Differentiable predictive control: Deep learning alternative to explicit model predictive control for unknown nonlinear systems
Top Cited Papers
Open Access
- 21 June 2022
- journal article
- research article
- Published by Elsevier in Journal of Process Control
- Vol. 116, 80-92
Abstract
No abstract availableKeywords
Funding Information
- Battelle (DE-AC05-76RL0-1830)
- Laboratory Directed Research and Development
- Pacific Northwest National Laboratory
- Agentúra Ministerstva Školstva, Vedy, Výskumu a Športu SR (VEGA 1/0545/20)
- Agentúra na Podporu Výskumu a Vývoja (APVV-20-0261)
- U.S. Department of Energy
- Vedecká Grantová Agentúra MŠVVaŠ SR a SAV
This publication has 54 references indexed in Scilit:
- DeepMPC: Learning Deep Latent Features for Model Predictive Control2015
- Combining the benefits of function approximation and trajectory optimization2014
- Complexity reduction of explicit model predictive control via separationAutomatica, 2013
- Stabilizing polynomial approximation of explicit MPCAutomatica, 2011
- Dynamic mode decomposition of numerical and experimental dataJournal of Fluid Mechanics, 2010
- Robust disturbance modeling for model predictive control with application to multivariable ill-conditioned processesJournal of Process Control, 2003
- On-line optimization via off-line parametric optimization toolsComputers & Chemical Engineering, 2002
- The explicit linear quadratic regulator for constrained systemsAutomatica, 2002
- Constrained model predictive control: Stability and optimalityAutomatica, 2000
- Stability of model predictive control with mixed constraintsIEEE Transactions on Automatic Control, 1995