained. Figure 2 shows the SHAP relationship diagram between AFA and VEC1 (a), VEC (b), ΔT (c), and boron content (d); the horizontal axis is the characteristic value, and the vertical axis is the corresponding SHAP value. It can be seen from Figure 2 that when VEC1>0.71, VEC<7.29, B content is 6.85at%<B<11.54at%, and ΔT>121℃, the SHAP values ​​are all greater than 0, which is conducive to obtaining good AFA, thereby establishing the alloy composition design criteria.

[0038] S130. Design the composition of nanocrystalline soft magnetic alloys using XGBoost algorithm.

[0039] According to the above alloy composition design criteria, relying on the NSGA-II genetic algorithm, by screening to meet VEC1>0.71, VEC<7.29, B content of 6.85at%<B<11.54at%, ΔT>121℃, it is possible to efficiently obtain the expected (both low H c and the precursor is an amorphous structure) alloy component Fe 73.1 Si 13 B 10.6 Cu 1.4 Nb 1.3 Mn 0.1 Ga0.6 .

[0040] The method further includes verifying the composition of the iron-based nanocrystalline soft magnetic alloy. Specifically, the method includes steps S141 to S145.

[0041] S141. According to the alloy composition and the atomic percentage molecular formula of each component, the materials are prepared and smelted to obtain an alloy ingot with uniform composition. Specifically, (1) a commercially available Fe3P intermediate alloy ingot is prepared; (2) pure raw materials of Fe, Si, B, Cu, Nb, Mn, and Ga with a purity of 99.9% and an intermediate alloy ingot Fe3P (99.9%) are prepared according to the atomic percentage of the alloy composition; (3) the raw materials weighed in step (2) are placed in a high-frequency induction melting furnace for melting, and first vacuumed to 5×10 -2 Pa, and then fill in an appropriate amount of protective gas argon. After the alloy is melted, keep it warm for 30 minutes to make the alloy raw materials melt evenly, then pour it into a casting copper mold and cool it to obtain an alloy ingot.

[0042] S142. Single-roll quench the alloy ingot to obtain an amorphous precursor strip. The alloy ingot is crushed and placed into a quartz tube with an open bottom end. The ingot is then placed in an induction coil of a casting device. After the alloy is melted, the molten alloy is sprayed onto a rotating copper roller at a set speed. The amorphous precursor strip is produced using a single-roll rapid quenching method.

[0043] S143. Perform XRD and DSC tests on the amorphous precursor strip. The amorphous precursor strips produced at different copper roller speeds (20-45 m / s) were tested for their phase structure using X-ray diffraction (XRD). As shown in FIG3 , a crystallization diffraction peak appeared at 2θ≈45°, wherein the peak at 2θ≈45° had the characteristics of an amorphous peak. Therefore, the alloy strip of this embodiment is an amorphous nanocrystalline strip. Example 1 of this embodiment still has an amorphous structure at 20 m / s, and its critical speed is 20 m / s, which is suitable for the speed required for industrial production. The amorphous precursor strip was tested and analyzed by DSC (differential scanning calorimetry). The results are shown in FIG4 . Its crystallization temperature range ΔT is 124°C. The larger the ΔT value, the more obvious the improvement of soft magnetic properties by magnetic field annealing.

[0044] S144. Place the amorphous precursor strip in a furnace, heat it to 560°C, keep it warm for 30 minutes for nanocrystallization, and then cool it to room temperature by water quenching to obtain an iron-based nanocrystalline soft magnetic alloy.

[0045] S145, the amorphous precursor strip after the crystallization heat treatment in step S144 is measured by a DC BH instrument to obtain the coercive force H of the iron-based nanocrystalline soft magnetic alloy. c As low as 1.4A / m.

[0046] The VEC1 of Example 1 is 1.08, VEC is 6.92, B content is 10.6 at%, and ΔT is 124°C. These results are basically consistent with the predicted results, demonstrating the feasibility of the alloy composition design principle proposed based on the model interpretation.

[0047] Example 2

[0048] The steps of this embodiment are basically the same as steps S110 to S120 in embodiment 1.

