{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-dynamical-modeling-and-control-of","title":"Deep Dynamical Modeling and Control of Unsteady Fluid Flows","arxiv_id":"1805.07472","date":"2018-05-18","proceeding":"NeurIPS 2018 12","authors":["Jeremy Morton","Freddie D. Witherden","Antony Jameson","Mykel J. Kochenderfer"],"abstract":"The design of flow control systems remains a challenge due to the nonlinear\nnature of the equations that govern fluid flow. However, recent advances in\ncomputational fluid dynamics (CFD) have enabled the simulation of complex fluid\nflows with high accuracy, opening the possibility of using learning-based\napproaches to facilitate controller design. We present a method for learning\nthe forced and unforced dynamics of airflow over a cylinder directly from CFD\ndata. The proposed approach, grounded in Koopman theory, is shown to produce\nstable dynamical models that can predict the time evolution of the cylinder\nsystem over extended time horizons. Finally, by performing model predictive\ncontrol with the learned dynamical models, we are able to find a\nstraightforward, interpretable control law for suppressing vortex shedding in\nthe wake of the cylinder.","url_abs":"http://arxiv.org/abs/1805.07472v2","url_pdf":"http://arxiv.org/pdf/1805.07472v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-dynamical-modeling-and-control-of","repo_url":"https://github.com/sisl/deep_flow_control","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-predictive-control","task_name":"Model Predictive Control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.07472","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}