Design Method, Storage Medium and Equipment for Heat-Treatable Die Casting Aluminum Alloy of Al-Si-Mg-Cu

Abstract

The present invention relates to the technical field of die-casting aluminum alloys, and specifically relates to a design method, a storage medium, and a device for an Al-Si-Mg-Cu heat-treatment-free die-casting aluminum alloy. The method includes establishing a thermodynamic database of the Al-Si-Mg-Cu quaternary system at the Al-rich end; obtaining the solidification microstructure information of the Al-Si-Mg-Cu alloy; training a Gaussian regression model using data with corresponding input features and output features, and completing the training when R<supgt;2< / supgt> is greater than or equal to 0.9; screening out the optimal composition points within the preset alloy composition content range. The storage medium stores computer program instructions; the device includes at least one processor, at least one memory, and computer program instructions stored in the memory; when the computer program instructions are executed by the processor, the method is implemented. The present invention can quickly screen out the optimal composition points within the preset alloy composition content range, and accelerate the design of new high-performance heat-treatment-free die-casting aluminum alloys.

Description

Technical Field

[0001] The present invention relates to the technical field of die-cast aluminum alloys, and in particular to a design method, storage medium and equipment for an Al-Si-Mg-Cu heat-treatment-free die-cast aluminum alloy. Background Art

[0002] In automobile manufacturing, lightweighting has become an important direction for energy conservation and emission reduction. Aluminum alloys, with their excellent performance, low density, good processability, and cost-effectiveness, have become an ideal material for achieving lightweighting in automobiles. As the proportion of aluminum alloys used in automobiles increases, the difficulty of splicing body structural parts continues to increase, and the splicing efficiency is low. At the same time, automobiles have increasingly higher requirements for the ultimate tensile strength, yield strength, elongation, hardness, and corrosion resistance of aluminum alloy materials. When automobile structural parts collide or are subjected to stress, aluminum alloy materials need to have extremely high ultimate tensile strength to ensure safety; the yield strength of aluminum alloy materials needs to be high enough to avoid permanent deformation during the use of the car. Aluminum alloys with high yield strength can ensure that the car maintains its structural stability during normal driving and collisions. In order to prevent brittle fracture of automobile structural parts when they encounter impact, aluminum alloy materials need to have good elongation.

[0003] Traditional aluminum alloys have relatively low ultimate tensile strength and yield strength, making them difficult to meet the demands of high-strength, high-load automotive structural components. In particular, during a collision, traditional aluminum alloys may not effectively withstand external impact forces, compromising vehicle safety. Furthermore, traditional aluminum alloys have low elongation, making them prone to brittle fracture when subjected to stress. Their lack of toughness prevents them from effectively absorbing collision energy, reducing the vehicle's impact resistance. Therefore, traditional aluminum alloys are insufficient to meet the high-performance requirements of modern automotive structural components. Meeting these high-performance requirements requires optimizing alloy composition, improving processing techniques, and enhancing surface treatments.

[0004] Developing high-performance, heat-treatment-free die-cast aluminum alloys for integrated die-casting of body structural components can effectively overcome this bottleneck. Tesla has developed a new alloy by adding copper to an Al-Si-Mg-based alloy and applied it to the production of the heat-treatment-free, integrated die-cast rear floor of the Model Y, reducing the number of parts and overall vehicle weight.

[0005] However, the optimal addition amount of Cu in Al-Si-Mg-based alloys is difficult to determine. Furthermore, conventional methods for developing Cu-modified Al-Si-Mg alloys often suffer from low efficiency, high cost, and long design cycles in determining the optimal alloy composition. Therefore, it is urgent to develop a design method, storage medium, and equipment for Al-Si-Mg-Cu heat-treatment-free die-cast aluminum alloys by combining computational thermodynamics and active learning methods to accelerate the design of new high-performance heat-treatment-free die-cast aluminum alloys. Summary of the Invention

[0006] The object of the present invention is to provide a design method, a storage medium and a device for an Al-Si-Mg-Cu heat-treatable die-casting aluminum alloy. The specific technical solutions are as follows:

[0007] In a first aspect, the present invention provides a design method for an Al-Si-Mg-Cu heat-treatable die-casting aluminum alloy, comprising:

[0008] Step S1: Collect the thermodynamic data of pure elements, binary systems, ternary systems and quaternary systems in the Al-Si-Mg-Cu quaternary system at the Al-rich end according to existing literature, and establish a thermodynamic database for the Al-Si-Mg-Cu quaternary system at the Al-rich end for the obtained thermodynamic data;

