CN116913404A - Machine learning-based integral die-casting heat treatment-free aluminum alloy component design method - Google Patents
Machine learning-based integral die-casting heat treatment-free aluminum alloy component design method Download PDFInfo
- Publication number
- CN116913404A CN116913404A CN202310875231.6A CN202310875231A CN116913404A CN 116913404 A CN116913404 A CN 116913404A CN 202310875231 A CN202310875231 A CN 202310875231A CN 116913404 A CN116913404 A CN 116913404A
- Authority
- CN
- China
- Prior art keywords
- casting
- performance
- aluminum alloy
- machine learning
- die
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004512 die casting Methods 0.000 title claims abstract description 79
- 229910000838 Al alloy Inorganic materials 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000010801 machine learning Methods 0.000 title claims abstract description 46
- 238000013461 design Methods 0.000 title claims abstract description 20
- 238000005266 casting Methods 0.000 claims description 65
- 239000000956 alloy Substances 0.000 claims description 44
- 229910045601 alloy Inorganic materials 0.000 claims description 37
- 238000005336 cracking Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 23
- 230000035945 sensitivity Effects 0.000 claims description 17
- 238000010438 heat treatment Methods 0.000 claims description 14
- 238000004519 manufacturing process Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 14
- 239000000463 material Substances 0.000 claims description 10
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 8
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 8
- 229910052710 silicon Inorganic materials 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 230000002068 genetic effect Effects 0.000 claims description 7
- 229910052720 vanadium Inorganic materials 0.000 claims description 7
- 229910052684 Cerium Inorganic materials 0.000 claims description 4
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 4
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 claims description 4
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 claims description 4
- RTAQQCXQSZGOHL-UHFFFAOYSA-N Titanium Chemical compound [Ti] RTAQQCXQSZGOHL-UHFFFAOYSA-N 0.000 claims description 4
- GWXLDORMOJMVQZ-UHFFFAOYSA-N cerium Chemical compound [Ce] GWXLDORMOJMVQZ-UHFFFAOYSA-N 0.000 claims description 4
- 239000010949 copper Substances 0.000 claims description 4
- 229910052802 copper Inorganic materials 0.000 claims description 4
- 230000007547 defect Effects 0.000 claims description 4
- 229910052742 iron Inorganic materials 0.000 claims description 4
- 229910052746 lanthanum Inorganic materials 0.000 claims description 4
- FZLIPJUXYLNCLC-UHFFFAOYSA-N lanthanum atom Chemical compound [La] FZLIPJUXYLNCLC-UHFFFAOYSA-N 0.000 claims description 4
- 239000011777 magnesium Substances 0.000 claims description 4
- 229910052749 magnesium Inorganic materials 0.000 claims description 4
- 229910052759 nickel Inorganic materials 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 239000010703 silicon Substances 0.000 claims description 4
- 229910052712 strontium Inorganic materials 0.000 claims description 4
- CIOAGBVUUVVLOB-UHFFFAOYSA-N strontium atom Chemical compound [Sr] CIOAGBVUUVVLOB-UHFFFAOYSA-N 0.000 claims description 4
- 239000010936 titanium Substances 0.000 claims description 4
- 229910052719 titanium Inorganic materials 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- LEONUFNNVUYDNQ-UHFFFAOYSA-N vanadium atom Chemical compound [V] LEONUFNNVUYDNQ-UHFFFAOYSA-N 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 2
- 238000013178 mathematical model Methods 0.000 abstract description 2
- 230000004044 response Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000004227 thermal cracking Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000000465 moulding Methods 0.000 description 4
- 230000000052 comparative effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003754 machining Methods 0.000 description 3
- 229910052761 rare earth metal Inorganic materials 0.000 description 3
- 150000002910 rare earth metals Chemical class 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000003466 welding Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 239000007791 liquid phase Substances 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 239000007769 metal material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000007711 solidification Methods 0.000 description 2
- 230000008023 solidification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000008646 thermal stress Effects 0.000 description 2
- 229910000714 At alloy Inorganic materials 0.000 description 1
- 238000003723 Smelting Methods 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005495 investment casting Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 229910001338 liquidmetal Inorganic materials 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000006104 solid solution Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013585 weight reducing agent Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Crystallography & Structural Chemistry (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Molds, Cores, And Manufacturing Methods Thereof (AREA)
Abstract
The invention discloses a machine learning-based integral die-casting heat treatment-free aluminum alloy component design method, which utilizes a machine learning algorithm to establish a machine learning mathematical model for the relation between various components of an aluminum alloy and the required performance of an integral heat treatment-free die casting, and realizes the component design of the integral die-casting aluminum alloy through optimizing the components, thereby achieving the aims of being suitable for integral die casting and heat treatment-free and meeting certain mechanical properties and structural strength.
