Real-time fault diagnosis

被引：147

作者：

Verma, V ^{[1
]}

Gordon, G

Simmons, R

Thrun, S

机构：

[1] Carnegie Mellon Univ, Sch Comp Sci, Pittsburgh, PA 15213 USA

[2] Stanford Univ, AI Lab, Stanford, CA 94305 USA

来源：

IEEE ROBOTICS & AUTOMATION MAGAZINE | 2004年 / 11卷 / 02期

关键词：

Efficient monitoring of hybrid dynamic systems; Particle filters; Real-time fault detection; Robot fault diagnosis; Tracking hybrid dynamic systems;

D O I：

10.1109/MRA.2004.1310942

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A number of complementary algorithms are now available for improving the accuracy of fault detection and identification (FDI) with a computationally tractable set of samples in a particle filter. Each algorithm provides an independent improvement over the basic approach. All of these approaches require dynamic models representing the behavior of each of the fault and operational states. The models can be built from analytical models of the robot dynamics, data from stimulation, or from the real robot.

引用

页码：56 / 66

页数：11