[0009] Step S2: Based on the thermodynamic database, use the Scheil-Gulliver model to simulate the influence of different Cu addition amounts on the solidification structure of the Al-Si-Mg-Cu alloy, so as to obtain the solidification structure information of the Al-Si-Mg-Cu alloy;

[0010] Step S3: Use the solidification structure information as input features, and use the ultimate tensile strength, yield strength and elongation of the initial experimental performance data of the Al-Si-Mg-Cu alloy as output features; use the data corresponding to the input features and the output features to train a Gaussian regression model until the fitting coefficient of the Gaussian regression model to the initial experimental performance data and the predicted performance data reaches R 2 When it is greater than or equal to 0.9, the training is completed;

[0011] Step S4: Use the trained Gaussian regression model to make predictions within the range of the preset alloy composition content of yAl-8wt.%Si-0.4wt.%Mg-xCu, and obtain predicted performance data that changes with the increase of the Cu mass percentage and the decrease of the Al mass percentage; wherein, the value range of y is 90wt.%~91.6wt.%; the value range of x is 0~1.6wt.%; convert the predicted performance data into a comprehensive mechanical property factor Q DJR ; According to Q DJR And combine the maximum value of the EI value to screen out the best composition point within the range of the preset alloy composition content.

[0012] Optionally, if the maximum value of Q DJR of the alloy corresponding to the best composition point within its confidence interval is greater than the maximum value of Q DJR of the alloy corresponding to any other composition point within the range of the preset alloy composition content within its confidence interval, it indicates that the screening of the best composition point is successful;

[0013] If the Q of the alloy corresponding to the optimal composition point DJR is less than the maximum value of the Q of the alloy corresponding to any other composition point within the confidence interval of the alloy corresponding to the optimal composition point within the range of the preset alloy composition content, it indicates that the optimal composition point needs to be reselected. DJR If the maximum value within its confidence interval is less than the maximum value of the Q of the alloy corresponding to any other composition point within the confidence interval of the alloy corresponding to the optimal composition point within the range of the preset alloy composition content, it indicates that the optimal composition point needs to be reselected.

[0014] Optionally, when reselecting the optimal composition point, first add each of the measured data to the initial experimental performance data, then complete the training of the Gaussian regression model in combination with step S3, and finally, screen out the optimal composition point within the range of the preset alloy composition content by using step S4.

[0015] Optionally, the initial experimental performance data includes the measured data of the ultimate tensile strength, yield strength, and elongation of the alloys corresponding to 5 to 10 composition points selected within the range of the preset alloy composition content.

[0016] Optionally, during the process of training the Gaussian regression model, the kernel functions adopted by the Gaussian regression model include the kernel function for training the ultimate tensile strength, the kernel function for training the yield strength, and the kernel function for training the elongation.

[0017] Optionally, the obtained thermodynamic data is used to establish a thermodynamic database for the Al-Si-Mg-Cu quaternary system at the Al-rich end by using the Calphad method.

[0018] Optionally, the predicted performance data includes the ultimate tensile strength, yield strength, and elongation.

[0019] Optionally, the solidification structure information includes the (Al) phase structure information, (Si) phase structure information, Mg2Si phase structure information, Al2Cu phase structure information, and Q-Al5Cu2Mg8Si6 phase structure information.

[0020] In a second aspect, the present invention provides a computer storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the Al-Si-Mg-Cu heat-treatment-free die-casting aluminum alloy design method is implemented.

[0021] In a third aspect, the present invention provides an electronic device, including: at least one processor, at least one memory, and computer program instructions stored in the memory, and when the computer program instructions are executed by the processor, the Al-Si-Mg-Cu heat-treatment-free die-casting aluminum alloy design method is implemented.

[0022] Applying the technical solution of the present invention has at least the following beneficial effects:

[0023] (1) The design method of an Al-Si-Mg-Cu heat-treatable die-casting aluminum alloy provided by the present invention can quickly screen out the optimal composition points within the preset alloy composition content range, accelerating the design of new high-performance heat-treatable die-casting aluminum alloys. Specifically, according to the thermodynamic database of the Al-Si-Mg-Cu quaternary system at the Al-rich end, the Scheil-Gulliver model is used to simulate the influence of different Cu addition amounts on the solidification structure of the Al-Si-Mg-Cu alloy, thereby obtaining the solidification structure information of the Al-Si-Mg-Cu alloy; the solidification structure information is used as the input feature, and the ultimate tensile strength, yield strength, and elongation of the initial experimental performance data of the Al-Si-Mg-Cu alloy are used as the output features, and the Gaussian regression model is trained with the data corresponding to the input feature and the output feature; the trained Gaussian regression model is used to make predictions within the preset alloy composition content range of yAl-8wt.%Si-0.4wt.%Mg-xCu, and according to the change of Q DJR and in combination with the maximum value of the EI value, the optimal composition points within the preset alloy composition content range are quickly screened out. In addition, through experimental verification, the alloy corresponding to the optimal composition point has the best comprehensive mechanical properties, ensuring the accuracy and reliability of the design method. Therefore, the present invention can combine computational thermodynamics and active learning methods to shorten the development cycle of the optimal composition points of the Al-Si-Mg-Cu heat-treatable die-casting aluminum alloy, reduce the development cost, and effectively improve the comprehensive performance of the alloy, meeting the requirements of automotive lightweight and structural strength.

