| |
FDI Based On Two Stage Classifiers For Fault Diagnosis Of Valve Actuators. Application To DAMADICS Benchmark
| [View]
[Download]
|
| Author(s) |
Arunas Lipnickas(lt), Jose Sa Da Costa(pt), Cosmin Danut Bocaniala(ro) |
| Abstract |
This paper describes a two stage classifiers FDI
system for fault diagnosis of industrial processes. The first stage
classifier is used for the fault detection and the second one
for fault isolation and identification. In order to reduce a
number of false alarms the penalization factor in the training
error cost function is introduced and also a methodology to
calculate the final fault detection. To increase the reliability of
the fault identification the probabilities of classification are
averaged within the fault duration time. The performance of the
proposed approach is demonstrated on the DAMADICS
benchmark problem to detect the abrupt faults in the valve
actuator block. |
| Download |
| Filename: | A58309 |
| Filesize: | 262.1 KB |
|
| Type |
Members Only |
| Date |
Last modified 2006-02-17 by System |
| |
 |