Liang Dingguo, Ren Yunxiao, Lv Yuezu, Wang Silong
Department of Mechanics and Engineering Science, College of Engineering, Peking University, Beijing 100871, China.
Advanced Research Institute of Multidisciplinary Sciences, Beijing Institute of Technology, Beijing 100081, China.
Sensors (Basel). 2024 Nov 27;24(23):7589. doi: 10.3390/s24237589.
This paper focuses on simultaneous estimation of states and faults for a linear time-invariant (LTI) system observed by sensor networks. Each sensor node is equipped with an observer, which uses only local measurements and local interaction with neighbors for monitoring. The observability of said observer is analyzed where non-local observability of a sensor node is required in terms of the system state and faults. The distributed observers present features of H∞ performance to constrain the influence of disturbances on the estimation errors, for which the global design condition is transformed into a linear matrix inequality (LMI). The LMI is proven to be solvable given collective observability of the system and a suitable H∞ performance index. Moreover, in the case that no disturbances exist, fully distributed observers with adaptive gains are designed to asymptotically estimate the states and faults without using any global information from the network. Finally, the effectiveness of the proposed methods is verified through case studies on a spacecraft's attitude control system.
本文聚焦于通过传感器网络观测的线性时不变（LTI）系统的状态和故障的同时估计。每个传感器节点都配备有一个观测器，该观测器仅使用局部测量值以及与邻居的局部交互来进行监测。分析了所述观测器的可观测性，其中根据系统状态和故障需要传感器节点的非局部可观测性。分布式观测器具有H∞性能特征，以限制干扰对估计误差的影响，为此将全局设计条件转化为线性矩阵不等式（LMI）。证明了给定系统的集体可观测性和合适的H∞性能指标时，该LMI是可解的。此外，在不存在干扰的情况下，设计了具有自适应增益的完全分布式观测器，以在不使用来自网络的任何全局信息的情况下渐近估计状态和故障。最后，通过对航天器姿态控制系统的案例研究验证了所提方法的有效性。