[0024] (2) When reselecting the optimal composition points in the present invention, first add each of the measured data to the initial experimental performance data, then complete the training of the Gaussian regression model in combination with step S3, and finally, use step S4 to screen out the optimal composition points within the preset alloy composition content range. Through this dynamic adjustment and optimization, it is ensured to screen out the optimal composition points within the preset alloy composition content range, so that the finally obtained Al-Si-Mg-Cu heat-treatable die-casting aluminum alloy has excellent mechanical properties and meets the high requirements in practical applications.

[0025] In addition to the purposes, features, and advantages described above, the present invention has other purposes, features, and advantages. The following will refer to the drawings for a further detailed description of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings forming a part of this application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0027] Figure 1It is a schematic flow chart of a design method for heat-treatable die-casting aluminum alloy of Al-Si-Mg-Cu in Example 1;

[0028] Figure 2 It is the comparison result between the calculated vertical section phase diagram of the quaternary alloy system of 70wt.%Al-0.2wt.%Si-0.16wt.%Mg-29.64wt.%Cu to 70wt.%Al-0.2wt.%Si-0.28wt.%Mg-29.52wt.%Cu calculated by the thermodynamic database in Example 1 and the experimental data;

[0029] Figure 3 It is the non-equilibrium solidification phase diagram of the preset alloy under different Cu contents in Example 1;

[0030] Figure 4 It is the solidification microstructure diagram of the preset alloy under different Cu contents in Example 1;

[0031] Figure 5 It is the prediction result of the Gaussian regression model for the preset alloy composition with different Cu contents in terms of ultimate tensile strength in Example 1;

[0032] Figure 6 It is the prediction result of the Gaussian regression model for the preset alloy composition with different Cu contents in terms of yield strength in Example 1;

[0033] Figure 7 It is the prediction result of the Gaussian regression model for the preset alloy composition with different Cu contents in terms of elongation in Example 1;

[0034] Figure 8 It is the calculation result of the comprehensive mechanical properties obtained by calculating the prediction performance data in Example 1;

[0035] Figure 9 It is to calculate the expected improvement EI value of the preset alloy composition with different Cu contents in Example 1;

[0036] Figure 10 It is the comparison chart between the experimental verification result of the best composition point with Cu content of 0.62wt.% in Example 1 and the mechanical properties of A356 alloy;

[0037] Figure 11 It is the prediction result of the Gaussian regression model for the preset alloy composition with different Cu contents in terms of ultimate tensile strength in Comparative Example 1;

[0038] Figure 12 It is the prediction result of the Gaussian regression model for the preset alloy composition with different Cu contents in terms of yield strength in Comparative Example 1;

[0039] Figure 13The prediction results of the Gaussian regression model in Comparative Example 1 for the preset alloy compositions with different Cu contents in terms of elongation;

[0040] Figure 14 The calculation results of the comprehensive mechanical properties obtained by calculating the prediction performance data in Comparative Example 1;

[0041] Figure 15 The expected improvement EI values calculated for the preset alloy compositions with different Cu contents in Comparative Example 1;

[0042] Among them, in Figures 5 - 8 and Figures 11 - 14 , the shaded areas near each curve are 95% confidence intervals; in Figures 5 - 8 and Figures 10 - 14 , UTS represents the ultimate tensile strength, YS represents the yield strength, and EL represents the elongation. Specific Embodiments

[0043] 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 belong to the scope of protection of the present invention. Embodiment 1:

[0044] Refer to Figure 1 , a design method for an Al-Si-Mg-Cu heat-treatable die-casting aluminum alloy, including:

