CN-122024897-A - Method, medium and computer equipment for regulating and controlling type of iron-containing phase in reclaimed aluminum

CN122024897ACN 122024897 ACN122024897 ACN 122024897ACN-122024897-A

Abstract

The invention relates to the technical field of nonferrous metal recycling, and discloses a method, a medium and computer equipment for regulating and controlling the type of an iron-containing phase in reclaimed aluminum. The method integrates unbalanced solidification simulation (physical knowledge) and machine learning (data driving), and specifically constructs a component-phase fraction-iron-containing phase type associated data set under the condition of limited experimental data, introduces a machine learning model based on the associated data set to predict iron-containing phase types corresponding to different alloy components, obtains component regulation criteria for distinguishing the different iron-containing phase types, and finally performs component regulation of alloy design based on the obtained component regulation criteria.

Inventors

ZHANG LIJUN
YI WANG
WU FAN

Assignees

中南大学

Dates

Publication Date: 20260512
Application Date: 20260410

Claims (7)

1. The method for regulating and controlling the type of the iron-containing phase in the reclaimed aluminum is characterized by comprising the following steps of: Step S1, obtaining different components Casting iron-containing phase type data of alloy, obtaining phase fraction data of iron-containing phase in the alloy by non-equilibrium solidification simulation, wherein the iron-containing phase type comprises needle-shaped Fe phase and Chinese character shape A Fe phase; s2, integrating the iron-containing phase type data and the phase fraction data obtained in the step S1 to construct a related data set containing alloy components, phase fraction and iron-containing phase type; s3, constructing and training to obtain a machine learning model taking the phase fraction as input and the iron-containing phase type as output based on the associated data set obtained in the step S2; s4, predicting iron-containing phase types corresponding to different alloy components based on the machine learning model obtained in the step S3, and determining component regulation criteria for distinguishing different iron-containing phase types according to the iron-containing phase types; and S5, carrying out component regulation and control on the alloy design based on the component regulation and control criterion obtained in the step S4.
2. The method for controlling the type of iron-containing phase in secondary aluminum according to claim 1, wherein the component control criteria in the step S4 is that when the Mn element content in the alloy is Needle-like structure is realized when the following relationship is satisfied Fe opposite Chinese character shape Complete conversion of the Fe phase is as follows: ; Wherein: The content of Fe element; Is Fe element content Is the square of (2); the content of Si element.
3. The method for controlling the type of iron-containing phase in secondary aluminum according to claim 1, wherein the components in step S1 are different The cast alloy contains 6.0-12.0 wt wt.% Si element, 0-0.5wt.% Mg element, 0-2.0 wt wt.% Fe element, and 0-2.5 wt wt.% Mn element.
4. The method for controlling the type of iron-containing phase in secondary aluminum according to claim 3, wherein the components are different The cast alloy includes at least one of the following alloys: 、、、、 And At least one of them.
5. The method for controlling the type of iron-containing phases in the secondary aluminum according to claim 1, wherein the machine learning model in the step S3 adopts a logistic regression model.
6. A computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer-executable instructions are used to implement the method for controlling the iron-containing phase type in the secondary aluminum according to any one of claims 1 to 5.
7. A computer device comprising a processor and a memory communicatively coupled to the processor; The memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method for controlling the type of iron-containing phases in the secondary aluminum as claimed in any one of claims 1 to 5.

Description

Method, medium and computer equipment for regulating and controlling type of iron-containing phase in reclaimed aluminum Technical Field The invention relates to the technical field of nonferrous metal recycling, in particular to a method, medium and computer equipment for regulating and controlling the type of an iron-containing phase in reclaimed aluminum. Background Aluminum and its alloys are favored for lightweight applications in aerospace, automotive, and other fields due to their excellent specific strength. However, during the casting and recovery of aluminum alloys, impurity elements such as iron (Fe) are inevitably introduced, and since Fe has extremely low solid solubility (about 0.05 wt%) in the aluminum matrix, excessive Fe is liable to react with elements such as Al, si and Mg to form brittle intermetallic compounds containing iron (iron-containing phases). Needle-like shapeFe) phase can severely fracture the matrix, so that the mechanical properties, particularly the ductility and fatigue resistance of the alloy are obviously reduced, and the alloy becomes a main obstacle for high-value utilization of the reclaimed aluminum. In the prior art, fe is directly removed from an aluminum melt, so that the technical difficulty is high and the economical efficiency is poor. Therefore, phase morphology regulation strategies are commonly adopted in the industry and academia, namely, by adding alloying elements (such as manganese, mn) and the like, harmful needle-like shapes are promotedThe Fe phase is converted into less harmful(Fe) phase. However, the existing Mn addition amount regulating method depends on experimental trial and error or limited experimental data, and is difficult to cope with the challenges of complex and changeable components (high-dimensional component space) of the raw material of the secondary aluminum. For example, excessive addition of Mn not only increases the total volume fraction of the iron-containing phase, but also may form coarse bulk slag phases, rather deteriorating alloy properties. Conventional alloy design methods typically rely on extensive experimental sampling of the high-dimensional component space to build a "component-microstructure-property" mapping. However, the pure experimental method faces significant challenges in a regenerated aluminum system, namely, on one hand, high experimental cost and long period due to large component fluctuation and complex interaction of impurity elements, and on the other hand, under the condition of a small sample with scarce data, the nonlinear mapping relationship between the components and the iron-containing phase type is easily subjected to overfitting, and the model generalization capability is poor. How to mine out the microstructure characteristics (such as the volume fraction of the iron-containing phase) hidden behind the components under the condition of limited experimental data, and to use the microstructure characteristics as physical constraints to guide a machine learning model is a key scientific problem for realizing accurate regulation and control of the iron-containing phase of the recycled aluminum. Therefore, it is necessary to provide a method for controlling the type of iron-containing phases in secondary aluminum with high prediction accuracy and strong generalization capability to solve the above-mentioned technical problems. Disclosure of Invention The invention mainly aims to provide the method for regulating and controlling the iron-containing phase type in the reclaimed aluminum, which integrates unbalanced solidification simulation (physical knowledge) and machine learning (data driving), can quickly and accurately explore and predict the iron-containing phase type of any component point in a high-dimensional component space, greatly reduces the repeated experiment and trial-and-error times required by the traditional method, obviously shortens the research and development period, reduces the research and development cost, and provides a brand-new technical path for the high-value utilization of a complex reclaimed aluminum system. In order to achieve the above purpose, the invention provides a method for regulating and controlling the type of an iron-containing phase in reclaimed aluminum, which comprises the following steps: Step S1, obtaining different components Casting iron-containing phase type data of alloy, obtaining phase fraction data of iron-containing phase in the alloy by non-equilibrium solidification simulation, wherein the iron-containing phase type comprises needle-shapedFe phase and Chinese character shapeA Fe phase; s2, integrating the iron-containing phase type data and the phase fraction data obtained in the step S1 to construct a related data set containing alloy components, phase fraction and iron-containing phase type; s3, constructing and training to obtain a machine learning model taking the phase fraction as input and the iron-containing phase type as output based on