[0049] S130, according to the above alloy composition design criteria, screening to meet VEC1>0.71, VEC<7.29, B content of 6.85at%<B<11.54at%, ΔT>121℃, you can efficiently obtain the expected alloy composition Fe 72.8 Si 12.7 B 9.9 Cu 1.5 Nb1Al 0.52 Mn 0.8 Ga 0.8 .

[0050] The method further includes step S140 of verifying the composition of the iron-based nanocrystalline soft magnetic alloy.

[0051] Specifically, the method for verifying the composition of the iron-based nanocrystalline soft magnetic alloy includes steps S141 to S145.

[0052] S141. The materials are prepared according to the alloy composition and the molecular formula of the atomic percentage of each component, and smelted to obtain an alloy ingot with uniform composition.

[0053] S142. Single-roller quenching is performed on the alloy ingot to obtain an amorphous precursor strip.

[0054] S143. Perform XRD and DSC tests on the amorphous precursor strip. The amorphous precursor strips produced at different copper roller speeds (20-45 m / s) were tested for their phase structure using X-ray diffraction (XRD). As shown in Figure 3, a crystallization diffraction peak appears at 2θ≈45°. The peak at 2θ≈45° has the characteristics of an amorphous peak, so the alloy strip of this embodiment is an amorphous nanocrystalline strip. This embodiment still has an amorphous structure at 20 m / s, and its critical speed is 20 m / s, which is suitable for the speed required for industrial production. The amorphous precursor strip was tested and analyzed by DSC. As shown in Figure 4, its ΔT is 133°C.

[0055] S144. Place the amorphous precursor strip in a furnace, heat it to 560°C, keep it warm for 30 minutes for nanocrystallization, and then cool it to room temperature by water quenching to obtain an iron-based nanocrystalline soft magnetic alloy.

[0056] S145, the amorphous precursor strip after the crystallization heat treatment in step S144 is measured by a DC BH instrument to obtain the coercivity of the alloy. c As low as 1.7A / m.

[0057] In Example 2, VEC1 is 1.11, VEC is 6.94, B content is 9.88 at.%, and ΔT is 133° C. This is basically consistent with the predicted results, proving the feasibility of the composition design principle proposed based on the model interpretation.

[0058] Example 3

[0059] The steps of this embodiment are basically the same as steps S110 to S120 in embodiment 1.

[0060] S130, according to the above alloy composition design criteria, screen VEC1>0.71, VEC<7.29, B content 6.85at%<B<11.54at%, ΔT>121℃, and you can efficiently obtain the expected alloy composition Fe 74 Cu1Nb2Si 13 B8M 1.9 Al 0.1 .

[0061] Verification of gold content:

[0062] S141. Industrial raw materials are blended according to the alloy composition and the atomic percentage molecular formula of each component, and smelted to obtain an alloy ingot with uniform composition. S142. The alloy ingot is rapidly quenched in air using a single roller to obtain an amorphous precursor strip. The strip has a thickness of 14-16 μm and a width of 65 mm.

[0063] S143, perform XRD and DSC tests on the amorphous precursor strip. The amorphous precursor strips produced at different copper roller speeds (20-25 m / s) were tested for their phase structure using X-ray diffraction (XRD). The amorphous structure of this embodiment remained at 20 m / s, which is suitable for the speed required for industrial production. The amorphous precursor strips were tested and analyzed by DSC. During the measurement process, the temperature was measured at a heating rate of 0.67 ° C / s. x1 and T x2 , thereby determining the heat treatment temperature range.

[0064] The results show that the amorphous precursor of this embodiment has a completely amorphous structure, and its ΔT is 163°C.

[0065] S144. Place the amorphous precursor strip in a furnace, heat it to 570°C, keep it warm for 30 minutes for nanocrystallization, then cool it to 360°C, keep it warm for 180 minutes under an 800 Oe magnetic field, and then cool it to room temperature to obtain an iron-based nanocrystalline soft magnetic alloy; wherein the direction of the magnetic field is perpendicular to the strip axis.

