Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks

Eduardo Apaza Alvarez, Elvis J. Alegria

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

Abstract

This paper proposes an artificial neural network-based method for fault detection and diagnosis of a MIMO four-tank process in a non-minimum phase. The approach considers two stages: a model output estimation error stage, where a nonlinear autoregressive exogenous neural network is used to model the system, and a fault detection and diagnosis stage based on the model output error estimates, where a standard feed-forward neural network is used to classify the kind of fault. Faults due to added noise and parametric changes are combined as a benchmark to be detected in real-time to evaluate this proposal. Therefore, the whole system considers two setpoint inputs, four transfer functions, two NARX neural networks, four feed-forward pattern recognition networks, and four outputs, each associated with a specific fault.

Original languageEnglish
Title of host publication2022 IEEE ANDESCON
Subtitle of host publicationTechnology and Innovation for Andean Industry, ANDESCON 2022
EditorsMariela Cerrada Lozada, Paul Sanmartiin Mendoza
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665488549
DOIs
StatePublished - 2022
Event11th IEEE Conference of the Andean Council, ANDESCON 2022 - Barranquilla, Colombia
Duration: 16 Nov 202219 Nov 2022

Publication series

Name2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022

Conference

Conference11th IEEE Conference of the Andean Council, ANDESCON 2022
Country/TerritoryColombia
CityBarranquilla
Period16/11/2219/11/22

Keywords

  • Fault detection
  • artificial neural networks
  • fault diagnosis
  • four-tanks process

Fingerprint

Dive into the research topics of 'Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this