Description
Technical Field
The invention relates to the field of integrated die casting, in particular to a machine learning-based integrated die casting heat treatment-free aluminum alloy component design method.
Background
The aluminum alloy has a series of advantages of light weight, high strength, good plasticity, good corrosion resistance and the like, and has become one of important materials widely applied to various fields of aviation, automobiles, buildings, electronics and the like. Integrated die casting is an advanced manufacturing technique integrating casting and processing, and by casting once and solidifying and molding under high pressure, lighter and stronger parts can be manufactured, so that it has been used in some industries such as automobile manufacturing and aerospace in recent years. In the field of automobiles, the integrated die casting can manufacture large complex structural parts, one part can replace tens or hundreds of parts, and the manufacturing process flow of the automobile body is remarkably simplified. The integrated die casting process replaces the component stamping and welding links of the traditional vehicle body structural part, taking Tesla as an example, the new generation of full-die casting chassis can reduce 370 parts, the vehicle door and the front and rear cover structural parts can also be die cast by the same process, the number of parts is greatly reduced, and the manufacturing flow of the vehicle body is greatly simplified. Therefore, compared with the metal materials manufactured by the traditional casting and machining modes, the aluminum alloy casting manufactured by the integrated die casting has the advantages of high precision, high strength, simple process, cost saving and the like.
At present, cast parts in the automotive field are mostly manufactured by adopting commercial cast alloys such as A356, A357 and the like, for example, conventional chassis components such as hubs, steering knuckles, control arms and the like, and after casting and machining treatment, the cast parts can be used only by further regulating and controlling T6 heat treatment. However, integrally die-cast parts are typically large in size and are often in the form of thin-shell parts. In order to maintain the dimensional accuracy and prevent the deformation of the parts, the integral die-casting parts cannot be subjected to the structure property regulation and control through a heat treatment process. Meanwhile, the forming difficulty of the integrated die casting is obviously higher than that of the conventional die casting process. Therefore, the existing commercial cast aluminum alloy is difficult to be suitable for an integrated die casting process, and the castability and the mechanical properties of parts cannot meet the existing requirements. For the process characteristics of integrated die casting, aluminum alloys are required to have not only excellent casting fluidity but also high mechanical properties of cast components without heat treatment.
