Skip to main navigation Skip to search Skip to main content

Fault detection and isolation using artificial neural networks

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

1 Scopus citations

Abstract

This paper presents fault detection and isolation method using neural network-based multi-fault models to detect and isolate faults in nonlinear systems. The fault diagnosis system consists of a fault detection part to sense the faults and a fault isolation part to identify the types of faults that have occurred. In the proposed method, the fault is detected when the errors between the nonlinear system and the artificial neural network (ANN) nominal system output cross a predetermined threshold. Once a fault in the system is detected, the fault classifier based on ANN isolates the fault. Simulation results demonstrate the effectiveness of the proposed ANN-based fault diagnosis method.

Original languageEnglish
Title of host publication19th International Conference on Computer Applications in Industry and Engineering, CAINE 2006
Pages335-340
Number of pages6
StatePublished - 2006
Event19th International Conference on Computer Applications in Industry and Engineering, CAINE 2006 - Las Vegas, NV, United States
Duration: 13 Nov 200615 Nov 2006

Publication series

Name19th International Conference on Computer Applications in Industry and Engineering, CAINE 2006

Conference

Conference19th International Conference on Computer Applications in Industry and Engineering, CAINE 2006
Country/TerritoryUnited States
CityLas Vegas, NV
Period13/11/0615/11/06

Keywords

  • Artificial neural networks
  • Fault detection and isolation
  • Nonlinear system

Fingerprint

Dive into the research topics of 'Fault detection and isolation using artificial neural networks'. Together they form a unique fingerprint.

Cite this