Neuro Fuzzy System For Industrial Processes Fault Diagnosis

Marius Pislaru, Alexandru Trandabat, Marius Olariu

Abstract

In the last decade considerable research efforts have been spent to seek for systematic approaches to Fault Diagnosis (FD) in dynamical systems The problem of fault detection consists in detecting faults in a physical system by monitoring its inputs and outputs .Recently, the research has focused on non-linear systems FDI. Traditionally, the FD problem for non-linear dynamic systems has been approached in two steps. Firstly, the models linearized at an operating point, and then robust techniques are applied to generate residuals. This method only works well when the linearization does not cause a large mismatch between linear and non-linear models and the system operates close to the operating point specified. To deal with systems with high non-linearity and wide operation range, the FD problem has to be tackled directly using non-linear techniques. In the last decade considerable research efforts have been spent to seek for systematic approaches to Fault Diagnosis in dynamical systems.

Download

IMEKO-TC4-2007-185.pdf

DOI

-

IMEKO TC

TC4 - Measurement of Electrical Quantities

Back to the proceedings