[0045] Step S1: Collect the thermodynamic data of 4 pure elements (Al, Si, Mg, and Cu), 6 binary systems (Al-Si, Al-Mg, Al-Cu, Si-Mg, Si-Cu, and Mg-Cu), 4 ternary systems (Al-Si-Mg, Al-Si-Cu, Al-Mg-Cu, and Si-Mg-Cu), and 1 quaternary system (Al-Si-Mg-Cu) in the Al-Si-Mg-Cu quaternary system at the Al-rich end according to existing literature, and establish a thermodynamic database for the Al-Si-Mg-Cu quaternary system at the Al-rich end by using the Calphad method for the obtained thermodynamic data; among them, the Al-rich end defined in this Embodiment 1 means that the Al-Si-Mg-Cu quaternary system has a high mass percentage of Al, and the mass percentage of Al is 90 wt.% to 91.6 wt.%;

[0046] Specifically, the thermodynamic data of pure elements Al, Si, Mg, and Cu are from existing literature: DINSDALE A T. SGTE data for pure elements[J]. Calphad, 1991, 15(4): 317-425;

[0047] The thermodynamic data of the binary systems Al-Si, Al-Mg, Si-Mg, and the ternary system Al-Si-Mg are from existing literature: TANG Y, DU Y, ZHANG L, et al. Thermodynamic description of the Al-Mg-Si system using a new formulation for the temperature dependence of the excess Gibbs energy[J]. Thermochimica Acta, 2012, 527: 131-142;

[0048] The thermodynamic data of the binary system Al-Cu are from existing literature: LIANG S-M, SCHMID-FETZER R. Thermodynamic assessment of the Al-Cu-Zn system, part II: Al-Cu binary system[J]. Calphad, 2015, 51: 252-260;

[0049] The thermodynamic data of the binary system Si-Cu and the ternary system Al-Si-Cu are from existing literature: HALLSTEDT B, GRÖBNER J, HAMPL M, et al. Calorimetric measurements and assessment of the binary Cu-Si and ternary Al-Cu-Si phase diagrams[J]. Calphad, 2016, 53: 25-38;

[0050] The thermodynamic data of the binary system Mg-Cu and the ternary system Al-Mg-Cu are from the existing literature: BUHLER T, FRIESS G, SPENCER P J, et al. A thermodynamic assessment of the Al-Cu-Mg ternary system[J]. Journal of Phase Equilibria, 1998, 19(4): 317-333;

[0051] The thermodynamic data of the ternary system Si-Mg-Cu are from the existing literature: ZHAO J, ZHOU J, LIU S, et al. Phase diagram determination and thermodynamic modeling of the Cu-Mg-Si system[J]. Journal of Mining and Metallurgy, Section B: Metallurgy, 2016, 52(1): 99-112;

[0052] The thermodynamic data of the Q-Al5Cu2Mg8Si6 phase in the quaternary system Al-Si-Mg-Cu are from the existing literature: PAN X, MORRAL J E, BRODY H D. Predicting the Q-phase in Al-Cu-Mg-Si alloys[J]. Journal of Phase Equilibria and Diffusion, 2010, 31(2): 144-148;

[0053] The comparison between the calculated vertical section phase diagram (mass percentage, %) of the quaternary alloy system from 70wt.%Al-0.2wt.%Si-0.16wt.%Mg-29.64wt.%Cu to 70wt.%Al-0.2wt.%Si-0.28wt.%Mg-29.52wt.%Cu and the experimental data is calculated using the said thermodynamic database as Figure 2 shown (due to a large amount of data, only part of the results are shown here), which Figure 2 indicates that the experimental data is basically in agreement with the calculated results, demonstrating the reliability of the said thermodynamic database.

[0054] Step S2: Based on the said thermodynamic database, the Scheil-Gulliver model (from Pandat software) is used to simulate the influence of different Cu addition amounts on the solidification microstructure of the Al-Si-Mg-Cu alloy, so as to obtain the solidification microstructure information of the Al-Si-Mg-Cu alloy;

[0055] Specifically, the Scheil-Gulliver model in Pandat software was used to simulate the solidification behavior of the preset alloy of yAl-8wt.%Si-0.4wt.%Mg-xCu at several composition points within the range of Cu content (i.e., mass percentage) from 0 to 1.6wt.%, and the non-equilibrium solidification phase diagram of the preset alloy was constructed, as Figure 3 shown; wherein, the value range of y is 90wt.% to 91.6wt.%; the value range of x is 0 to 1.6wt.%; within the range of the preset alloy composition content, the mass percentages of Mg and Si remain unchanged, the mass percentage of Cu increases (the specific increase range is 0 to 1.6wt.%), and the mass percentage of Al decreases (the specific decrease range is 91.6wt.% to 90wt.%). It can be seen from Figure 3 this that the Cu content significantly affects the solidification path of the preset alloy: when the Cu content is less than 0.61wt.%, with the decrease in temperature, there are simultaneously ternary eutectic reactions Liquid→(Al)+(Si)+Mg2Si and Liquid→(Al)+(Si)+Q-Al5Cu2Mg8Si6 in the solidification path of the preset alloy. When the Cu content is higher than 0.61wt.%, the ternary eutectic reaction Liquid→(Al)+(Si)+Mg2Si in the preset alloy completely disappears, and only the ternary eutectic reaction Liquid→(Al)+(Si)+Q-Al5Cu2Mg8Si6 exists, and the Mg2Si phase in the alloy is completely replaced by the Q-Al5Cu2Mg8Si6 phase.