[0066] S145, the amorphous precursor strip after the crystallization heat treatment in step S144 is measured by a DC BH instrument to obtain the coercive force H of the iron-based nanocrystalline soft magnetic alloy. c The loss is 0.5A / m. Using an AC BH instrument to test the loss, the result is 2.28W / kg at an operating magnetic induction of 0.5T and a frequency of 10kHz. This means that the loss of the iron-based nanocrystalline soft magnetic alloy is less than 2.3W / kg at an operating magnetic induction of 0.5T and a frequency of 10kHz.

[0067] In Example 3, VEC1 is 1.106, VEC is 7.026, B content is 8 at.%, and ΔT is 163° C. This is basically consistent with the predicted results, proving the feasibility of the composition design principle proposed based on the model interpretation.

[0068] Example 4

[0069] The steps of this embodiment are basically the same as steps S110 to S120 in embodiment 1.

[0070] S130, according to the above alloy composition design criteria, screening to meet VEC1>0.71, VEC<7.29, B content of 6.85at%<B<11.54at%, ΔT>121℃, you can efficiently obtain the expected alloy composition Fe 74 Cu1Nb2Si 15 B7P 0.7 Al 0.3 .

[0071] Verification of the composition of iron-based nanocrystalline soft magnetic alloy:

[0072] S141. The materials are prepared according to the alloy composition and the molecular formula of the atomic percentage of each component, and smelted to obtain an alloy ingot with uniform composition.

[0073] S142: Single-roller quenching is performed on the alloy ingot to obtain an amorphous precursor strip having a thickness of 16 μm.

[0074] S143. Perform XRD and DSC tests on the amorphous precursor strip. The amorphous precursor strips prepared at different copper roller speeds (20-45 m / s) were tested for their phase structure using X-ray diffraction (XRD). The amorphous structure of this embodiment remained at 30 m / s, and its critical speed was 30 m / s, which is suitable for the speed required for industrial production. The amorphous precursor strips were tested and analyzed by DSC. During the measurement process, the temperature was measured at a heating rate of 0.67 ° C / s. x1 and T x2 , thereby determining the heat treatment temperature range.

[0075] The results show that the amorphous precursor of this embodiment has a completely amorphous structure, and its ΔT is 159°C.

[0076] S144. Place the amorphous precursor strip in a furnace, heat it to 560°C, keep it warm for 30 minutes for nanocrystallization, and cool it to room temperature by water quenching to obtain an iron-based nanocrystalline soft magnetic alloy.

[0077] S145, the amorphous precursor strip after the crystallization heat treatment in step S144 is measured by a DC BH instrument to obtain the coercivity of the iron-based nanocrystalline soft magnetic alloy. c As low as 1.3A / m.

[0078] In Example 4, VEC1 is 1.064, VEC is 6.984, the B content is 7 at.%, and ΔT is 159° C. This is basically consistent with the predicted results, proving the feasibility of the composition design principle proposed based on the model interpretation.

[0079] The alloys in Examples 1-4 can produce amorphous ribbons at rotation speeds of 30 m / s or less. This demonstrates that the present invention's synthesis method based on high-frequency nanocrystalline alloys is advantageous for obtaining alloys with high amorphous-forming ability. Testing indicates that the thickness of the amorphous ribbons obtained in Examples 1-4 is all less than 18 μm, demonstrating that the present invention's synthesis method based on high-frequency nanocrystalline alloys is advantageous for obtaining alloys with low ribbon thickness.

[0080] Example 5

[0081] The steps of this embodiment are basically the same as steps S110 to S120 in embodiment 1.

[0082] S130, according to the above alloy composition design criteria, screening to meet VEC1>0.71, VEC<7.29, B content of 6.85at%<B<11.54at%, ΔT>121℃, you can efficiently obtain the expected alloy composition Fe 74 Cu1Nb2Si 13 B8M 1.9 Al 0.1 .

[0083] Verification of the composition of iron-based nanocrystalline soft magnetic alloy:

[0084] S141. Industrial raw materials are blended according to the alloy composition and the atomic percentage molecular formula of each component, and smelted to obtain an alloy ingot with uniform composition. S142. The alloy ingot is rapidly quenched in air using a single roller to obtain an amorphous precursor strip. The strip has a thickness of 14-16 μm and a width of 65 mm.

