A learning- and scenario-based MPC design for nonlinear systems in LPV framework with safety and stability guarantees
A learning- and scenario-based MPC design for nonlinear systems in LPV framework with safety and stability guarantees
复制标题
DOI：
10.1080/00207179.2023.2212814
复制
发表时间：
2022-06
影响因子：
2.1
通讯作者：
Yajie Bao;H. S. Abbas;J. Mohammadpour
中科院分区：
文献类型：
--
作者：
Yajie Bao;H. S. Abbas;J. Mohammadpour
摘要针对线性变参数（LPV）模型系统，提出了一种基于学习和神经网络的模型预测控制（MPC）设计方法。使用从系统中收集的输入输出数据，状态空间LPV模型与不确定性量化的第一次学习通过变分贝叶斯推理神经网络（BNN）的方法。学习的概率模型被假设为包含具有高概率的系统的真实动态，并且用于生成确保基于MIMO的MPC的安全性的场景。此外，为了保证闭环系统的稳定性和提高性能，一个参数依赖的终端成本和控制器，以及终端鲁棒正不变集的设计。数值例子将被用来证明所提出的控制设计方法可以确保安全性，并达到预期的控制性能。
ABSTRACT This paper presents a learning- and scenario-based model predictive control (MPC) design approach for systems modelled in the linear parameter-varying (LPV) framework. Using input-output data collected from the system, a state-space LPV model with uncertainty quantification is first learned through the variational Bayesian inference Neural Network (BNN) approach. The learned probabilistic model is assumed to contain the true dynamics of the system with a high probability and is used to generate scenarios that ensure safety for a scenario-based MPC. Moreover, to guarantee stability and enhance the performance of the closed-loop system, a parameter-dependent terminal cost and controller, as well as a terminal robust positive invariant set are designed. Numerical examples will be used to demonstrate that the proposed control design approach can ensure safety and achieve desired control performance.