检索结果-内蒙古大学图书馆

microstructure prediction of semi-solid AZ91D magnesium alloy prepared by mechanical stirring based on regression analysis and neural network

引用

MATERIALWISSENSCHAFT UND WERKSTOFFTECHNIK 2025年第4期56卷 565-574页

作者： Zhang, X. Luo, H. Wang, Y. Jiang, B. Ji, Z. Lui, J. Harbin Univ Sci & Technol Sch Architectural Engn Harbin 150040 Peoples R China Harbin Univ Sci & Technol Sch Mat Sci & Chem Engn Harbin Peoples R China Harbin Boiler Co Ltd Harbin Peoples R China

In the present investigation two smart prediction tools, namely the multiple regression analysis and general regression neural network models were developed to predict average grain size and shape factor of the semi-solid AZ91D magnesium alloy microstructure prepared by mechanical stirring. The process parameters (stirring temperature, stirring rate, stirring time) were considered as input variables to establish predictive models. The models were developed using the multiple regression analysis was employed to determine the significance of process parameters on microstructure. In the general regression neural network models, the k-fold cross validation method is used to optimize the smoothing factor. The neural network models were trained, validated and tested. The results show the general regression neural network models achieve higher prediction accuracy for predicted error within 5 % compared with regression models within 10 %, which suggests that the model is more reliable. Finally, the accuracy of models was demonstrated based on experimental verification, asserting that they can provide a foundation for developing a comprehensive prediction system to optimize the structural and processing of semi-solid magnesium alloys.

关键词： magnesium alloy mechanical stirring microstructure prediction neural network regression analysis semi-solid Gef & uuml geabsch & auml tzung halbfest Magnesiumlegierung mechanisches R & uuml hren neuronales Netzwerk Regressionsanalyse

来源：评论

学校读者我要写书评

暂无评论

Optimization of Process Parameters and microstructure prediction of A360 Al-Alloy During Die Casting

引用

INTERNATIONAL JOURNAL OF METALCASTING 2025年 1-13页

作者： Xu, Zehui Chen, Tianle Li, Bing Wang, Changfeng Yang, Shengyuan Chen, Yucheng Guo, Zhipeng Zhang, Wei Guan, Renguo Dalian Jiaotong Univ Engn Res Ctr Continuous Extrus Minist Educ Dalian 116028 Peoples R China Dalian Jiaotong Univ Key Lab Near Net Forming Light Met Liaoning Prov Dalian 116028 Peoples R China Beijing Supreium Technol Co Ltd Beijing Peoples R China

To address the issue of significant defects in A360 Al-Alloy cover plates caused by excessive porosity during the die casting process, Response Surface Methodology (RSM), based on the Ordinary Least Squares (OLS) method, was employed. The relationship between three key process parameters (casting temperaturee [T-C], mold preheating temperature [T-M], and fast injection speed [V]) and volumetric porosity was systematically investigated through 17 distinct combinations of injection molding parameters. The filling and solidification processes of A360 Al-Alloy die casting were numerically simulated, and the optimal process parameters were selected based on the principle of minimizing porosity. The average grain size (AGS) of several parts of the casting was determined by the Electron Back Scatter Diffraction (EBSD) test results, and the test results were combined with OLS method to obtain a mathematical model for predicting the AGS, the numerical simulation results of other parts of the casting were input into the mathematical model, resulting in a predicted distribution of AGS. The predicted distribution of AGS was presented in the form of an image using Monte Carlo method. Experimental results indicate that the optimal process parameters are T-C of 630 degrees C, T-M of 220 degrees C, and V of 2.5 m/s. Under these conditions, the porosity (P) is minimized, resulting in the highest product quality. The analysis indicates that T-C and T-M significantly affect P. The Monte Carlo method predicts grain size with an error of less than 2.13% when compared to actual measurements.

