Machine-learning-assisted prediction of the mechanical properties of Cu-Al alloy

Deng, Zhenghua; Yin, Haiqing; Jiang, Xue; Zhang, Cong; Zhang, Guofei; Xu, Bin; Yang, Guoqiang; Zhang, Tong; Wu, Mao; Qu, Xuanhui

doi:10.1007/s12613-019-1894-6

Cited by 34 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…), thermodynamic (e.g., thermal conductivity, mixing entropy, etc.) and catalytical properties (e.g., reactant binding energy on alloy's crystalline facets) for various alloys, [139][140][141][142][143] and to predict ε for several compound materials and polymers. [144][145][146][147] The inverse design of alloys with targeted mechanical and electrical properties (e.g., tensile strength, conductivity, etc.)…”

Section: Discussionmentioning

confidence: 99%

Emergent Opportunities with Metallic Alloys: From Material Design to Optical Devices

Gong

Lyu

Palm

et al. 2020

Advanced Optical Materials

View full text Add to dashboard Cite

devices is the fact that their dielectric function (i.e., permittivity, ε = ε 1 + iε 2) is predefined. Thus, several research groups, including ours, have recently merged two almost orthogonal fields, photo nics, and metallurgy, to pursue metallic materials with arbitrary permit tivity. [1-5] Alloying is now a burgeoning framework for achieving materials with engineered optical properties, encom passing both nanostructures and thin films, as will be surveyed in this Review. Plasmonics exploits the interaction of incident electromagnetic fields with the col lective motion of free electrons (plasmons) in metals. This phenomenon confines the electromagnetic fields in close vicinity of the metal interfaces, dramatically enhancing the electrical field intensity surrounding the material. [6-8] Plasmons can be divided into two categories: surface plasmon polaritons (SPP) that propagate along the metal and dielectric interface, and localized surface plasmon resonance (LSPR) that are confined in a subwavelength nanostructure. For the latter, their optical scattering or absorp tion (and/or the nearby dielectrics and semiconductors) can be significantly increased. As a result, these enhancement effects are the underpinnings to a range of novel optical processes, and have found countless applications in photovoltaics, [9-11] photo catalysis, [12-14] bio and chemicalsensing, [15,16] electrooptical modu lation, [17,18] and superabsorbers. [19-21] As expected, the features of either type of plasmon are strongly dependent upon the dielectric function of the material, which is somewhat fixed in metals. Concerning materials, coinage metals, such as Au, Ag, or Cu, are widely used in photonics due to their abundant free electrons and chemical stability. [1] Other noble metals including Metallic nanostructures and thin films are fundamental building blocks for next-generation nanophotonics. Yet, the fixed permittivity of pure metals often imposes limitations on the materials employed and/or on device performance. Alternatively, metallic mixtures, or alloys, represent a promising pathway to tailor the optical and electrical properties of devices, enabling further control of the electromagnetic spectrum. In this Review, a survey of recent advances in photonics and plasmonics achieved using metal alloys is presented. An overview of the primary fabrication methods to obtain subwavelength alloyed nanostructures is provided, followed by an in-depth analysis of experimental and theoretical studies of their optical properties, including their correlation with band structure. The broad landscape of optical devices that can benefit from metallic materials with engineered permittivity is also discussed, spanning from superabsorbers and hydrogen sensors to photovoltaics and hot electron devices. This Review concludes with an outlook of potential research directions that would benefit from the on demand optical properties of metallic mixtures, leading to new optoelectronic materials and device opportunities.

show abstract

Section: Discussionmentioning

confidence: 99%

Emergent Opportunities with Metallic Alloys: From Material Design to Optical Devices

Gong

Lyu

Palm

et al. 2020

Advanced Optical Materials

View full text Add to dashboard Cite

show abstract

“…Zhenghua et al used the chemical composition and porosity of compacts as descriptors to predict the mechanical properties of Cu-Al alloys. Six algorithms were introduced, of which SVR showed the best prediction ability [23]. Together, these studies show the great application potential for machine learning.…”

Section: Machine Learning Application In Mechanical Properties Predic...mentioning

confidence: 96%

Prediction of Mechanical Properties of Three-Dimensional Printed Lattice Structures Through Machine Learning

Tang

Liu

et al. 2021

Journal of Computing and Information Science in Engineering

View full text Add to dashboard Cite

Lattice structures (LS) manufactured by 3D printing are widely applied in many areas, such as aerospace and tissue engineering, due to their lightweight and adjustable mechanical properties. It is necessary to reduce costs by predicting the mechanical properties of LS at the design stage since 3D printing is exorbitant at present. However, predicting mechanical properties quickly and accurately poses a challenge. To address this problem, this study proposes a novel method that is applied to different LS and materials to predict their mechanical properties through machine learning. First, this study voxelized 3D models of the LS units and then calculated the entropy vector of each model as the geometric feature of the LS units. Next, the porosity, material density, elastic modulus, and unit length of the lattice unit are combined with entropy as the inputs of the machine learning model. The sample set includes 57 samples collected from previous studies. Support vector regression (SVR) was used in this study to predict the mechanical properties. The results indicate that the proposed method can predict the mechanical properties of LS effectively and is suitable for different LS and materials. The significance of this work is that it provides a method with great potential to promote the design process of lattice structures by predicting their mechanical properties quickly and effectively.

show abstract

“…Zhenghua et al used the chemical composition and porosity of compacts as descriptors to predict the mechanical properties of Cu-Al alloys. Six algorithms were introduced, of which SVR showed the best prediction ability [22]. Together, these studies show the great application potential for machine learning.…”

Section: Machine Learning Application In Mechanical Properties Predictionmentioning

confidence: 96%

Predicting Mechanical Properties of 3D Printed Lattice Structures

Tang

et al. 2021

Volume 2: 41st Computers and Information in Engineering Conference (CIE)

View full text Add to dashboard Cite

Lattice structures (LS) manufactured by 3D printing are widely applied in many areas, such as aerospace and tissue engineering, due to their lightweight and adjustable mechanical properties. It is necessary to reduce costs by predicting the mechanical properties of LS at the design stage since 3D printing is exorbitant at present. However, predicting mechanical properties quickly and accurately poses a challenge. To address this problem, this study proposes a novel method that is applied to different LS and materials to predict their mechanical properties through machine learning. First, this study voxelised 3D models of the LS units and then calculated the entropy vector of each model as the geometric feature of the LS units. Next, the porosity, material density, elastic modulus, and unit length of the lattice unit are combined with entropy as the inputs of the machine learning model. The sample set includes 57 samples collected from previous studies. Support vector regression was used in this study to predict the mechanical properties. The results indicate that the proposed method can predict the mechanical properties of LS effectively and is suitable for different LS and materials. The significance of this work is that it provides a method with great potential to promote the design process of lattice structures by predicting their mechanical properties quickly and effectively.

show abstract

Machine-learning-assisted prediction of the mechanical properties of Cu-Al alloy

Cited by 34 publications

References 28 publications

Emergent Opportunities with Metallic Alloys: From Material Design to Optical Devices

Emergent Opportunities with Metallic Alloys: From Material Design to Optical Devices

Prediction of Mechanical Properties of Three-Dimensional Printed Lattice Structures Through Machine Learning

Predicting Mechanical Properties of 3D Printed Lattice Structures

Contact Info

Product

Resources

About