[0056] Figure 4 is the solidification microstructure diagram of the preset alloy under different Cu contents. It can be seen from Figure 4It can be seen that the Cu content has a significant impact on the solidification structure of the preset alloy. As the Cu content increases, the content of the (Si) phase in the preset alloy slightly decreases, and the content of the (Al) phase basically remains stable. As the Cu content increases, the content of the (Al) phase remains stable, indicating that the Cu element has no significant inhibitory effect on the formation of the (Al) phase. The solubility of the Cu element is relatively low, so it will not have an obvious impact on the stability of the (Al) phase. The content of the (Si) phase decreases slightly, possibly because the Cu element reacts with the Si element to form eutectic or hypoeutectic reactions, resulting in the conversion of some Si into other compounds. In aluminum alloys, the Si element usually forms a eutectic structure with the Al matrix. Therefore, although the Cu element is added, the (Si) phase still remains relatively stable, and its content only decreases slightly. For the Mg2Si phase, its content decreases as the Cu content increases and completely disappears when the Cu content is 0.61 wt.%. For the Q-Al5Cu2Mg8Si6 phase, when the Cu content is less than 0.61 wt.%, its content continuously increases as the Cu content increases; when the Cu content is greater than 0.61 wt.%, the content of the Q-Al5Cu2Mg8Si6 phase tends to be stable. This phenomenon can be explained by the interaction between the preset alloy elements: when the Cu content is low, the Mg2Si phase in the preset alloy is relatively stable. As the Cu content increases, Cu reacts with Mg and Si to form a new metal compound, the Q-Al5Cu2Mg8Si6 phase; in addition, the Cu element affects the solid solution structure of the preset alloy, restricting the further combination of Mg and Si to form the Mg2Si phase; when the Cu content is greater than 0.61 wt.%, the content of the Q-Al5Cu2Mg8Si6 phase tends to be stable. When the Cu content is high, there are not enough Mg atoms in the preset alloy to continue to form the Q-Al5Cu2Mg8Si6 phase, so the phase fraction of the Q-Al5Cu2Mg8Si6 phase no longer increases significantly.

[0057] Step S3: Use the solidification structure information as the input feature, where the solidification structure information includes (Al) phase structure information, (Si) phase structure information, Mg2Si phase structure information, Al2Cu phase structure information, and Q-Al5Cu2Mg8Si6 phase structure information; use the ultimate tensile strength, yield strength, and elongation of the initial experimental performance data of the Al-Si-Mg-Cu alloy as the output features; use the data corresponding to the input features and the output features to train a Gaussian regression model until the fitting coefficient of the Gaussian regression model for the initial experimental performance data and the predicted performance data reaches R 2 greater than or equal to 0.9, and the training is completed; the R of the ultimate tensile strength, yield strength, and elongation in this Example 1 2They are respectively: 0.9638706913760833, 0.9914384871024077, 0.9864146081641261; During the training of the Gaussian regression model, the kernel function and hyperparameters adopted by the Gaussian regression model are shown in Table 1.

[0058] Table 1 Kernel function and hyperparameters of the Gaussian regression model used for each output feature in Example 1

[0059]

[0060] Step S4: Use the trained Gaussian regression model to make predictions within the preset alloy composition content range to obtain prediction performance data that changes with the increase of the Cu mass percentage and the decrease of the Al mass percentage; the prediction performance data includes ultimate tensile strength, yield strength, and elongation; convert the prediction performance data into a comprehensive mechanical property factor Q DJR ; According to the change of Q DJR and combine the maximum value of the EI value to screen out the best composition point within the preset alloy composition content range.

[0061] If the maximum value of Q DJR of the alloy corresponding to the best composition point within its confidence interval is greater than the maximum value of Q DJR of the alloy corresponding to any other composition point within the preset alloy composition content range within its confidence interval, it indicates that the screening of the best composition point is successful;

[0062] If the maximum value of Q DJR of the alloy corresponding to the best composition point within its confidence interval is less than the maximum value of Q DJR of the alloy corresponding to any other composition point within the preset alloy composition content range within its confidence interval, it indicates that the best composition point needs to be reselected.