At present, related vehicle enterprises and scientific research institutions conduct related research work aiming at alloy component design of integrated die casting, and alloy components are optimized mainly through experience. The existing integral die-casting aluminum alloy components are mainly prepared by adding or changing other metal element components and adopting an experimental method, wherein the added main elements are silicon, magnesium, copper, iron and the like, and rare earth alloys such as titanium, strontium, vanadium, nickel, lanthanum, cerium and the like, and the patent CN 116083762A discloses a die-casting aluminum alloy material suitable for the integral die-casting aluminum alloy material. In the production process, due to the influence of various factors such as smelting, casting, cooling speed and the like, the structure and structure of the aluminum alloy material are not uniform enough, so that the mechanical property, physical property, chemical property and the like of the aluminum alloy part are problematic. In order to improve the structure and texture of the aluminum alloy material and to improve its mechanical properties and durability, heat treatment is required. The performance and the like of the parts manufactured by the existing aluminum alloy materials through integrated die casting cannot meet the requirements, and the performance of castings can be improved to a certain extent by adopting a heat treatment process, but dimensional deformation is easily caused for large-size or thin-wall components. Further, as disclosed in Chinese patent publication No. CN113642121A, an optimization method of casting process parameters of the aluminum alloy brake caliper based on a response surface design and a multi-objective evolutionary algorithm is disclosed, and a response surface test is constructed by determining test variables and optimizing objectives; obtaining a response value through a casting numerical simulation test, and establishing a plurality of response surface models reflecting the input and output relation; and optimizing and solving the response surface model through a multi-objective evolutionary algorithm to obtain the optimal technological parameters. However, the invention still has the following problems: the patent selects a casting numerical simulation test to obtain a response value, establishes a plurality of response surface models for reflecting the relation between input and output, and cannot realize high-precision prediction simulation in the basic principle. And as for the obtaining method, the determining method and the casting process of the casting process parameters of the high-temperature alloy in CN115171815A, the known casting process parameters of the known high-temperature alloy are obtained by grabbing the casting process parameters of the high-temperature alloy in the known literature through python, but the learning ability of the known casting process parameters is insufficient, and the requirement of the integral die-casting heat-treatment-free aluminum alloy component design cannot be met.
Summarizing the drawbacks of the prior art are: (1) Because of the different thermal fluidity, hot cracking tendency and the like of the aluminum alloys with different components, the cast workpiece produced by integral casting is easy to generate defects such as insufficient casting, hot cracking, air holes, shrinkage holes and the like; (2) The alloy design of the integrated casting at the present stage mostly adopts experience design, has no universality and cannot be designed according to the specific casting performance requirement; (3) The integrated casting aluminum alloy at the present stage cannot accurately align the performance parameters and the performance characteristics of the finished casting product required in the integrated die casting process; (4) The castings produced by the integrated casting are deformed after heat treatment, and the performances of the castings are affected; (5) The design method of the integrated die-casting aluminum alloy at the present stage is time-consuming, consumable and low in efficiency.
Disclosure of Invention
The present invention aims to solve the following problems: and the machine learning method is utilized to design alloy components of the integrated die-casting heat treatment-free aluminum alloy, so that the integrated die-casting part has good casting performance and mechanical property.
The invention provides a machine learning-based integral die-casting heat treatment-free aluminum alloy component design method. The specific implementation method of the heat treatment-free aluminum alloy component design for integral die casting and casting based on machine learning is as follows:
step one: determining component selection standards of the integrated die-casting aluminum alloy: selecting alloy elements influencing casting performance and parameters influencing casting performance and mechanical performance of the integrated die-casting part;
step two: establishing a data set according to known integral die-casting aluminum alloy composition data and corresponding data such as thermal fluidity, crack sensitivity, shrinkage, ultimate tensile strength, yield strength, elongation at break and the like;
step three: establishing a machine learning model of the performance parameters required by the integral die casting process, the performance parameters free of heat treatment and the aluminum alloy components, and verifying the accuracy of the machine learning model;
step four: inputting the parameters of the performance requirements of the die casting process and the performance requirements of the finished products of the castings, which are calculated by pushing the integrated die castings with different sizes, into a machine learning model to obtain alloy components and contents meeting the requirements;
step five: carrying out experimental verification on the related performances of fluidity, hot cracking tendency, hot cracking sensitivity and shrinkage by using the components and the contents of the aluminum alloy obtained in the step four;
step six: the integrated die casting is manufactured by using the qualified alloy, and experimental verification is carried out on manufacturing performance and finished product performance, so that the integrated die casting meets the requirements for actual production.
