Rapid Oscillation Fault Detection for Distributed System via Deterministic Learning

摘要：

　　In this paper,a rapid detection and isolation scheme for oscillation faults in a distributed nonlinear system is proposed based on a recent result on deterministic learning (DL) theory.The distributed nonlinear system considered is modeled as a set of interconnected subsystems.Firstly,a local learning and merging method based on DL is proposed to obtain knowledge of the unknown interconnections and the fault functions.Secondly,by utilizing learned knowledge,a bank of consensus-based dynamical estimators are constructed for each subsystem,and average L1 norms of the residuals are generated to make the detection and isolation decisions.Thirdly,a rigorous analysis for characterizing the detection and isolation capabilities of the proposed scheme is given.The attraction of the intelligence fault diagnosis approach is to give a fast response to faults by using the learned knowledge and processing huge data in a dynamical and distributed manner.Simulation studies are included to demonstrate the effectiveness of the approach.

关键词： Fault detection and isolation distributed systems deterministic learning radial basis function neural networks persistent excitation condition

作者: Tianrui Chen Cong Wang David J. Hill

作者单位: School of Automation, Guangdong University of Technology, Guangzhou 510006, P. R. China;School of El School of Automation and the Center for Control and Optimization, South China University of Technolo School of Electrical and Information Engineering, University of Sydney, NSW, 2006 Australia

会议类型: 国际会议

会议名称: the 25th Chinese Control and Decision Conference(第25届中国控制与决策会议)

会议地点: 贵阳

会议语种:英文

页码: 4746-4751

在线出版日期: 2013-05-01（万方平台首次上网日期，不代表论文的发表时间）