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

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

Research output: Contribution to journalArticlepeer-review


A robust fault detection observer (RFDO), which includes a robust residual, is designed for a general nonlinear system with polynomial-type nonlinearities. Two main theoretical results are given for the existence, stability and the detectability of the RFDO. The approach is applied to a three-tank hydraulic system where two fault scenarios are considered. Three different degree observers, with corresponding residuals, are assessed. This observer approach is then compared to the performance of a neural network approach under the same fault conditions.
Original languageUndefined
Pages (from-to)85-106
Number of pages22
JournalSystems Science
Issue number1
Publication statusPublished - 2002


  • Asymptotic stability
  • Control system synthesis
  • Differential equations
  • Failure analysis
  • Hydraulic equipment
  • Neural networks
  • Nonlinear control systems
  • Polynomials
  • System stability
  • Polynomial-type nonlinearities
  • Robust fault detection observer
  • Hydraulic system
  • Robustness (control systems)

Cite this