关键词： A360 Al-Alloy Die casting Numerical simulation Monte Carlo method microstructure prediction

来源：评论

学校读者我要写书评

暂无评论

Generative network-assisted acceleration for microstructure simulation and prediction in laser-based additive manufacturing

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2025年第5-6期137卷 2455-2470页

作者： Gu, Zhaochen Manjunath, Aishwarya Anantatamukala, Amrutha Krishna, Karri Venkata Mani Fu, Song Sharma, Shashank Dahotre, Narendra Bapurao Univ North Texas Dept Comp Sci & Engn 3940 N ELM St Denton TX 76207 USA Univ North Texas Dept Mat Sci & Engn 3940 N ELM St Denton TX 76207 USA Univ North Texas Dept Mech Engn 3940 N Elm St Denton TX 76207 USA Univ North Texas Ctr Agile & Adapt Addit Mfg 3940 N Elm St Denton TX 76207 USA

In laser-based additive manufacturing, the process-structure-property paradigm has been critical for optimizing the fabrication of metallic components. The formation of anisotropic microstructures, primarily influenced by thermokinetics, has posed challenges in achieving desired mechanical properties. Computational methods such as cellular automata, phase field, and Monte Carlo simulations were traditionally employed to predict microstructural evolution;however, they have proven to be computationally intensive. This study employed a conditional generative adversarial network (GAN) utilizing the Pix2Pix architecture to predict microstructural evolution in laser-based additive manufacturing. The model was trained on over 1500 microstructure images generated by Kinetic Monte Carlo simulations with varying processing parameters, focusing on grain morphology and size distribution. Traditional image comparison metrics such as structural similarity index and mean squared error were deemed unsuitable due to their inability to capture higher-level features like grain structure. Instead, quantitative comparisons based on grain size distributions were employed to assess model performance. The results indicated strong efficacy in predicting equiaxed grain morphologies and accurately capturing grain size distributions, achieving the highest similarity score of 3.88e - 2 and the lowest distance score of 0.29. However, challenges were noted in predicting columnar grains, where larger grains were sometimes mispredicted as smaller. The findings suggested that a more balanced dataset could further improve performance, particularly in handling larger and columnar-shaped grains.

关键词： Surrogate modeling Deep learning Kinetic Monte Carlo microstructure prediction Laser-based additive manufacturing

来源：评论

学校读者我要写书评

暂无评论

Investigation of microstructure prediction during experimental thermo-mechanical plate rolling

引用

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY 2001年第1-2期109卷 112-119页

作者： Korczak, P Dyja, H Czestochowa Tech Univ Fac Met & Mat Engn PL-42200 Czestochowa Poland

In this study results of experimental and theoretical research of modeling of microstructure in hot rolling process of steel carbon plates with niobium are presented. Models describing kinetics of recrystallization of a deformed austenite and precipitation of niobium carbon-nitrides were verified in semi-industrial conditions. The main aim of the experimental study made in present paper were determination of distributions of microstructure parameters after partly steps of thermo-mechanical steel rolling. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： microstructure prediction recrystallization precipitation mechanical properties

来源：评论

学校读者我要写书评

暂无评论

microstructure Evolution and prediction Model of 6082-T6 Aluminum Alloy Pulsed Metal Inert Gas Welded Joint

引用

JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE 2024年 1-20页

作者： Xu, Shiwei Wang, Yaochao Yang, Xiaoyi Li, Mengnie Victor Zuo, Hanning Yang, Shuhan Kunming Univ Sci & Technol Fac Mat Sci & Engn Kunming 650093 Peoples R China Kunming Dalv Technol Co Ltd Kunming 650093 Peoples R China

The weld metal (WM) and heat-affected zone are often the weak areas of aluminum alloy welded joints, in which poor properties of WM are typically associated with the microstructure formed during the melting and solidification. This paper focuses on the changes in microstructure and properties of aluminum alloy WM. Based on the finite element method, a three-dimensional model for predicting the columnar-to-equiaxed transition (CET) of weld metal during pulsed metal inert gas welding of 6082-T6 aluminum alloy was successfully *** the same time, this study also analyzed the changes of microstructure and mechanical properties of WM under different heat inputs. The criterion curve for the CET of 6082-T6 aluminum alloy WM was expressed as Gn/R=Cst\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$G<^>{n} /R = C_{st}$$\end{document}, where n\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n$$\end{document} is 7.85855, and Cst\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$C_{st}$$\end{document} is 7.9749 x 104. Additionally, it is found that as the heat input increases, the grain size of WM initially decreases and then increases, and promoting the formation of equiaxed grains. At the same time, the content of Mg2Si and Al6 (Mn, Fe) phases in the WM increases, which affects the microhardness of the WM . This method is also applicable to other aluminum alloys joints, and it is of significant importance in predicting microstructure t

