Deep model predictive flow control with limited sensor data and online learning
| Autor: | J. Nathan Kutz, Steven L. Brunton, Katharina Bieker, Sebastian Peitz, Michael Dellnitz |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Fluid Flow and Transfer Processes
Flow control (data) 0209 industrial biotechnology Computer science business.industry Deep learning General Engineering Computational Mechanics Control engineering 02 engineering and technology Condensed Matter Physics Artificial respiration Optimal control 01 natural sciences 010305 fluids & plasmas Model predictive control Nonlinear system 020901 industrial engineering & automation Recurrent neural network Flow (mathematics) 0103 physical sciences Artificial intelligence business |
| Zdroj: | Theoretical and Computational Fluid Dynamics. 34:577-591 |
| ISSN: | 1432-2250 0935-4964 |
| Popis: | The control of complex systems is of critical importance in many branches of science, engineering, and industry, many of which are governed by nonlinear partial differential equations. Controlling an unsteady fluid flow is particularly important, as flow control is a key enabler for technologies in energy (e.g., wind, tidal, and combustion), transportation (e.g., planes, trains, and automobiles), security (e.g., tracking airborne contamination), and health (e.g., artificial hearts and artificial respiration). However, the high-dimensional, nonlinear, and multi-scale dynamics make real-time feedback control infeasible. Fortunately, these high-dimensional systems exhibit dominant, low-dimensional patterns of activity that can be exploited for effective control in the sense that knowledge of the entire state of a system is not required. Advances in machine learning have the potential to revolutionize flow control given its ability to extract principled, low-rank feature spaces characterizing such complex systems. We present a novel deep learning model predictive control framework that exploits low-rank features of the flow in order to achieve considerable improvements to control performance. Instead of predicting the entire fluid state, we use a recurrent neural network (RNN) to accurately predict the control relevant quantities of the system, which are then embedded into an MPC framework to construct a feedback loop. In order to lower the data requirements and to improve the prediction accuracy and thus the control performance, incoming sensor data are used to update the RNN online. The results are validated using varying fluid flow examples of increasing complexity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |