Model Predictive Control With Guaranteed Feasibility of Inequality Path Constraints
针对非线性模型预测控制中路径约束只能在有限时间点满足、无法保证全程可行的问题，提出一种结合半无限规划与事件触发采样的新框架，在保证约束可行性的同时降低计算负担，并给出闭环系统渐近收敛的充分条件。
This article concerns nonlinear model predictive control (MPC) with guaranteed feasibility of inequality path constraints (PCs). For MPC with PCs, the existing methods, such as direct multiple shooting, cannot guarantee feasibility of PCs because the PCs are enforced at finitely many time points only. Therefore, this article presents a novel MPC framework that is capable of not only achieving stability control but also guaranteeing feasibility of PCs during the rolling optimization stages of MPC. Under the above MPC framework, an algorithm is first proposed by applying the semi-infinite programming technique to the rolling optimization of MPC. However, it takes heavy computational time to achieve guaranteed feasibility of PCs. Therefore, to guarantee feasibility of PCs meanwhile effectively reducing the computation burden of the closed-loop system, an event-triggered sampling mechanism is constructed in the above path-constrained MPC algorithm. Moreover, sufficient conditions are given for asymptotic convergence of the closed-loop systems. Finally, the effectiveness of the proposed results is illustrated via a cart-damper-spring system.