Search Results for machine learning

This article is an informal discussion among three industry leaders about how additive manufacturing is impacted by new data-driven technologies. The panelists are Elizabeth A. Holm, James C. Williams, and Edward D. Herderick; the discussion is moderated by Hanchen Huang. The discussion is a preview for an IMAT 2020 panel session on the same topic organized by the ASM Emerging Technologies Awareness Committee.

This article demonstrates the application of machine learning to the classification and segmentation of bainitic microstructures and compares three approaches for assigning the ground truth: correlative microscopy using EBSD as an additional information source, comparison with images obtained from specially produced reference samples, and unsupervised learning.

Vision-based machine learning systems for microstructural characterization and analysis are being successfully used for image classification, semantic and instance segmentation, and object detection, leading to accurate, autonomous, objective, and repeatable results.

This article starts with a synopsis of machine learning (ML) and explores the characteristics of ML algorithms. It then reports on the results of two recently completed research projects investigating the potential use of ML to establish additive manufacturing materials property allowables. Although continued research and development work is required, the results are very promising.

This article provides a brief overview of the many ways that artificial intelligence and machine learning are being used for materials and manufacturing research. Several case studies show how the discovery, development, and deployment of novel materials are being dramatically accelerated through automation and data-driven models.

This article describes highlights from a panel held at IMAT 2024. Representatives from industry, government, and academia discussed the potential that artificial intelligence and machine learning offer the materials science and manufacturing communities. David Furrer, Pratt & Whitney, moderated the panel. The panelists were Seth Kimble, ASM International; Joshua Stuckner, NASA Glenn Research Center; James E. Saal, Citrine Informatics; and S. Mohadeseh Taheri-Mousavi, Carnegie Mellon University. Each panelist provided their perspective on how AI and ML are impacting current and future materials design and manufacturing processes.

An in-depth understanding of technology trends not only keep materials engineers relevant, but also puts them in the driver’s seat when it comes to formulating strategies and executing projects. Some of today’s technology trends that are relevant to materials engineers include data analytics, artificial intelligence (machine learning and deep learning), blockchain, digital thread and digital twins, Internet of Things (IoT) or Industry 4.0, additive manufacturing, electric vehicles, and autonomous vehicles.

A novel framework including experimental and model-based techniques saves time and enables the introduction of new alloys for additive manufacturing. This article describes the first phase of the probabilistic machine learning framework that was successfully demonstrated to rapidly define optimum parameter sets for commercial high-temperature nickel superalloys, as well as to guide alloy design and selection for compatibility with laser powder bed fusion additive manufacturing.

Highlights from a member survey and panel discussion outlining the challenges and benefits of advanced manufacturing for the materials community. The article covers research being conducted in academia and industry to develop and integrate advanced manufacturing techniques; methods for in-process monitoring and machine learning; and challenges in adopting new digital manufacturing technologies.

This article describes new software that helps predict properties of high-entropy alloy compositions under high-temperature conditions. The tool was developed by extensive testing on the quinary Al-Co-Cr-Fe-Ni alloy system with both first-principles density functional theory calculations and machine learning to establish a substantial database for modeling.

Designed with key input from members, ASM International’s new Data Ecosystem provides a digital platform to assist engineering design and manufacturing stakeholders working in the Materials 4.0 era.

Synergistic performance can be achieved by integrating judgment-focused humans and prediction-focused AI agents. This article discusses general developments in this area and potential implications for materials innovation in semiconductor devices.

Ford Motor Company’s stamping division looks to leap into Industry 4.0 the same way Henry Ford led the transformation from Industry 1.0 to 2.0.

The integration of artificial intelligence for predictive modeling and adaptive learning allows manufacturers to achieve unprecedented levels of efficiency and precision in ceramic additive manufacturing products.

ASM International’s strong strategic plan now includes a focus on financials, to ensure that the Society is ready for the next generation, in addition to building and marketing digital-first products and forming collaborations across disciplines and continents.

Digital image correlation data and Bayesian inference used together facilitate rigorous quantification of the uncertainty in material input parameters for finite element simulations of superelastic deformation.

Industrial computed tomography data analysis is harnessing deep learning to both accelerate in-line inspection and build better products. This article includes a case history involving deep learning industrial CT scan data analysis.

News about ASM members, chapters, events, awards, conferences, affiliates, and other society activities. Topics include: ASM affiliate societies name committee chairs for the 2019-2020 term; ASM President Zi-Kui Liu discusses the ASM response to Materials 4.0 and the Materials Genome Initiative; progress report on the ASM strategic plan; professional profile for Danielle Cote.

To learn about the latest trends in advanced materials, we turned to four of ASM’s thought leaders: John Ågren, KTH Royal Institute of Technology; George T. (Rusty) Gray III, Los Alamos National Laboratory; Jennie S. Hwang, H-Technologies Group; and David K. Matlock, Colorado School of Mines. This article presents their perspectives on the future of engineered materials, key areas of opportunity, and what ASM can do to support the next generation of materials scientists and engineers.

This article reports on outcomes from an additive manufacturing workshop that developed guidelines for AM data management to realize the promise of Materials 4.0 and achieve process qualification for AM parts.