Physics-Enhancing Machine Learning Strategies in Applied Solid Mechanics - Recent Advances

Explore recent advances in physics-enhancing machine learning strategies for applied solid mechanics in this comprehensive seminar. Delve into the challenges and solutions in integrating Machine Learning techniques with physics-based knowledge in the field of solid mechanics. Examine the use of Physics-informed Machine Learning to address issues such as limited data availability, generalization in small to medium data scenarios, and enforcing physics constraints with large datasets. Gain insights into the complexities of integrating data and physics-based models, including uncertainty quantification, result interpretability, and handling small, heterogeneous, gappy, and noisy data. Learn about cutting-edge research conducted by the Data, Vibration and Uncertainty Group, focusing on enhanced strategies in structural health monitoring and friction force evaluation. Discover how these advancements are revolutionizing computational efficiency, improving modeling and forecasting, and enabling more accurate information extraction in applied solid mechanics.