The specific implementation method of the first step is as follows:
s11, selecting performance parameters which influence the integral die casting process, including fluidity, hot cracking tendency, hot cracking sensitivity and shrinkage rate;
s12, selecting heat treatment-free performance parameters of a casting finished product, wherein the heat treatment-free performance parameters comprise ultimate tensile strength, yield strength, elongation at break and elastic modulus;
s13, selecting components which influence the performance of the material, including silicon, magnesium, copper, iron and the like, and rare earth alloys such as titanium, strontium, vanadium, nickel, lanthanum, cerium and the like;
the specific implementation method of the second step is as follows:
s21, establishing an aluminum alloy component type data set according to the die-casting aluminum alloy materials in the existing research;
s22, establishing a unified performance parameter data set according to the performance parameters which are selected in the step one and affect the integrated die casting process and the finished product and are free from heat treatment in the prior study;
s23, integrating the two data sets, establishing a data set with the aluminum alloy component types and contents corresponding to the relevant performances, and providing data support for the data preprocessing and machine learning of the next step.
The specific implementation method of the third step is as follows:
s31, respectively preprocessing the known integral die-casting aluminum alloy composition data obtained in the second step and corresponding data such as thermal fluidity, thermal cracking sensitivity, shrinkage, ultimate tensile strength, yield strength, elongation at break, casting elongation and the like;
s32, a second generation non-inferior sorting genetic algorithm (NSGA-II) is selected to establish a machine learning model, and the algorithm has unique operation advantages and application conditions. Compared with the first generation non-inferior sorting genetic algorithm, the second generation has stronger exploration performance, can screen and reject the population more accurately when calculating, can not miss the individuals in the good front stage, and has more comprehensive and reasonable calculated quantity and range;
s33, training a machine learning model by using the preprocessed aluminum alloy performance data set and the component data set of the corresponding aluminum alloy;
s34, predicting test set data by using the trained machine learning model, comparing a prediction result with known data, detecting feasibility and accuracy of the machine learning model, and carrying out parameter correction on the machine learning model until the required precision requirement is met;
the target performance is input as input data into the trained model to obtain the initial design components.
The specific implementation method of the fourth step is as follows:
s41, calculating the performance parameter requirements of complete mold filling and no defects according to the size and thickness of the casting;
s42, calculating the performance parameter requirements of the finished casting product according to the requirements of the application scene, the reliability and the like of the casting;
s43, inputting the performance parameters obtained in the two steps into a machine learning model, and performing multi-objective optimization through the machine learning model to obtain the optimal alloy composition.
The specific implementation method of the fifth step is as follows:
s51, carrying out experimental verification on the alloy components obtained in the step four, testing flowability by using a single spiral die, testing hot cracking tendency by using a hot cracking constraint rod die, and carrying out body shrinkage rate test by using a common conical die;
s52, integrating the experimental results, and meeting the requirements of the performance parameter range of the die casting process.
The beneficial effects are that: according to the method, a machine learning mathematical model is established for the relation between various components of the aluminum alloy and the required performances of the integrated die casting by using a machine learning algorithm, and the components of the integrated die casting aluminum alloy are designed by optimizing the components, so that the aims of being suitable for integrated die casting and free of heat treatment are fulfilled, and certain mechanical properties and structural strength are met.
Term interpretation: integral die casting: the integrated die casting technology is to adopt a precision casting process to produce, to apply high pressure in a die to press molten metal or alloy into a die cavity, to perform primary casting, to perform solidification molding under a certain pressure, and to avoid secondary processing. The die casting aluminum alloy has finer grains than the traditional casting mode, so lighter and stronger parts can be manufactured, and the die casting technology is mainly applied to the manufacturing of parts with complex shapes, high precision and high strength, such as the fields of automobile weight reduction, aerospace, electronic equipment and the like. Compared with the traditional casting technology, the integrated die casting has the advantages of high precision, high production efficiency, low energy consumption and the like.