[0063] When reselecting the best composition point, first add each of the measured data to the initial experimental performance data, then complete the training of the Gaussian regression model in combination with step S3, and finally, use step S4 to screen out the best composition point within the preset alloy composition content range.

[0064] The initial experimental performance data includes the measured data of the ultimate tensile strength, yield strength, and elongation of the alloys corresponding to 7 composition points selected within the range of the preset alloy composition content. Specifically, high-purity Al, Si, Mg, and Cu elemental substances with a purity of 99.99 wt.% were used as raw materials, and seven samples with different Cu contents numbered A1 - A7 were designed, as shown in Table 2. The total mass of all raw materials was designed to be 75 g and weighed using an electronic balance of model AUY120. Subsequently, alloy samples were prepared by melting in a vacuum melting furnace of model CXZG - 0.5. During the melting process, high-purity argon gas was used as the protective gas to prevent the influence of impurity gases on the quality of the samples. The melting parameters used were from the existing literature: ZHANG S, YI W, ZHONG J, et al. Computer alloy design of Ti modified Al - Si - Mg - Sr casting alloys for achieving simultaneous enhancement in strengthand ductility[J]. Materials, 2023, 16(1): 306.

[0065] Powder samples were prepared from the alloy samples using a diamond file. The mass of each powder sample was 0.2 g. The composition of the alloy samples was analyzed using inductively coupled plasma mass spectrometry (ICP - MS) and chemical analysis (CA) methods. Some of the results are shown in Table 3. Subsequently, tensile specimens for mechanical property testing were prepared from the alloy samples using a wire cutting machine of model DK7725. Three tensile specimens were prepared for each alloy sample, resulting in a total of 21 tensile specimens. Subsequently, the surfaces of the tensile specimens were polished successively with metallographic sandpapers of 240 mesh, 400 mesh, 600 mesh, 800 mesh, 1500 mesh, and 2000 mesh to remove the oxide layer, oil stain, and microcracks on the surfaces of the tensile specimens. Finally, the mechanical properties of each tensile specimen were tested using a universal testing machine of model America instron - 3369. The test results are shown in Table 4. Among them, the ultimate tensile strength, yield strength, and elongation were tested in accordance with GB / T 228.1 - 2021 "Metallic materials - Tensile testing - Part 1: Method of test at room temperature".

[0066] Table 2 Seven samples numbered A1 - A7 with different Cu contents

[0067]

[0068] Table 3 Partial analysis results of the composition of alloy samples

[0069]

[0070] Table 4 Mechanical properties of each tensile part

[0071]

[0072] In step S4, the preset alloy compositions with different Cu contents are predicted by using the Gaussian regression model after completion of training, and the predicted performance data as shown in Figures 5 - 7 are obtained; in addition, the data in Table 4 are marked in Figures 5 - 7 . As can be seen from Figures 5 - 7 , the predicted points are in complete agreement with the experimental points, and the confidence interval can well include the error values of the experimental points, indicating that the Gaussian regression model after completion of training has good prediction accuracy.

[0073] The comprehensive mechanical property factor Q DJR =UTS + YS • log 10 (EL) is used to convert the multi-objectives (i.e., UTS, YS, EL) into a single objective representing the comprehensive mechanical properties, so as to facilitate efficient global design. The specific conversion results are shown in Figure 8 . Among them, the comprehensive mechanical property factor Q DJR is derived from the existing literature: GAO J, ZHONG J, LIU G, et al. Accelerated discovery of high-performance Al-Si-Mg-Sc casting alloys by integrating active learning with high-throughput CALPHAD calculations[J]. Science and Technology of Advanced Materials, 2023, 24(1): 2196242. The value of the calculation expected improvement function (i.e., Expected Improvement, EI) at the best composition point within the range of the preset alloy composition content is calculated, and the calculation results are shown in Figure 9 . Among them, the expected improvement function is derived from the existing literature: GAO J, ZHONG J, LIU G, et al. Accelerated discovery of high-performance Al-Si-Mg-Sc casting alloys by integrating active learning with high-throughput CALPHAD calculations[J]. Science and Technology of Advanced Materials, 2023, 24(1): 2196242. According to QDJR The variation of [the relevant parameter] is analyzed, and the optimal composition point within the range of the preset alloy composition content is selected by combining with the maximum value of the EI value. Specifically, the optimal composition point is 90.98 wt.% Al - 8 wt.% Si - 0.4 wt.% Mg - 0.62 wt.% Cu. At this time, Q DJR = 390.21394 ± 15.57331 MPa, and the maximum value of Q DJR is 405.78725 MPa.

