Detecting faults in a hydraulic system using neural network and observer approaches

D.N. Shields, S. Du, E. Gaura

Research output: Chapter in Book/Report/Conference proceedingConference proceedingpeer-review


A detection observer and residual are designed for a general nonlinear system with polynomial-type nontinearities. A suboptomal approach is also described. The approach is applied to a three-tank hydraulic system for detecting two faults. Three different degree observers, with correponding residuals, are assessed. This observer approach is then compared to the performance of a neural network approach, where the same faults are assessed.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Systems Science
EditorsZ. Bubnicki, A. Grzech
Number of pages8
Publication statusPublished - 2001
EventInternational Conference on Systems Science - Wroclaw, Poland
Duration: 11 Sept 200114 Sept 2001
Conference number: 14


ConferenceInternational Conference on Systems Science


  • Differential equations
  • Neural networks
  • Nonlinear systems
  • Polynomials
  • Hydraulics
  • Hydraulic systems


Dive into the research topics of 'Detecting faults in a hydraulic system using neural network and observer approaches'. Together they form a unique fingerprint.

Cite this