PhD position on Physics-Guided Digital Twin Development
Core
Develop a physics-guided digital twin framework for magnesium alloys by integrating crystal plasticity, phase-field modeling, precipitation modeling, and machine learning to predict microstructure evolution and mechanical properties.
Role type
PhD researcher in computational materials engineering and machine learning
Builds
A unified physics-guided digital twin framework for advanced lightweight materials
Domain
Materials science, computational mechanics, machine learning
Deliverable
production ML models
Required skills
Python programming, machine learning, crystal plasticity, phase-field modeling, experimental data analysis, uncertainty quantification, explainable AI (XAI)
Preferred skills
Finite element methods, thermodynamic simulations, analysis of microstructure data
Technologies
Python, PyTorch, Scikit-Learn, SEM, EBSD, XRD
Responsibilities
Develop physics-guided ML models for composition-process-structure-property relationships; Combine crystal plasticity, phase-field, and ML into a unified framework; Implement simulation and ML workflows; Incorporate experimental characterization data; Investigate uncertainty quantification and XAI; Validate computational predictions; Publish scientific results
Seniority
PhD candidate