A multi-task learning-based optimization approach for finding diverse sets of microstructures with desired properties

Iraki, Tarek; Morand, Lukas; Dornheim, Johannes; Link, Norbert; Helm, Dirk

doi:10.1007/s10845-023-02139-8

Cited by 6 publications

(4 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be enforced by using e.g. siamese neural networks [3]. It still remains crucial that the original texture representation contains the essential information about the properties.…”

Section: Texture Representations For Learning Texture-property Relationsmentioning

confidence: 99%

“…Nevertheless, for the purposes of this paper, the computationally inexpensive Taylor-type material model is sufficient. Other descriptions of the Taylor-type material model used in this study can be found in [2,3].…”

Section: Appendix C Taylor-type Materials Modelmentioning

confidence: 99%

“…Then it is important to know how far the actual texture of the process path is away from the target [2]. The knowledge of texture distances is also required for the design of textures for given desired properties [3].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accurate distances measures and machine learning of the texture-property relation for crystallographic textures represented by one-point statistics

Iraki,

Morand,

Link

et al. 2024

Modelling Simul. Mater. Sci. Eng.

View full text Add to dashboard Cite

The crystallographic texture of metallic materials is a key microstructural feature that is responsible for the anisotropic behavior, e.g., important in forming operations. In materials science, crystallographic texture is commonly described by the orientation distribution function, which is defined as the probability density function of the orientations of the monocrystal grains conforming a polycrystalline material. For representing the orientation distribution function, there are several approaches such as using generalized spherical harmonics, orientation histograms, and pole figure images . Measuring distances between crystallographic textures is essential for any task that requires assessing texture similarities, e.g. to guide forming processes. Therefore, we introduce novel distance measures based on (i) the Earth Movers Distance that takes into account local distance information encoded in histogram-based texture representations and (ii) a distance measure based on pole figure images. For this purpose, we evaluate and compare existing distance measures for selected use-cases. The present study gives insights into advantages and drawbacks of using certain texture representations and distance measures with emphasis on applications in materials design and optimal process control.

show abstract

“…This can be enforced by using e.g. siamese neural networks [3]. It still remains crucial that the original texture representation contains the essential information about the properties.…”

Section: Texture Representations For Learning Texture-property Relationsmentioning

confidence: 99%

Section: Appendix C Taylor-type Materials Modelmentioning

confidence: 99%

See 1 more Smart Citation

Accurate distances measures and machine learning of the texture-property relation for crystallographic textures represented by one-point statistics

Iraki,

Morand,

Link

et al. 2024

Modelling Simul. Mater. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…Optimization revealed a family of optimal microstructures with uniaxial tensile strength comparable to that of the optimal microstructure. Iraki et al [129] developed an approach for the optimization of crystallographic textures with the desired properties of cold-rolled DC04 steel sheet. Their machine learning model combined a multi-task learning-based approach with Siamese multi-task learning (SMTL) ANNs.…”

Section: Auto-encoders (Aes)mentioning

confidence: 99%

Artificial Intelligence in Predicting Mechanical Properties of Composite Materials

Kibrete,

Trzepieciński,

Gebremedhen

et al. 2023

J. Compos. Sci.

View full text Add to dashboard Cite

The determination of mechanical properties plays a crucial role in utilizing composite materials across multiple engineering disciplines. Recently, there has been substantial interest in employing artificial intelligence, particularly machine learning and deep learning, to accurately predict the mechanical properties of composite materials. This comprehensive review paper examines the applications of artificial intelligence in forecasting the mechanical properties of different types of composites. The review begins with an overview of artificial intelligence and then outlines the process of predicting material properties. The primary focus of this review lies in exploring various machine learning and deep learning techniques employed in predicting the mechanical properties of composites. Furthermore, the review highlights the theoretical foundations, strengths, and weaknesses of each method used for predicting different mechanical properties of composites. Finally, based on the findings, the review discusses key challenges and suggests future research directions in the field of material properties prediction, offering valuable insights for further exploration. This review is intended to serve as a significant reference for researchers engaging in future studies within this domain.

show abstract

Semantic Orchestration and Exploitation of Material Data: A Dataspace Solution Demonstrated on Steel and Copper Applications

Nahshon,

Morand,

Büschelberger

et al. 2024

Adv Eng Mater

View full text Add to dashboard Cite

In materials science and manufacturing, vast amounts of heterogeneous data (e.g., measurement and simulation logs, process data, publications) serve as the bedrock of valuable knowledge for various engineering applications. However, efficiently storing and managing this diverse data pose challenges due to limited standardization and integration across different organizational units. Addressing these challenges is essential to fully unlock the potential of data‐driven approaches. This article introduces novel, comprehensive semantic methodology tailored to materials engineering and realized as a technology stack named Dataspace Management System (DSMS), which powers dataspace solutions that leverage the knowledge encoded in heterogeneous data sources to support data‐driven insights and to derive new knowledge. At its core, DSMS offers a distinctive knowledge management approach tuned to meet the specific requirements of the materials science and manufacturing domain, all while adhering to the FAIR (findable, accessible, interoperable, reusable) principles. DSMS provides functionalities for data integration, linkage, exploration, visualization, processing, data sharing, and services (e.g., consulting) to support engineers in decision‐making, design, and optimization. An architectural overview is presented, outlining core concepts and their technological implementation. In addition, the applicability of these concepts to common data processing tasks is demonstrated through use cases from the StahlDigital and KupferDigital research projects within Germany's MaterialDigital initiative.

show abstract

A multi-task learning-based optimization approach for finding diverse sets of microstructures with desired properties

Cited by 6 publications

References 64 publications

Accurate distances measures and machine learning of the texture-property relation for crystallographic textures represented by one-point statistics

Accurate distances measures and machine learning of the texture-property relation for crystallographic textures represented by one-point statistics

Artificial Intelligence in Predicting Mechanical Properties of Composite Materials

Semantic Orchestration and Exploitation of Material Data: A Dataspace Solution Demonstrated on Steel and Copper Applications

Contact Info

Product

Resources

About