Materials Process Modeling Machine-Learning

About the Research

This project will encompass modeling of quantitative parts performance relationships using state‑of‑the‑art machine‑learning technologies and tools. In traditional design, process optimization and part optimization are performed independently, ignoring the inherent dependence of materials and part properties on processing conditions. In this project, ML models will extract cross‑property and inverse functions in a holistic framework of the scientific design and production process.

Organization

DEVCOM Army Research Laboratory

Reference Code

ARL-R-WMRD-300093

Candidate Requirements

• Well‑versed in the application and/or development of probabilistic graph models, dimensionality reduction and featurization, or neural networks for materials science or process modeling.
• Experience with computational materials science or engineering is appreciated but not necessary.
• Experience with software engineering is highly respected.

Keywords

• materials science
• machine‑learning
• process modeling
• artificial neural networks
• dimensionality reduction
• probabilistic graphical models
• software engineering
• data science

Advisor :

B. Christopher Rinderspacher

Advisor Email : berend.c.rinderspacher.civ

Eligibility Requirements

• Citizenship: U.S. Citizen Only
• Degree:
  Bachelor’s Degree, Master’s Degree, or Doctoral Degree
• Academic Level(s):
  Any academic level
• Discipline(s):
  Chemistry and Materials Sciences, Computer, Information, and Data Sciences, Engineering, Mathematics and Statistics, Physics
• Age:
  Must be 18 years of age