关键词： 6082-T6 aluminum alloy microstructure prediction Models for the transformation of columnar to equiaxed grains P-MIG

来源：评论

学校读者我要写书评

暂无评论

The prediction of microstructure Evolution of 6005A Aluminum Alloy in a P-ECAP Extrusion Study

引用

JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE 2018年第5期27卷 2566-2575页

作者： Shi Lei Wen Jiu-Ba Ren Chang Henan Univ Sci & Technol Sch Mat Sci & Engn Luoyang 471023 Peoples R China Luoyang Inst Sci & Technol Sch Mat Sci & Engn Luoyang 471023 Peoples R China Northwestern Polytech Univ Sch Mat Sci & Engn Xian 710072 Shaanxi Peoples R China

Finite element modeling (FEM) was applied for predicting the recrystallized structure in extruded 6005 aluminum alloy, and simulated results were experimentally validated. First, microstructure evolution of 6005 aluminum alloy during deformation was studied by means of isothermal compression test, where the processing parameters were chosen to reproduce the typical industrial conditions. Second, microstructure evolution was analyzed, and the obtained information was used to fit a dynamic recrystallization model implementing inside the DEFORM-3D FEM code environment. FEM of deformation of 6005 aluminum has been established and validated by microstructure comparison. Finally, the obtained dynamic recrystallization model was applied to tube extrusion by using a portholes-equal channel angular pressing die. The finite element analysis results showed that coarse DRX grains occur in the extruded tube at higher temperature and in the extruded tube at the faster speed of the stem. The test results showed material from the front end of the extruded tube has coarse grains (60 mu m) and other extruded tube has finer grains (20 mu m).

关键词： aluminum alloy dynamic recrystallization finite element modeling (FEM) microstructure prediction

来源：评论

学校读者我要写书评

暂无评论

Cooling Characteristic of Polymeric Quenchant: Calculation of HTC and prediction of microstructure and Hardness

引用

JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE 2014年第11期23卷 3819-3830页

作者： Ikkene, Rafika Koudil, Zahia Mouzali, Mohammed Ctr Res Phys & Chem Anal CRAPC Algiers Rp 16004 Algeria USTHB Fac Chem Lab Physicochem Studies Mat & Applicat Environm Algiers 16111 Algeria

The present paper discusses the influence of experimental conditions on the quenching performance of poly(2-ethyl-2-oxazoline) (PEOX) aqueous solutions used as cooling medium, using a standard ISO Inconel alloy probe for measurements of cooling rate. The evaluation procedure is demonstrated on characterization of cooling power of water-based polymer (PEOX) solutions by using different concentration, temperatures, and agitation conditions of the cooling media. The results show that the different experimental conditions have a significant effect on the cooling performance. The polymer quenching mechanism and the comparative cooling characteristics of water, and water-based PEOX polymer solution with concentrations from 2.5 to 15 wt.% were discussed. The study involved the assessment of the quenching severity by calculating the hardening power (HP) via empirical equations. Calculation of heat transfer coefficients as well as prediction of microstructural constituents and the hardness profile in a cross-section of steel sample were carried out on the basis of inverse calculation from the recorded cooling curve.

关键词： cooling curve hardening power heat transfer coefficient heat treatment microstructure prediction polymer quenchant

来源：评论

学校读者我要写书评

暂无评论

prediction of microstructure for AISI316L Steel from Numerical Simulation of Laser Powder Bed Fusion

引用

METALS AND MATERIALS INTERNATIONAL 2022年第11期28卷 2735-2746页

作者： Abrami, Maria Beatrice Tocci, Marialaura Obeidi, Muhannad Ahmed Brabazon, Dermot Pola, Annalisa Univ Brescia Dipartimento Ingn Meccan & Ind Via Branze 38 I-25123 Brescia Italy Dublin City Univ Adv Mfg Res Ctr Sch Mech & Mfg Engn I Form Glasnevin Ireland