And (3) heat treatment is avoided: the heat treatment-free method is used for casting and die-casting large complex castings without solid solution (quenching) and aging treatment, and the structural part assembled by several or tens of parts is required in the past, and can be replaced by a complex large part formed by die-casting the heat treatment-free aluminum alloy in an integrated way, so that only a small amount of necessary machining is performed, the economic benefit is improved, and the performance is also improved. Typically such alloys are cast aluminum alloys of the 1XX series, 3XX series and 5XX series.
And (3) designing the components of the aluminum alloy: the alloy design is to obtain the expected performance through the strict control and reasonable coordination of alloy components and structures, and is a comprehensive result based on the quantitative relation of alloy components, structures, performances and processes, and the design additive elements of the aluminum alloy components mainly comprise silicon, magnesium, copper, iron and the like, and rare earth alloys such as titanium, strontium, vanadium, nickel, lanthanum, cerium and the like.
Large complex structural members: the large complex structural member refers to a member or a part which has a large volume, a complex shape, a complex structure and a specific function. These components or parts are often assembled from multiple parts, with high technical difficulty and process complexity, requiring elaborate design and manufacture to achieve their intended functions and performance. Large complex structural members are commonly used for airplanes, ships, locomotives and the like, and have wide application in the fields of transportation, aerospace, energy and the like. The integrated die casting technology can be used for integrally die-casting a complex large part from complex structural parts assembled by a plurality of or tens of parts in the past, and has the advantages of high precision, high strength, processing cost reduction and production efficiency improvement.
Machine learning: machine Learning (Machine Learning) is an artificial intelligence technique based on data that automatically learns rules from the data through algorithms and models, and makes predictions and decisions using the learned rules. Machine learning can help us identify complex data patterns and perform tasks such as accurate prediction, classification, regression, clustering, dimension reduction, and the like.
NSGA-II algorithm: the second generation non-inferior ranking genetic algorithm (NSGA-II) is a multi-objective optimization algorithm, which is an improvement based on genetic algorithms. NSGA-II can be used to optimize under multiple constraints and multiple objective functions, and multiple objectives can be optimized simultaneously.
Crack sensitivity: crack sensitivity is the sensitivity of a metal material to crack during solidification such as casting, welding, etc. The cracking sensitivity can be generally classified into hot cracking sensitivity and cold cracking sensitivity according to the type of cracks.
Thermal cracking tendencies: the hot cracking tendency (Hot Cracking Susceptibility) refers to the tendency of cracking on the surface or in the interior of a material during the processing such as welding or casting due to thermal stress or other factors generated after the material is heated. At high temperature, liquid phase or semi-liquid phase is easy to form in the material, meanwhile, thermal stress can also change along with temperature change, and all factors can cause thermal cracking. Thermal cracking has a great influence on the processing ability and performance of materials, and therefore it is necessary to evaluate and control the thermal cracking tendency of materials.
Alloy fluidity: the fluidity of an alloy refers to the ability of the liquid metal itself to flow, which determines the ability of the liquid alloy to fill a mold, and is one of the important indicators for the casting performance of the alloy.
Drawings
FIG. 1 is a prior art integrated die cast body;
FIG. 2 is a flow chart of a method of designing alloy compositions;
FIG. 3 is a machine learning flow chart for step three;
FIG. 4 is a drawing of the examples and comparative examples;
fig. 5 shows the metallographic structures of examples and comparative examples.
Detailed Description
The invention will be further illustrated by the following examples, which are not intended to limit the scope of the invention, in order to facilitate the understanding of those skilled in the art.
