Harnessing Legacy Data to Educate Data-Enabled Structural Materials Engineers
- PDF / 555,873 Bytes
- 9 Pages / 432 x 648 pts Page_size
- 53 Downloads / 215 Views
MRS Advances © 2020 Materials Research Society DOI: 10.1557/adv.2020.132
Harnessing Legacy Data to Educate Data-Enabled Structural Materials Engineers Jennifer L.W. Carter1, Amit K. Verma1,2, Nishan M. Senanayake1 1 Case Western Reserve University, Department of Materials Science and Engineering, Cleveland OH, 44106, USA, [email protected] 2
Carnegie Mellon University, Department of Materials Science and Engineering, Pittsburgh, PA, 15213, USA
ABSTRACT Data-driven materials design informed by legacy data-sets can enable the education of a new workforce, promote openness of the scientific process in the community, and advance our physical understanding of complex material systems. The performance of structural materials, which are controlled by competing factors of composition, grain size, particle size/distribution, residual strain, cannot be modelled with single-mechanism physics. The design of optimal processing route must account for the coupled nature of the creation of such factors, and requires students to learn machine learning and statistical modelling principles not taught in the conventional undergraduate or graduate level Materials Science and Engineering curricula. Therefore, modified curricula with opportunities for experiential learning are paramount for workforce development. Projects with real-world data provide an opportunity for students to establish fluency in the iterative steps needed to solve relevant scientific and engineering process design questions.
INTRODUCTION: Materials Data-Science, also known as Materials Informatics, is an emerging sub-field in research and development of materials [1]. The integration of data science, machine learning, deep learning, and artificial intelligence techniques into the materials discovery, design, and processing of materials [2] is poised to provide the integration of theory, computation, and experimental metrics needed to enable the visions of the integrated materials science engineering (ICME), and Materials Genome Initiative [3]. Additionally, both the impending retirement of the baby boomer generation, and expectation of millennial engineers that they will change companies over the course of their careers, each pose a knowledge loss to many industries [4]. Developing company319
Downloaded from https://www.cambridge.org/core. Macquarie University, on 30 May 2020 at 16:57:56, subject to the Cambridge Core terms of use, available at https://www.cambridge.org/core/terms. https://doi.org/10.1557/adv.2020.132
owned and open-databases and training of the next generation workforce to be dataenabled material engineers is of strategic importance to the materials science community to counter these potential knowledge losses [5,6]. There is an apparent disconnect between the materials design lifecycle, and the addition of machine learning to the design process. The Materials Design lifecycle, from discovery to implementation is long, Figure 1. Once discovery has occurred, the process of designing optimal microstructures and processing routes requires that w
Data Loading...
