External Resources
Physics-Informed Machine Learning by Dr. Navid Zobeiry
Section 1 - Introduction, Part 1
Topic: The motivation for PIML and how integrating physics-based constraints with machine learning (ML) can address complex multi-physics challenges in engineering.
Section 1 - Introduction, Part 2
Topic: Data collection, model optimization, and uncertainty quantification in physics-based machine learning.
Section 1 - Introduction, Part 3
Topic: Overview of Neural Networks (NNs) for regression and their application in deterministic modeling
Section 1 - Introduction, Part 4
Section 2 - Case Study on Heat Transfer, Part 1
Section 2 - Case Study on Heat Transfer, Part 2
Topic: Gain insight into probabilistic modeling using Gaussian Process Regression (GPR) and explore Ensemble Methods
Topic: A detailed case study on heat transfer during the combined convection and conduction heating of a part in an oven.
Topic: Developing several physics-informed machine learning models using techniques such as Physics-Informed Features, Physics-Informed Loss, Physics-Informed Domain Transformation, and Physics-Informed Neural Networks (PINNs)
Section 3 - Case Study on Discovering Chemical Reactions
Topic: The application of Physics-Informed Machine Learning (PIML) to chemical reaction dynamics using Sparse Identification of Nonlinear Dynamics (SINDy)
Section 4 - Case Study on 3D Printing
Topic: Exploring the application of Physics-Informed Machine Learning (PIML) for predicting the properties of additively manufactured parts.
Section 5 - Case Study on Adhesive Bonding Strength
Topic: This final case study analyzes adhesive bonding failure using Gaussian Process Regression (GPR)
External Webinars
SAMPE webinar 7/17/24
Topic: A New Laminate Theory: Simplified, Invariant, and Universal
​
Speaker:
Dr. Stephen W. Tsai
Stanford University
Veryst Engineering Webinar 10/22/24
Topic: Practical Materials Structure and Characterization
​
​Speaker:
Dr. Scott Grindy