Example 1
Step one: selecting fluidity, hot cracking tendency, hot cracking sensitivity and shrinkage, ultimate tensile strength, yield strength, elongation at break and elastic modulus; the alloy elements of the aluminum alloy are Si, zn, fe, mg, mn, cu, sr, la, ni, V, be;
step two: according to the existing integrated die-casting aluminum alloy research material, establishing a data set of the corresponding correlation properties of the component types and the content of the aluminum alloy;
step three: and training a machine learning model by using a second generation non-inferior sorting genetic algorithm (NSGA-II), establishing a machine learning model of the performance parameters required by the integral die casting process, the performance parameters free of heat treatment and aluminum alloy components, and verifying the accuracy of the machine learning model. The ultimate tensile strength, yield strength, elongation at break and elastic modulus precision are required to be within 0.5% during model verification;
step four: according to the requirement of the casting, the alloy elements obtained by inputting all required performance parameters into a machine learning model are formed into Si, zn, fe, mg, mn, cu, sr, la, ni, and the weight percentage of each component is Si9.22%; zn1.35%; fe0.54%; mg0.32%; mn0.62%; cu0.05%; sr0.05%; la0.05%; ni0.2%; the balance of Al;
step five: the test proves that the fluidity, the hot cracking tendency, the hot cracking sensitivity and the shrinkage rate all meet the casting molding requirement, and the finished product casting has the performance tensile strength of 355MPa, the yield strength of 220MPa and the elongation of 15.4 percent after integral die casting.
By comparing the tensile properties of the existing die-casting aluminum alloy castings suitable for integration with those of castings manufactured by the method, the tensile strength, the yield strength and the elongation are improved. Through microscopic observation, the aluminum alloy casting which is suitable for integrated die casting and is free from heat treatment and is obtained through the method is basically free from air hole defects and finer in crystal grains compared with the existing aluminum alloy casting which is suitable for integrated die casting.
TABLE 1 example 1 alloy compositions
| Element(s) | Si | Zn | Fe | Mg | Mn | Cu | Sr | La | Ni | V | Be |
| Comparative example 1 | 7.54 | 0.62 | 0.22 | 0.4 | 0.65 | 0 | 0.045 | 0.06 | 0 | 0 | 0 |
| Example 1 | 9.22 | 1.35 | 0.54 | 0.32 | 0.62 | 0.05 | 0.05 | 0.05 | 0.2 | 0 | 0 |
Table 2 example 1 cast tensile properties
Example two
Step one: selecting fluidity, hot cracking tendency, hot cracking sensitivity and shrinkage, ultimate tensile strength, yield strength, elongation at break and elastic modulus; the alloy elements of the aluminum alloy are Si, zn, fe, mg, mn, cu, sr, la, ni, V, be;
step two: according to the die-casting aluminum alloy materials in the existing research, a data set of the corresponding related properties of the component types and the content of the aluminum alloy is established;
step three: and training a machine learning model by using a second generation non-inferior sorting genetic algorithm (NSGA-II), establishing a machine learning model of the performance parameters required by the integral die casting process, the performance parameters free of heat treatment and aluminum alloy components, and verifying the accuracy of the machine learning model. The ultimate tensile strength, yield strength, elongation at break and elastic modulus precision are required to be within 0.5% during model verification;
step four: according to the requirement of the casting, inputting all required performance parameters into a machine learning model to obtain alloy elements Si, zn, fe, mg, mn, cu, sr, la, ni, V, be, wherein the weight percentage of each component is Si10.24%; zn3.23%; fe0.65%; mg0.4%; mn0.6%; cu0.08%; sr0.1%; la0.06%; ni0.28%; v0.1%; be0.2%; the balance of Al;
step five: the test proves that the fluidity, the hot cracking tendency, the hot cracking sensitivity and the shrinkage rate all meet the casting molding requirement, and the finished product casting has the properties of 345MPa of tensile strength, 244MPa of yield strength and 12.6% of elongation after integral die casting.
