基于约束近似动态规划的自适应反馈控制。
Adaptive feedback control by constrained approximate dynamic programming.
作者信息
Ferrari Silvia, Steck James E, Chandramohan Rajeev
机构信息
Department of Mechanical Engineering, Duke University, Durham, NC 27708, USA.
出版信息
IEEE Trans Syst Man Cybern B Cybern. 2008 Aug;38(4):982-7. doi: 10.1109/TSMCB.2008.924140.
A constrained approximate dynamic programming (ADP) approach is presented for designing adaptive neural network (NN) controllers with closed-loop stability and performance guarantees. Prior knowledge of the linearized equations of motion is used to guarantee that the closed-loop system meets performance and stability objectives when the plant operates in a linear parameter-varying (LPV) regime. In the presence of unmodeled dynamics or failures, the NN controller adapts to optimize its performance online, whereas constrained ADP guarantees that the LPV baseline performance is preserved at all times. The effectiveness of an adaptive NN flight controller is demonstrated for simulated control failures, parameter variations, and near-stall dynamics.
提出了一种约束近似动态规划（ADP）方法，用于设计具有闭环稳定性和性能保证的自适应神经网络（NN）控制器。利用线性化运动方程的先验知识，以确保当被控对象在线性参数变化（LPV）状态下运行时，闭环系统满足性能和稳定性目标。在存在未建模动态或故障的情况下，NN控制器进行自适应调整以在线优化其性能，而约束ADP则保证始终保持LPV基线性能。针对模拟的控制故障、参数变化和近失速动态，演示了自适应NN飞行控制器的有效性。
Zotero 插件