[0085] S143, perform XRD and DSC tests on the amorphous precursor strip. The amorphous precursor strips produced at different copper roller speeds (20-25 m / s) were tested for their phase structure using X-ray diffraction (XRD). The amorphous structure of this embodiment remained at 20 m / s, which is suitable for the speed required for industrial production. The amorphous precursor strips were tested and analyzed by DSC. During the measurement process, the temperature was measured at a heating rate of 0.67 ° C / s. x1 and T x2 , thereby determining the heat treatment temperature range.

[0086] The results show that the amorphous precursor of this embodiment has a completely amorphous structure, and its crystallization temperature range ΔT is 163°C.

[0087] S144, placing the amorphous precursor strip in a furnace, heating it to 570° C., keeping it at that temperature for 30 minutes for nanocrystallization, and cooling it to room temperature by water quenching to obtain an iron-based nanocrystalline soft magnetic alloy;

[0088] S145, the amorphous precursor strip after the crystallization heat treatment in step S144 is measured by a DC BH instrument to obtain the coercive force H of the iron-based nanocrystalline soft magnetic alloy. c The loss is 1.8A / m. The AC BH instrument is used to test the loss, and the loss is 5.5W / kg at a working magnetic induction of 0.5T and a frequency of 10kHz.

[0089] The alloy composition of Example 5 is identical to that of Example 3, differing only in that the alloy is not prepared by cooling to 360°C after nanocrystallization, holding in an 800 Oe magnetic field for 180 minutes, and then cooling to room temperature after applying the magnetic field. The coercivity of the alloy obtained in Example 5 is 1.8 A / m. Compared with Example 3, the coercivity increases by more than three times, and the change in high-frequency loss also increases accordingly.

[0090] Example 6

[0091] The steps of this embodiment are basically the same as steps S110 to S120 in embodiment 1.

[0092] S130, according to the above alloy composition design criteria, screening to meet VEC1>0.71, VEC<7.29, B content of 6.85at%<B<11.54at%, ΔT>121℃, you can efficiently obtain the expected alloy composition Fe 72.8 Si 12.7 B 9.9 Cu 1.5 Nb1Al 0.52 Mn 0.8 Ga 0.8 .

[0093] The method further includes step S140 of verifying the composition of the iron-based nanocrystalline soft magnetic alloy.

[0094] Specifically, the method for verifying the composition of the iron-based nanocrystalline soft magnetic alloy includes steps S141 to S145.

[0095] S141. The materials are prepared according to the alloy composition and the atomic percentage molecular formula of each component, and smelted to obtain an alloy ingot with uniform composition.

[0096] S142. Single-roller quenching is performed on the alloy ingot to obtain an amorphous precursor strip.

[0097] S143. Perform XRD and DSC testing on the amorphous precursor strip. X-ray diffraction (XRD) was used to analyze the phase structure of the amorphous precursor strips produced at different copper roller speeds (20-45 m / s). The present embodiment still exhibited an amorphous structure at 20 m / s, indicating a critical speed of 20 m / s, suitable for industrial production. DSC analysis of the amorphous precursor strip revealed a ΔT of 133°C.

[0098] S144. Place the amorphous precursor strip in a furnace, heat it to 560°C, keep it warm for 30 minutes for nanocrystallization, then cool it to 420°C, keep it warm for 30 minutes under a 500 Oe magnetic field, and then cool it to room temperature to obtain an iron-based nanocrystalline soft magnetic alloy; wherein the direction of the magnetic field is perpendicular to the strip axis.

[0099] S145, the amorphous precursor strip after the crystallization heat treatment in step S144 is measured by a DC BH instrument to obtain the coercive force H of the iron-based nanocrystalline soft magnetic alloy. c As low as 0.7A / m. The loss is tested by AC BH instrument, and the loss is 2.2W / kg at a working magnetic induction of 0.5T and a frequency of 10kHz.

