Artificial Intelligence for Engineering Design and Computational Mechanics

Ramin Bostanabad, University of California, Irivine
AI for engineering design and computational mechanics


Engineered systems are an indispensable part of our modern life with far-reaching applications that include aerial and ground transportation, electronics, large-scale structures, and medicine. The ever-evolving societal, environmental, and cultural awareness calls for significantly complex systems with unprecedented properties that reliably meet stakeholders’ demands under extreme conditions. To accelerate the design and deployment of such systems while reducing the reliance on costly and time-consuming experiments, it is necessary to develop advanced computational methods that streamline their design and analysis process.

In this talk, I will present some of our recent works for solving challenging problems in engineering design, solid mechanics, and fluid dynamics. In particular, I will demonstrate how we can (1) drastically accelerate multiscale simulations of cast alloys via mechanistic reduced order models, surrogate plastic and history-dependent deformation of fiber composites with deep learning, optimize material composition with latent map Gaussian processes and Bayesian optimization, and (4) solve partial differential equations such as the Navier-Stokes equations with transfer learning. 

Bio: Dr. Ramin Bostanabad received his Ph.D. in February 2019 from Northwestern University where his research was recognized with a number of awards including Terminal Year Fellowship, Martin Outstanding doctoral Fellowship, Predictive Science and Engineering Design Fellowship, and Walter P. Murphy Fellowship. He joined the Department of Mechanical and Aerospace Engineering at UCI in September 2019 and founded the Probabilistic Modeling and Analysis of Complex Systems (PMACS) laboratory. At PMACS lab, Dr. Bostanabad’s group develops computational framework and tools for analyzing and designing complex systems such as multiscale materials. These contributions have been so far supported by NSF, ARPA-E, and Advanced Casting Research Center and are at the interface of computational statistics, scientific machine learning, and computational mechanics. Recent applications have been on data-driven microstructure characterization, multi-scale materials modeling with deep learning and random processes, inverse system identification with evolutionary programming, and assimilation of multiple data sources with Bayesian statistics.

BlueJeans Link: