This paper presents a cooperative fault diagnosis scheme for a class of uncertain nonlinear multiagent systems component and sensor faults in individual agents. Since the faulty system affects the healthy systems through interconnections, for each agent an estimator is designed to collect neighboring output estimations errors to consider its faulty effects on others, when computing its estimations for local state and faulty parameters. A new structure of distributed estimators is proposed by filtering regressor signals and sharing them among agents. Then, the sharings of signals are planned by properly constructing auxiliary graphs for undirected and directed networks. Two conditions are given to preselect estimators parameters for the convergences of the estimation errors. Unlike the existing results dealing with one common parameter with full state measurement and only for undirected graphs, this paper presents an output measurementbased approach for multiple parameters in undirected/directed networks. It shows that for the faults not providing persistent excitation in a signal agent, it is possible to estimate the faults exactly if the they excite all agents persistently. A simulation example of a group of single-link flexible-joint robots is given to verify the effectiveness of the proposed method.

中文翻译：

---

基于自适应分布式模糊估计的不确定非线性多智能体系统协同故障诊断


针对一类不确定非线性多智能体系统中各个智能体的部件和传感器故障，提出了一种协同故障诊断方案。由于故障系统通过互连影响健康系统，因此对于每个代理，设计了一个估计器来收集邻近的输出估计误差，以在计算其对本地状态和故障参数的估计时考虑其对其他系统的故障影响。通过过滤回归信号并在代理之间共享它们，提出了一种新的分布式估计器结构。然后，通过正确构建无向和有向网络的辅助图来规划信号的共享。给出了两个条件来预选估计器参数以实现估计误差的收敛。与处理具有全状态测量的一个公共参数且仅适用于无向图的现有结果不同，本文提出了一种针对无向/有向网络中的多个参数的基于输出测量的方法。它表明，对于未在信号代理中提供持续激励的故障，如果它们持续激励所有代理，则可以准确估计故障。给出了一组单连杆柔性关节机器人的仿真实例，验证了该方法的有效性。