[0100] The alloy composition of Example 6 is exactly the same as that of Example 2, the only difference being the additional step of cooling to 330-420°C after nanocrystallization, keeping warm and applying a magnetic field, and then cooling to room temperature to obtain the alloy; the coercive force of the alloy obtained in Example 6 is 0.7 A / m, which is 2.5 times lower than that in Example 2.

[0101] Example 7

[0102] The steps of this embodiment are basically the same as steps S110 to S120 in embodiment 1.

[0103] S130, according to the above alloy composition design criteria, screening VEC1 ≥ 0.71, VEC ≤ 7.29, ΔT > 121 ° C, B atomic content of 6.85at% ≤ B ≤ 11.54at%, you can efficiently obtain the expected alloy composition Fe 74 Cu1Nb2Si 15 B7P 0.7 Al 0.3 .

[0104] Verification of the composition of iron-based nanocrystalline soft magnetic alloy:

[0105] S141. The alloy components and the atomic percentage molecular formula of each component are prepared and melted to obtain an alloy ingot with uniform composition. S142. The alloy ingot is subjected to single-roll rapid cooling to obtain an amorphous precursor strip. The strip thickness is 16 μm.

[0106] S143. Perform XRD and DSC tests on the amorphous precursor strip. The amorphous precursor strips prepared at different copper roller speeds (20-45 m / s) were tested for their phase structure using X-ray diffraction (XRD). The amorphous structure of this embodiment remained at 30 m / s, and its critical speed was 30 m / s, which is suitable for the speed required for industrial production. The amorphous precursor strips were tested and analyzed by DSC. During the measurement process, the temperature was measured at a heating rate of 0.67 ° C / s. x1 and T x2 , thereby determining the heat treatment temperature range.

[0107] The results show that the amorphous precursor of this embodiment has a completely amorphous structure, and its ΔT is 159°C.

[0108] S144. Place the amorphous precursor strip in a furnace, heat it to 560°C, keep it warm for 30 minutes to perform nanocrystallization, then cool it to 330°C, keep it warm for 100 minutes under a 1000 Oe magnetic field, and then cool it to room temperature to obtain an iron-based nanocrystalline soft magnetic alloy; wherein the direction of the magnetic field is perpendicular to the strip axis.

[0109] S145, the amorphous precursor strip after the crystallization heat treatment in step S144 is measured by a DC BH instrument to obtain the coercive force H of the iron-based nanocrystalline soft magnetic alloy. c As low as 0.6A / m. The loss is tested by AC BH instrument, and the loss is 2.1W / kg at a working magnetic induction of 0.5T and a frequency of 10kHz.

[0110] The alloy composition of Example 7 is exactly the same as that of Example 4, the only difference being the addition of the step of cooling to 330-420°C after nanocrystallization, maintaining the temperature and applying a magnetic field, and then cooling to room temperature to obtain the alloy; the coercivity of the alloy obtained in Example 7 is 0.6 A / m, which is significantly reduced compared to the coercivity of 1.3 A / m in Example 4. In summary, through the comparison of the above embodiments (Example 2 and Example 6, Example 3 and Example 5, Example 4 and Example 7), it can be seen that the composite nanocrystallization heat treatment method of the present application can achieve the matching of random effective anisotropy and uniaxial uniform anisotropy effect, so that the domain wall motion and magnetization rotation are balanced during the magnetization process, thereby obtaining an ultra-thin nanocrystalline soft magnetic alloy strip with high amorphous forming ability, low coercivity, and low loss, thereby achieving the technical effect of efficiently completing the design of high-frequency nanocrystalline alloys.

[0111] The high-frequency losses in Examples 6-7 are all less than or equal to 2.2 W / kg. Compared with the high-frequency loss of Example 5, which does not add the step of cooling to 330-420°C after nanocrystallization, keeping the alloy warm and applying a magnetic field, and then cooling to room temperature to obtain the alloy, the high-frequency loss is greatly reduced.

[0112] It can be seen from the test that the coercive force H of the alloys obtained in Examples 1 to 7 is c All are lower than 1.8A / m; the coercive force H of the alloy obtained in the prior art is c It is about 3.1A / m. Through comparison, it is found that the synthesis method based on high-frequency nanocrystalline alloy of the present application is conducive to obtaining alloys with low coercivity.