[0074] Using the method for preparing alloy samples and the method for mechanical property testing in the initial experimental performance data, the measured mechanical property data corresponding to the optimal composition point of 90.98 wt.% Al - 8 wt.% Si - 0.4 wt.% Mg - 0.62 wt.% Cu are obtained. The results are shown in Figure 10 the new alloy in [the relevant reference] and Table 5; among them, in Figure 10 the mechanical properties of A356 alloy are also shown, and these mechanical properties are measured by using the mechanical property testing method in the initial experimental performance data; in Table 5, the measured mechanical property data corresponding to the composition point of 90.9 wt.% Al - 8 wt.% Si - 0.4 wt.% Mg - 0.7 wt.% Cu are also provided by using the method for preparing alloy samples and the method for mechanical property testing in the initial experimental performance data. In addition, the data in Table 5 are marked in Figures 5 - 8 [the relevant figure].

[0075] Table 5 Experimental verification results of the preset alloy under different Cu contents

[0076]

[0077] From Table 5 and Figures 5 - 8 [the relevant reference], it can be seen that the experimental verification results at the two composition points with Cu contents of 0.62 wt.% and 0.7 wt.% are consistent with the predicted performance data, and the error is negligible. This shows that the Gaussian regression model after training has good prediction accuracy. Therefore, the optimal composition alloy designed by the present invention within the range of the preset alloy composition content of yAl - 8 wt.% Si - 0.4 wt.% Mg - xCu is: 90.98 wt.% Al - 8 wt.% Si - 0.4 wt.% Mg - 0.62 wt.% Cu.

[0078] Referring to Figure 10 [the relevant figure], it can be seen that the experimental verification result at the optimal composition point with a Cu content of 0.62 wt.% is significantly better than the mechanical properties of A356 alloy.

[0079] Comparative Example 1:

[0080] Different from Example 1, when training the Gaussian regression model in step S3, the preset alloy composition content change is used as the input feature. Among them, the mass percentages of Mg and Si remain unchanged, the mass percentage of Cu increases, and the specific increase range is 0 to 1.6 wt.%, and the mass percentage of Al decreases, and the specific decrease range is 91.6 wt.% to 90 wt.%.

[0081] The Gaussian regression model is trained using the data corresponding to the input feature and the output feature. During the process of training the Gaussian regression model, the kernel function and hyperparameters used by the Gaussian regression model are shown in Table 6.

[0082] Table 6 Kernel function and hyperparameters of the Gaussian regression model used for each output feature in Comparative Example 1

[0083]

[0084] The R values of the ultimate tensile strength, yield strength, and elongation of this Comparative Example 1 2 are 0.6128910488100194, 0.8055718322044677, and 0.6580101273505832 respectively; it can be seen that R 2 are all less than 0.9, and it is preliminarily judged that the Gaussian regression model after training in this Comparative Example 1 is not worthy of being adopted.

[0085] Furthermore, the preset alloy composition with different Cu contents is predicted using the Gaussian regression model after training in this Comparative Example 1, and the prediction performance data as follows Figures 11 - 13 is obtained; in addition, the data in Table 2 is marked in Figures 11 - 13 . It can be seen from Figures 11 - 13 that the prediction points and the experimental points do not completely match, and there are large errors at Cu contents of 0, 0.5 wt.%, and 1.5 wt.%, and the confidence interval cannot well include the error values of the experimental points, indicating that the prediction accuracy of the Gaussian regression model after training is poor.

[0086] The comprehensive mechanical property factor Q DJR =UTS + YS•log 10 (EL) is used to convert the multi-objective mechanical properties (i.e., UTS, YS, EL) into a single objective representing the comprehensive mechanical properties, so as to facilitate efficient global design. The specific conversion results can be seen in Figure 14 . The expected improvement function (i.e., Expected Improvement, EI) is used to determine the best composition point within the range of the preset alloy composition content. The calculation results can be seen in Figure 15 . According to Q DJRThe change situation is combined with the maximum value of the EI value to screen out the optimal composition point within the range of the preset alloy composition content. Specifically, the optimal composition point is 90 wt.% Al - 8 wt.% Si - 0.4 wt.% Mg - 1.6 wt.% Cu. At this time, Q DJR The prediction result of Q cannot well describe the initial experimental performance data, especially at 0.5 wt.% Cu DJR The prediction result deviates seriously from the initial experimental performance data, further verifying that the result of using the change of the preset alloy composition content as the input feature in Comparative Example 1 is not worthy of consideration.

