CSE Community Seminar

April 19, 2024, 12 PM

AI for Design: unsteady prediction of a dynamical system in the parametric design space

Hamid R. Karbasian
Postdoctoral Research Associate
Department of Mechanical Engineering, MIT

Abstract:

The ability to efficiently predict unsteady flow fields is imperative for exploration, control, and performance optimization within the design space of a given problem. In many engineering problems, case studies rely on large amounts of numerical simulations or, in some cases, experimental runs, each one of which requires a spatio-temporal evolution of the flow field associated with a different set of design parameters. Data-driven Reduced-Order Models (ROMs) pose an attractive pathway to capture low-dimensional patterns and system dynamics based on a small set of high-fidelity training data. These models can then be used in a design or optimization pipeline for low-cost, high-throughput prediction of flow results. In this work, we developed a ROM to robustly predict the dynamics of fluid flows across a parametric design space. Our approach extends a Long-Short Term Memory (LSTM) neural network with a new design gate, which enables the network to distinguish dynamic patterns associated with different design parameters. The parametric LSTM (pLSTM) can successfully predict the long-time dynamics of the flow field for unseen design parameters while showing exceptional robustness to noise in the initial states. The proposed pLSTM offers a three-aspect ROM approach (space, time, design space) to benefit prediction, optimization, and control problems across parametric flow regimes.

Bio:

Dr. Hamid R. Karbasian is currently a Postdoctoral Associate in the Department of Mechanical Engineering at the Massachusetts Institute of Technology (MIT). His research work focuses on developing mathematical algorithms and leveraging digital twins for fluid mechanics and aerospace applications. Before joining MIT, he was awarded the Fields CQAM Postdoctoral Fellowship at the Fields Institute at the University of Toronto, where he developed a deep-learning-based model for fluid dynamics in a Lagrangian system. He was also a Lead Aerospace Engineer at Limosa Inc., where he led the aerodynamics division toward developing a new concept of air taxi for urban air mobility. He has a Ph.D. in Mechanical Engineering from Concordia University in Canada with a focus on computational science. He has more than 30 publications in well-known journals and international conference presentations. Dr. Karbasian is also the founder of the OPtimization Toolkit for Highly NOn-linear Systems (OPTHiNOS) scientific software package, a specialized framework to perform sensitivity analysis and optimization of large-scale engineering problems.

April 19, 2024 CSE Community Seminar
Hamid R. Karbasian
Postdoctoral Research Associate
Department of Mechanical Engineering, MIT