Approximate Closed-Loop Robust Model Predictive Control With Guaranteed Stability and Constraint Satisfaction
Approximate Closed-Loop Robust Model Predictive Control With Guaranteed Stability and Constraint Satisfaction
复制标题
具有保证稳定性和约束满足的近似闭环鲁棒模型预测控制
DOI：
10.1109/lcsys.2020.2980479
复制
发表时间：
2020
影响因子：
3
通讯作者：
A. Mesbah
中科院分区：
文献类型：
--
作者：
J. Paulson;A. Mesbah
闭环鲁棒模型预测控制（MPC）方案的实时实现对于快速系统来说是一个重要的挑战，因为它们的解决方案复杂性在很大程度上取决于系统规模、控制策略参数化和预测范围。我们希望通过使用深度学习近似隐式定义的 MPC 控制器来解决这个问题。尽管所得的神经网络近似具有较小的内存占用并且可以有效地计算，但它不能保证鲁棒的约束满足或稳定性。我们提出了一种新颖的基于投影的策略，能够实时提供强大的可行性和输入状态稳定性的证书。我们还展示了如何将该投影算子表示为可离线求解的参数二次规划。所提出方法的优点在基准案例研究中得到了证明。
The real-time implementation of closed-loop robust model predictive control (MPC) schemes is an important challenge for fast systems, as their solution complexity depends strongly on the system size, control policy parametrization, and prediction horizon. We look to address this problem by approximating the implicitly-defined MPC controller using deep learning. Although the resulting neural network approximation has a small memory footprint and can be efficiently computed, it does not guarantee robust constraint satisfaction or stability. We propose a novel projection-based strategy that is capable of providing a certificate of robust feasibility and input-to-state stability in real-time. We also show how this projection operator can be formulated as a parametric quadratic program that is solvable offline. The advantages of the proposed approach are demonstrated on a benchmark case study.
线性约束系统$lambda$-收缩集的计算
影响因子：
6.8
作者：
M. Schulze Darup;M. Cannon
通讯作者：
M. Cannon
影响因子：
4.2
作者：
Lucia, Sergio;Finkler, Tiago;Engell, Sebastian
通讯作者：
Engell, Sebastian