[0087] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A design method for heat-treatable die-casting aluminum alloy of Al-Si-Mg-Cu, characterized in that, Including: Step S1: Collect the thermodynamic data of pure elements, binary systems, ternary systems, and quaternary systems in the Al-Si-Mg-Cu quaternary system at the Al-rich end according to existing literature, and establish a thermodynamic database for the Al-Si-Mg-Cu quaternary system at the Al-rich end based on the obtained thermodynamic data; Step S2: Based on the thermodynamic database, use the Scheil-Gulliver model to simulate the influence of different Cu addition amounts on the solidification microstructure of the Al-Si-Mg-Cu alloy, so as to obtain the solidification microstructure information of the Al-Si-Mg-Cu alloy; Step S3: Use the solidification structure information as the input feature, and use the ultimate tensile strength, yield strength, and elongation of the initial experimental performance data of the Al-Si-Mg-Cu alloy as the output features; use the data corresponding to the input feature and the output feature to train a Gaussian regression model until the fitting coefficient R 2 is greater than or equal to 0.9, then the training is completed; Step S4: Use the trained Gaussian regression model to make predictions within the range of the preset alloy composition of yAl-8wt.%Si-0.4wt.%Mg-xCu, and obtain prediction performance data that changes with the increase in the mass percentage of Cu and the decrease in the mass percentage of Al; wherein, the value range of y is 90wt.% to 91.6wt.%; the value range of x is 0 to 1.6wt.%; Convert the prediction performance data into a comprehensive mechanical property factor Q DJR ; According to Q DJR 's change situation, and combine the maximum value of the EI value to screen out the best composition point within the range of the preset alloy composition; EI represents the expected improvement function.

2. The design method of the heat-treatment-free die-casting aluminum alloy Al-Si-Mg-Cu according to claim 1, characterized in that, If the Q of the alloy corresponding to the optimal composition point DJR The maximum value within its confidence interval is greater than the Q of the alloy corresponding to any other composition point within the range of the preset alloy composition content DJR The maximum value within its confidence interval indicates that the screening of the optimal composition point is successful; If the Q of the alloy corresponding to the optimal composition point DJR is less than the maximum value of the Q of the alloy corresponding to any other composition point within the confidence interval of the alloy corresponding to the optimal composition point DJR within its confidence interval, it indicates that the optimal composition point needs to be reselected.

3. The design method of the heat-treatable die-casting aluminum alloy Al-Si-Mg-Cu according to claim 2, characterized in that, When reselecting the optimal composition point, first add each measured data to the initial experimental performance data, then complete the training of the Gaussian regression model in combination with Step S3, and finally, use Step S4 to screen out the optimal composition point within the range of the preset alloy composition content.

4. The design method of the heat-treatable die-casting aluminum alloy Al-Si-Mg-Cu according to claim 2, characterized in that, The initial experimental performance data includes the measured data of the ultimate tensile strength, yield strength, and elongation of the alloys corresponding to 5 to 10 composition points selected within the range of the preset alloy composition content.

5. The design method of the heat-treatable die-casting aluminum alloy Al-Si-Mg-Cu according to claim 1, characterized in that During the process of training the Gaussian regression model, the kernel functions adopted by the Gaussian regression model include the kernel function for training the ultimate tensile strength, the kernel function for training the yield strength, and the kernel function for training the elongation.

6. The design method of the heat-treatment-free die-casting aluminum alloy of Al-Si-Mg-Cu according to claim 1, wherein Use the Calphad method to establish a thermodynamic database for the Al-Si-Mg-Cu quaternary system at the Al-rich end based on the obtained thermodynamic data.

7. The design method of the heat-treatment-free die-casting aluminum alloy of Al-Si-Mg-Cu according to claim 1, characterized in that, The predicted performance data includes the ultimate tensile strength, yield strength, and elongation.

8. The design method of the heat-treatable die-casting aluminum alloy Al-Si-Mg-Cu according to claim 1, wherein, The solidification microstructure information includes the Al-phase microstructure information, Si-phase microstructure information, Mg2Si-phase microstructure information, Al2Cu-phase microstructure information, and Q-Al5Cu2Mg8Si6-phase microstructure information.

9. A computer storage medium, characterized in that, It stores computer program instructions, and when the computer program instructions are executed by a processor, it realizes the Al-Si-Mg-Cu heat-treatment-free die-casting aluminum alloy design method described in any one of claims 1 to 8.

10. An electronic device, characterized in that, Including: At least one processor, at least one memory, and computer program instructions stored in the memory, and when the computer program instructions are executed by the processor, it realizes the Al-Si-Mg-Cu heat-treatment-free die-casting aluminum alloy design method described in any one of claims 1 to 8.

Images