A Robust Detection and Isolation scheme for Incipient and Abrupt Faults in Robot Manipulator Using Neural Network

摘要：

This paper investigates an algorithm for robust fault detection and isolation(FDI) in robot manipulator using an neural network(NN) based observer. The proposed FDI algorithm uses both an nonlinear estimation process and an neural network based learning algorithm. This online monitoring algorithm is used to detect and isolate dynamic changes of a robot manipulator due to both incipient and abrupt faults. Another neural network is used for estimate the uncertainties in robot dynamics. A computer simulation for a two link robot manipulator shows the effectiveness of the proposed algorithm in the fault detection and isolation process.

关键词： Neural Network Fault Detection Fault Isolaltion nonlinear model

作者: Van Mien Hee-Jun Kang Young-Shick Ro

作者单位: Graduate school of Electrical Engineering University of Ulsan,680-749,Ulsan,South Korea School of Electrical Engineering University of Ulsan,680-749,Ulsan,South Korea

会议类型: 国际会议

会议名称: The 6th International Forum on Strategic Technology(IFOST 2011)(第六届国际战略技术论坛)

会议地点: 哈尔滨

会议语种:英文

页码: 313-316

在线出版日期: 2011-08-22（万方平台首次上网日期，不代表论文的发表时间）