Laser powder bed fusion (L-PBF) success in the industrial scenario strongly depends on the ability to manufacture components without defects and with high building rates, but also on the ability to effectively control the microstructure to gain the required properties in the final component. In this regard, the recently developed numerical simulation software of L-PBF technologies can represent an effective tool, since many of them provide solidification data (i.e. temperature gradient and cooling rate) useful for microstructure prediction. In this work, a numerical model was applied to simulate the processing of four single scan tracks of 316L stainless steel processed with different parameters. Temperature and cooling rate around the melt pool were extracted from the numerical model and used to estimate the microstructure cellular arm spacing and the microhardness. Experimental measurements were then compared with the estimated values revealing good agreement. The good agreement between experimental and estimated values shows the advantages of the proposed method for microstructure and microhardness prediction based on numerical modelling as a useful resource for process optimization according to the required final microstructural features.

关键词： microstructure prediction Cellular microstructure Microhardness prediction Numerical simulation 316L stainless steel Laser powder bed fusion

来源：评论

学校读者我要写书评

暂无评论

Finite Element Simulation and Experiment on the microstructure of High-Strength Mg-Gd-Y-Zn-Zr Alloy during U-Shaped Bending Process

引用

JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE 2025年第2期34卷 1243-1257页

作者： Wang, Hao Yin, Jiaming Yao, Caogen Hu, Zhenggen Luo, Junting Yanshan Univ Minist Educ China Key Lab Adv Forging & Stamping Technol & Sci Qinhuangdao 066004 Peoples R China Aerosp Res Insitute Mat & Proc Technol Beijing Peoples R China Beijing Inst Astronaut Syst Engn Beijing Peoples R China

In this study, the recrystallization evolution model of Mg-Gd-Y-Zn-Zr alloy under tensile stress was established, and the microstructure evolution of Mg-Gd-Y-Zn-Zr alloy sheet in U-shaped bending process was simulated by Deform software. The U-bending test was performed based on the simulation parameters, and the microstructure evolution law of the high-strength Mg-Gd-Y-Zn-Zr alloy sheet during the U-shaped bending process was studied. The research showed that the grain size gradually decreased from the straight wall area to the curved filet area. Furthermore, the grain size of the formed part increased with increasing forming temperature and decreasing stamping speed. The average grain size error between finite element simulation and test results was less than 10%. The fragmentation of the bulk long-period stacking ordered (LPSO) phase and the kink of the lamellar LPSO phase led to the formation of the recrystallized structure. The initial dynamic recrystallized structure at the interface of the LPSO phase increased with increasing stamping speed, decreasing the overall average grain size. Moreover, the recrystallized grain size increased slightly with increasing forming temperature.

关键词： Mg-Gd-Y-Zn-Zr alloy U-shaped bending process finite element simulation microstructure prediction

来源：评论

学校读者我要写书评

暂无评论

A deep learning model for the accurate prediction of the microstructure performance of hot rolled steel

引用

INTERNATIONAL JOURNAL OF MANUFACTURING RESEARCH 2021年第3期16卷 262-279页

作者： Wang, Bin-bin Song, Yong Wang, Jing Univ Sci & Technol Beijing Engn Technol Res Inst Beijing 100083 Peoples R China

The prediction of microstructure performance can guide the adjustment of parameters during hot rolling. Scholars from all over the world has developed physical metallurgical models of rolling process based on the physical and thermodynamic characteristics of strip steel, but the prediction accuracy of the model is greatly affected by the complex production environment. In recent years, neural network method is used to build the prediction model of organisational performance. However, the prediction accuracy and robustness of the single hidden layer neural network model are poor. Deep learning method is introduced in this paper to establish the prediction model of hot rolling microstructure performance in this paper. The application results show that compared with the traditional model, the prediction accuracy of the hot rolled steels yield strength, tensile strength and elongation increased by 3.46%, 2.35%, and 5.11%, respectively. [Submitted 13 March 2019;Accepted 27 October 2019]

关键词： auto encoder deep learning hot rolled steel microstructure prediction steel properties

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：