Materials Prognosis from Integrated Modeling & Experiment (M’) Lab
Research Scope
The M’ Lab researches emergent structural and material prognosis issues that involve the multiscale and stochastic nature of plasticity and fatigue cracking in structural materials. The research objective of the group is to leverage the ever-increasing capabilities in experimental observation and data analysis tools to provide new capabilities for prognosing reliability of advanced engineered structures and materials.Open Source Software
The M' Lab contributes to the open-source code, Bingo.- Bingo is an open source package for performing symbolic regression, though it can be used as a general purpose evolutionary optimization package. Go to the Bingo github page.
Recent Publications
- (2025) Learning implicit yield surface models with uncertainty quantification for noisy datasets
- (2024) Modeling plasticity-mediated void growth at the single crystal scale: A physics-informed machine learning approach
- (2024) Stress intensity factor models using mechanics-guided decomposition and symbolic regression
- (2024) Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients
- (2024) On the validity of the Tada stress intensity factor solution for the single edge notch tension specimen with pinned ends
Good News
- Congratulations to Will Jenkins for passing his proposal defense titled, "Leveraging physics-informed machine learning to develop material models for ceramic matrix composites"
- Congratulations to Sam Parry for passing his thesis defense titled, "Predicting mesh quality for boundary representations: A machine learning driven defeaturing method"