Data-enabled predictive control (DeePC) is a data-driven control algorithm that utilizes data matrices to form a non-parametric representation of the underlying system, predicting future behaviors and generating optim...
详细信息
Data-enabled predictive control (DeePC) is a data-driven control algorithm that utilizes data matrices to form a non-parametric representation of the underlying system, predicting future behaviors and generating optimal control actions. DeePC typically requires solving an online optimization problem, the complexity of which is heavily influenced by the amount of data used, potentially leading to expensive online computation. In this article, we leverage deep learning to propose a highly computationallyefficient DeePC approach for general nonlinear processes, referred to as Deep DeePC. Specifically, a deep neural network is employed to learn the DeePC vector operator, which is an essential component of the non-parametric representation of DeePC. This neural network is trained offline using historical open-loop input and output data of the nonlinear process. With the trained neural network, the Deep DeePC framework is formed for online control implementation. At each sampling instant, this neural network directly outputs the DeePC operator, eliminating the need for online optimization as conventional DeePC. The optimal control action is obtained based on the DeePC operator updated by the trained neural network. To address constrained scenarios, a constraint handling scheme is further proposed and integrated with the Deep DeePC to handle hard constraints during online implementation. The efficacy and superiority of the proposed Deep DeePC approach are demonstrated using two benchmark process examples.
In this note two related problems for stabilization of a class of Lipschitz nonlinear systems are considered. (1) observer design for the estimation of system states (2) observer based controller design which consists...
详细信息
ISBN:
(纸本)9781457708398
In this note two related problems for stabilization of a class of Lipschitz nonlinear systems are considered. (1) observer design for the estimation of system states (2) observer based controller design which consists of two parts: observer part that estimates system states from the measured ones and a linear feedback part that utilizes these estimated states. A Lyapunov-based stability analysis is developed to show that this computationally efficient controller results in global asymptotic stability of the estimation and tracking error. An interesting feature of the developed method is that it can be used for a wide class of mechanical systems including serial and parallel robotic systems with kinematic constraints. Numerical validations of the proposed method on a slider crank as a sample of constrained robotic systems is presented.
暂无评论