[0113] Comparative Example 1

[0114] Using the existing machine learning-based prediction method for iron-based nanocrystalline alloys, the obtained iron-based nanocrystalline soft magnetic alloy composition is: Fe 81.4 Si 6.8 B 8.6 Cu 0.7 P 1.9 Nb 0.6 ; A single-roller rapid cooling strip spinning process was used to prepare an amorphous precursor strip with a width of about 1 mm and a thickness of about 22 μm at a rate of 40 m / s in an argon atmosphere; the experimental values ​​of Bs and Hc in this embodiment were 1.72T and 3.8 A / m, respectively.

[0115] Compared with Examples 3 and 4, the strip thickness of the amorphous precursor strip obtained in Example 3 is less than 16 μm; compared with the strip thickness of the alloy obtained in Comparative Example 1 of 22 μm, the synthesis method based on high-frequency nanocrystalline alloy of the present application is conducive to obtaining alloys with low strip thickness.

[0116] H in the alloys of Examples 1 and 2 c The H of the alloy obtained in Comparative Example 1 is 1.76A / m and 1.40A / m respectively; c It is 3.8 A / m. Through comparison, it is found that the synthesis method based on high-frequency nanocrystalline alloy of the present application is conducive to obtaining alloys with low coercivity.

[0117] Comparative Example 2

[0118] Using the existing machine learning-based prediction method for iron-based nanocrystalline alloys, the obtained iron-based nanocrystalline soft magnetic alloy composition is: Fe 81.6 Si 7.3 B 8.5 Cu 0.7 P 1.8 Nb 0.1 ; A single-roller rapid cooling and strip spinning process is used to obtain the amorphous precursor strip; the experimental values ​​of Bs and Hc in this embodiment are 1.71T and 3.3A / m respectively.

[0119] H in the alloys of Examples 1 and 2 c 1.76A / m and 1.40A / m respectively; further, the H of the alloys obtained in Example 3, Example 6 and Example 7 c Less than 0.7A / m; while the H of the alloy obtained in Comparative Example 2 c It is 3.3 A / m. Through comparison, it is found that the synthesis method based on high-frequency nanocrystalline alloy of the present application is conducive to obtaining alloys with low coercivity.

[0120] The synthesis method of high-frequency nanocrystalline alloy according to the present application is described above with reference to Figure 1. The synthesis method of high-frequency nanocrystalline alloy according to the present application can be implemented by software, hardware, or a combination of software and hardware.

[0121] As shown in Figure 5, the present application provides a high-frequency nanocrystalline alloy synthesis system 500, which can be installed in an electronic device. Depending on the functions implemented, the high-frequency nanocrystalline alloy synthesis system 500 can include a data set acquisition module 510, an alloy composition design criterion acquisition module 520, and a design module 530. The unit of the present application can also be referred to as a module, which refers to a series of computer program segments that can be executed by an electronic device processor and can perform fixed functions, which are stored in the memory of the electronic device.

[0122] In this embodiment, the functions of each module / unit are as follows:

[0123] The data set acquisition module 510 is used to construct a data set based on amorphous forming ability, coercive force and characteristics. The alloy composition design criterion acquisition module 520 is used to screen key features and obtain alloy composition design criteria through SHAP analysis; the design module 530 is used to design nanocrystalline soft magnetic alloy compositions in combination with the XGBoost algorithm. The high-frequency nanocrystalline alloy synthesis system 500 of the present application, based on the XGBoost algorithm, obtains alloy composition design criteria with a low error rate by limiting the selection of alloy elements and key features such as electron concentration; the alloy composition design criteria of the present application can obtain ultra-thin nanocrystalline soft magnetic alloy strips with high amorphous forming ability, low coercive force and low loss, thereby achieving the technical effect of efficiently completing the design of high-frequency nanocrystalline alloys; the synthesis method of the high-frequency nanocrystalline alloy of the present application has the characteristics of wide application scenarios and is suitable for industrial production.