TABLE 3 example 2 alloy compositions
Table 4 example 2 cast tensile properties
By comparing the tensile properties of the existing die-casting aluminum alloy castings suitable for integration with those of castings manufactured by the method, the tensile strength, the yield strength and the elongation are improved. By comparing the existing integrated heat treatment-free aluminum alloy die castings which are suitable for the integrated die casting aluminum alloy castings and the method, the alloy grains can be found to be finer by adopting the method.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
It should be understood that the detailed description of the technical solution of the present invention, given by way of preferred embodiments, is illustrative and not restrictive. Modifications of the technical solutions described in the embodiments or equivalent substitutions of some technical features thereof may be performed by those skilled in the art on the basis of the present description; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The integral die-casting heat treatment-free aluminum alloy component design method based on machine learning is characterized by comprising the following steps of:
step one: determining component selection standards of the integrated die-casting aluminum alloy: selecting alloy elements influencing casting performance and parameters influencing casting performance and mechanical performance of the integrated die-casting part;
step two: establishing a data set according to the known integral die-casting aluminum alloy composition data and the performance data;
step three: establishing a machine learning model of the performance parameters required by the integral die casting process, the performance parameters free of heat treatment and the aluminum alloy components, and verifying the accuracy of the machine learning model;
step four: inputting the casting performance requirements and casting finished product performance requirement parameters calculated by the integrated die castings with different sizes into a machine learning model to obtain alloy components and contents meeting the requirements;
step five: carrying out experimental verification on the related performances of fluidity, hot cracking tendency, hot cracking sensitivity and shrinkage by using the components and the contents of the aluminum alloy obtained in the step four;
step six: the integrated die casting is manufactured by using the qualified alloy, and experimental verification is carried out on manufacturing performance and finished product performance, so that the integrated die casting meets the requirements for actual production.
2. The method of claim 1, wherein the step one is performed as follows:
s11, selecting performance parameters affecting the integrated die casting process;
s12, selecting heat treatment-free performance parameters of a casting finished product;
s13, selecting components affecting the material performance.
3. The method of claim 2, wherein S11 selects performance parameters affecting the integrated die casting process, including flowability, hot cracking tendency, hot cracking sensitivity, and shrinkage;
and/or
S12, selecting heat treatment-free performance parameters of a casting finished product, wherein the heat treatment-free performance parameters comprise ultimate tensile strength, yield strength, elongation at break and elastic modulus;
and/or
S13, selecting components which influence the performance of the material, wherein the components comprise silicon, magnesium, copper, iron, titanium, strontium, vanadium, nickel, lanthanum and cerium.
4. The method of claim 1, wherein the performance data in step two includes corresponding thermal fluidity and crack sensitivity, shrinkage, ultimate tensile strength, yield strength, and elongation at break.
5. The method of claim 1, wherein the method comprises the steps of,
the specific implementation method of the second step is as follows:
s21, establishing an aluminum alloy component type data set;
s22, establishing a unified performance parameter data set for the parameters which are selected in the step one and affect the integral die casting process and the heat treatment-free finished product;
s23, integrating the two data sets, and establishing a data set of the corresponding performance of the aluminum alloy component types and the content.
6. The method according to claim 1, wherein the method of step three is performed as follows:
s31, preprocessing the component data and the performance data of the known integrated die-casting aluminum alloy obtained in the step two;
s32, a second generation non-inferior sorting genetic algorithm is selected to establish a machine learning model;
s33, training a machine learning model by using the preprocessed aluminum alloy performance data set and the component data set of the corresponding aluminum alloy;
s34, predicting test set data by using the trained machine learning model, comparing a prediction result with known data, detecting feasibility and accuracy of the machine learning model, and carrying out parameter correction on the machine learning model until the required precision requirement is met;
the target performance is input as input data into the trained model to obtain the initial design components.
7. The method according to claim 1, wherein the implementation method of the fourth step is as follows:
s41, calculating the performance parameter requirements of complete mold filling and no defects according to the size and thickness of the casting;
s42, calculating the performance parameter requirements of the finished casting product according to the application scene and the reliability requirements of the casting;
s43, inputting the performance parameters obtained in the two steps into a machine learning model, and performing multi-objective optimization through the machine learning model to obtain the optimal alloy composition.
