期刊
IET CONTROL THEORY AND APPLICATIONS
卷 16, 期 2, 页码 139-150出版社
WILEY
DOI: 10.1049/cth2.12207
关键词
-
资金
- Core Research for Evolutional Science and Technology [JPMJCR2012]
- Japan Society for the Promotion of Science [21H01352]
- OsakaUniversity Start-Up Research Fund of the Graduate School of Information Science and Technology
- Grants-in-Aid for Scientific Research [21H01352] Funding Source: KAKEN
This paper proposes a computational technique to solve discrete-time optimal control problems for nonlinear systems, utilizing deep unfolding and deep learning methods to optimize control inputs that would otherwise be difficult to obtain. Numerical experiments demonstrate the effectiveness of this approach.
This paper proposes a computational technique to solve discrete-time optimal control problems for nonlinear systems subject to stochastic disturbances, hard input constraints, and soft constraints. The approach employs the idea of deep unfolding, which is a recently developed model-based deep learning method that is applicable to iterative algorithms. By regarding each state transition of the dynamical system as an iteration step, these state transitions are unfolded into the layers of a deep neural network. This produces a computational graph that contains trainable parameters that determine control inputs. These parameters are optimized by training the deep neural network using the standard deep learning technique of backpropagation and incremental training. Then, the optimal control inputs are obtained from the optimized parameters. This provides a way to optimize the control inputs that otherwise would be difficult to obtain. The effectiveness of the proposed technique is demonstrated by numerical experiments for the maximum hands-off control problem and constrained model predictive control problems using a highly nonlinear model of a continuous stirred tank reactor.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据