[0124] As shown in FIG6 , the present application also provides an electronic device 6 based on the synthesis method of high-frequency nanocrystalline alloy.

[0125] The electronic device 6 may include a processor 60, a memory 61, and a bus. It may also include a computer program stored in the memory 61 and executable on the processor 60, such as a high-frequency nanocrystalline alloy synthesis program 62. The memory 61 may include both an internal storage unit of the high-frequency nanocrystalline alloy synthesis system and an external storage device. The memory 61 may be used to store not only installed application software and various data, such as the code for the high-frequency nanocrystalline alloy synthesis program, but also temporarily store data that has been output or is about to be output.

[0126] The memory 61 includes at least one type of readable storage medium, including a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 61 may be an internal storage unit of the electronic device 6, such as a mobile hard disk of the electronic device 6. In other embodiments, the memory 61 may also be an external storage device of the electronic device 6, such as a plug-in mobile hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 6. Furthermore, the memory 61 may include both an internal storage unit of the electronic device 6 and an external storage device. The memory 61 can be used not only to store application software and various types of data installed in the electronic device 6, such as the code of the synthesis program of the high-frequency nanocrystalline alloy, but also to temporarily store data that has been output or is about to be output.

[0127] In some embodiments, the processor 60 may be comprised of an integrated circuit, such as a single packaged integrated circuit or a plurality of packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 60 is the control core (control unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and circuits. It executes or runs programs or modules stored in the memory 61 (e.g., a high-frequency nanocrystalline alloy synthesis program) and calls data stored in the memory 61 to perform various functions of the electronic device 6 and process data.

[0128] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable connection and communication between the memory 61 and at least one processor 60, etc.

[0129] Figure 6 only shows an electronic device with components. Those skilled in the art will understand that the structure shown in Figure 6 does not constitute a limitation on the electronic device 6, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0130] For example, although not shown, the electronic device 6 may further include a power source (such as a battery) for powering various components. Preferably, the power source may be logically connected to the at least one processor 60 via a power management system, thereby implementing functions such as charge management, discharge management, and power consumption management through the power management system. The power source may further include any components such as one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 6 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not further described here.

[0131] Furthermore, the electronic device 6 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device 6 and other electronic devices.

[0132] Optionally, the electronic device 6 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 6 and to display a visual user interface.

[0133] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0134] The synthesis program 62 of high-frequency nanocrystalline alloy stored in the memory 61 in the electronic device 6 is a combination of multiple instructions. When running in the processor 60, it can achieve: based on the amorphous forming ability, coercive force and characteristic composition data set, screening key features, SHAP analysis to obtain alloy composition design criteria, and combining XGBoost algorithm to design nanocrystalline soft magnetic alloy composition.

[0135] Specifically, the specific implementation method of the processor 60 for the above instructions can be referred to the description of the relevant steps in the embodiment corresponding to Figure 1, and will not be repeated here. It should be emphasized that to further ensure the privacy and security of the above-mentioned high-frequency nanocrystalline alloy synthesis process, the above-mentioned database high-availability processing data is stored in the node of the blockchain where this server cluster is located.

[0136] Furthermore, if the modules / units integrated in the electronic device 6 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable medium may include any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0137] An embodiment of the present application also provides a computer-readable storage medium, which can be non-volatile or volatile, and stores a computer program. When the computer program is executed by a processor, it implements: based on the amorphous forming ability, coercive force and characteristic composition data set, key features are screened, SHAP analysis is performed to obtain alloy composition design criteria, and the nanocrystalline soft magnetic alloy composition is designed in combination with the XGBoost algorithm.

[0138] Specifically, the specific implementation method when the computer program is executed by the processor can refer to the description of the relevant steps in the synthesis method of high-frequency nanocrystalline alloy in the embodiment, which will not be repeated here.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0140] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0141] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0142] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application.

[0143] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the present application is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0144] The blockchain referred to in this application is a new application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0145] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems recited in a system claim may also be implemented by a single unit or system through software or hardware. Second-order terms are used to indicate names and do not imply any particular order.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for synthesizing a high-frequency nanocrystalline alloy, characterized in that: include: Based on the amorphous forming ability, coercive force and characteristic composition data sets, key features were screened, SHAP analysis was used to obtain the alloy composition design criteria, and the XGBoost algorithm was used to design the nanocrystalline soft magnetic alloy composition.

2. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: The characteristics include elemental characteristics, thermodynamic characteristics and calculated characteristics.

3. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 2, characterized in that: The elemental characteristics involve Fe, Co, Ni, Si, P, B, C, Cu, Nb, Al, Cr, Mn, Mo, Ga and Ge.

4. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 2, characterized in that: The thermodynamic characteristics include the first crystallization temperature T x1 , the second crystallization temperature T x2 , the first crystallization temperature T x1 The second crystallization temperature T x2 The temperature range ΔT between them.

5. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 2, characterized in that: The calculated features are the non-magnetic electron concentration VEC1, the total electron concentration VEC, the mixing entropy ΔS and the electronegativity χ.

6. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: The key features are the atomic percentages of VEC1, VEC, and B elements and ΔT.

7. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: The alloy composition design criteria are VEC1>0.71, VEC<7.29, ΔT>121° C. and the atomic percentage of the B element is 6.85 at % to 11.54 at %.

8. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: The nanocrystalline soft magnetic alloy composition is Fe 72.8 Si 12.7 B 9.9 Cu 1.5 Nb1Al 0.52 Mn 0.8 Ga 0.8 .

9. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: The nanocrystalline soft magnetic alloy composition is Fe 73.1 Si 13 B 10.6 Cu 1.4 Nb 1.3 Mn 0.1 Ga 0.6 .

10. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: The nanocrystalline soft magnetic alloy composition is Fe 74 Cu1Nb2Si 15 B7P 0.7 Al 0.3 .

11. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: The Fe 74 Cu1Nb2Si 13 B8 1.9 Al 0.1 The alloy is obtained by cooling to 330-420°C after nanocrystallization, keeping the temperature and applying a magnetic field, and then cooling to room temperature.

12. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 11, characterized in that: The direction of the magnetic field is perpendicular to the belt axis, and the magnetic field magnitude is 500 to 1000 Oe.

13. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: The nanocrystalline soft magnetic alloy composition is Fe 74 Cu1Nb2Si 13 B8 1.9 Al 0.1 The alloy strip thickness is 14-16μm; the bandwidth is 65mm, and the loss at 0.5T and 10kHz is less than 2.3W / kg.

14. The method for synthesizing a high-frequency nanocrystalline alloy according to claim 1, characterized in that: Also included is a method for verifying the gold component: The ingredients are prepared according to the alloy composition, and the alloy ingot with uniform composition is obtained by smelting; the molten alloy is rapidly quenched to obtain an amorphous precursor strip; and the amorphous structure of the strip is detected; The precursor strip is placed in a furnace for heat treatment to obtain a nanocrystalline soft magnetic alloy, and the magnetic properties are tested.

15. A synthesis system of high-frequency nanocrystalline alloy, characterized in that: The system includes, A data set acquisition module for forming a data set based on amorphous forming ability, coercivity and characteristics; Alloy composition design criteria acquisition module, used to screen key features and obtain alloy composition design criteria through SHAP analysis; Design module, used to design nanocrystalline soft magnetic alloy composition in combination with XGBoost algorithm.

16. The synthesis system of high frequency nanocrystalline alloy according to claim 15, characterized in that: It also includes a verification module, which is used to verify the composition of the nanocrystalline soft magnetic alloy by the following method: preparing the materials according to the alloy composition and smelting to obtain an alloy ingot with uniform composition; rapidly quenching the molten alloy to obtain an amorphous precursor strip; and detecting the amorphous structure of the strip; placing the precursor strip in a furnace for heat treatment to obtain a nanocrystalline soft magnetic alloy, and testing the magnetic properties.

17. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps in the method for synthesizing a high-frequency nanocrystalline alloy as claimed in any one of claims 1 to 14.

18. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for synthesizing a high-frequency nanocrystalline alloy as claimed in any one of claims 1 to 14 is implemented.

Images