8. The method of claim 1, wherein the step five is performed as follows:
s51, carrying out experimental verification on the alloy components obtained in the step four, testing flowability by using a single spiral die, testing hot cracking tendency by using a hot cracking constraint rod die, and carrying out body shrinkage rate test by using a common conical die;
s52 integrates the experimental results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310875231.6A CN116913404A (en) | 2023-07-17 | 2023-07-17 | Machine learning-based integral die-casting heat treatment-free aluminum alloy component design method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310875231.6A CN116913404A (en) | 2023-07-17 | 2023-07-17 | Machine learning-based integral die-casting heat treatment-free aluminum alloy component design method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116913404A true CN116913404A (en) | 2023-10-20 |
Family
ID=88356054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310875231.6A Pending CN116913404A (en) | 2023-07-17 | 2023-07-17 | Machine learning-based integral die-casting heat treatment-free aluminum alloy component design method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116913404A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117352110A (en) * | 2023-12-05 | 2024-01-05 | 江苏美特林科特殊合金股份有限公司 | System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method |
-
2023
- 2023-07-17 CN CN202310875231.6A patent/CN116913404A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117352110A (en) * | 2023-12-05 | 2024-01-05 | 江苏美特林科特殊合金股份有限公司 | System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method |
| CN117352110B (en) * | 2023-12-05 | 2024-02-13 | 江苏美特林科特殊合金股份有限公司 | System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102134671B (en) | Aluminum alloy products and artificial aging method | |
| CN116913404A (en) | Machine learning-based integral die-casting heat treatment-free aluminum alloy component design method | |
| CN104636565B (en) | The die forging forming process optimization method of magnesium alloy analyzed based on machinability | |
| CN110334416B (en) | Optimized design method for prefabricated blank during forging of dual-performance disc | |
| Gupta et al. | Optimization of process parameters during pressure die casting of A380: a silicon-based aluminium alloy using GA & fuzzy methodology | |
| Baser et al. | New trends in aluminum die casting alloys for automotive applications | |
| Azhagan et al. | Optimization of process parameters to enhance the hardness on squeeze cast aluminium alloy AA6061 | |
| Lin et al. | Optimization of hot deformation processing parameters for as-extruded 7005 alloys through the integration of 3D processing maps and FEM numerical simulation | |
| Hsiang et al. | Using artificial neural networks to investigate the influence of temperature on hot extrusion of AZ61 magnesium alloy | |
| Amirthagadeswaran et al. | Enhancing wear resistance of squeeze cast ac2a aluminum alloy | |
| Muñoz-Ibáñez et al. | Design and application of a quantitative forecast model for determination of the properties of aluminum alloys used in die casting | |
| Zhou et al. | A systematic approach to model and optimize qualities of castings produced by squeeze casting process | |
| CN114178454A (en) | Preparation method of magnesium-lithium alloy hollow component with complex section | |
| Falsafi et al. | Lower cost automotive piston from 2124/SiC/25p metal-matrix composite | |
| CN107677786A (en) | Cast steel shrinkage defect ranking method | |
| Zhou et al. | Study on squeeze casting process of the integrated aluminum alloy subframe | |
| Peng et al. | Parametric analysis of warm forming of aluminum blanks with FEA and DOE | |
| CN114117684A (en) | Selective laser melting forming 316L stainless steel abrasion prediction method based on machine learning | |
| Kumar et al. | Optimization of casting process through reliability approach | |
| Beals et al. | Development of Advanced Aluminum Alloy for Structural Castings | |
| Pongen et al. | Optimal design of die casting process parameters of A713 cast alloy with grain refinement by using genetic algorithm approach for automobile industries | |
| CN111861041A (en) | Method for predicting dynamic recrystallization type flowing stress of Nb microalloyed steel | |
| CN118278273A (en) | Intelligent grading and optimizing method for light alloy die casting process parameters | |
| Wu et al. | Numerical and physical simulation of the forging process with liquid core | |
| Sata et al. | Mechanical property prediction of investment castings using artificial neural network and multivariate regression analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |