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

Eduardo Apaza Alvarez; Elvis J. Alegria

doi:10.1109/ANDESCON56260.2022.9989558

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

Eduardo Apaza Alvarez, Elvis J. Alegria

Department of Electrical and Mechatronics Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

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 language	English
Title of host publication	2022 IEEE ANDESCON
Subtitle of host publication	Technology and Innovation for Andean Industry, ANDESCON 2022
Editors	Mariela Cerrada Lozada, Paul Sanmartiin Mendoza
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665488549
DOIs	https://doi.org/10.1109/ANDESCON56260.2022.9989558
State	Published - 2022
Event	11th IEEE Conference of the Andean Council, ANDESCON 2022 - Barranquilla, Colombia Duration: 16 Nov 2022 → 19 Nov 2022

Publication series

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

Conference

Conference	11th IEEE Conference of the Andean Council, ANDESCON 2022
Country/Territory	Colombia
City	Barranquilla
Period	16/11/22 → 19/11/22

Keywords

Fault detection
artificial neural networks
fault diagnosis
four-tanks process

Access to Document

10.1109/ANDESCON56260.2022.9989558

Cite this

Alvarez, E. A., & Alegria, E. J. (2022). Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks. In M. C. Lozada, & P. S. Mendoza (Eds.), 2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022 (2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ANDESCON56260.2022.9989558

Alvarez, Eduardo Apaza ; Alegria, Elvis J. / Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks. 2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022. editor / Mariela Cerrada Lozada ; Paul Sanmartiin Mendoza. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022).

@inproceedings{5e1a874d69fd408798155710b95b0bfb,

title = "Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks",

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.",

keywords = "Fault detection, artificial neural networks, fault diagnosis, four-tanks process",

author = "Alvarez, {Eduardo Apaza} and Alegria, {Elvis J.}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 11th IEEE Conference of the Andean Council, ANDESCON 2022 ; Conference date: 16-11-2022 Through 19-11-2022",

year = "2022",

doi = "10.1109/ANDESCON56260.2022.9989558",

language = "English",

series = "2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Lozada, {Mariela Cerrada} and Mendoza, {Paul Sanmartiin}",

booktitle = "2022 IEEE ANDESCON",

}

Alvarez, EA & Alegria, EJ 2022, Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks. in MC Lozada & PS Mendoza (eds), 2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022. 2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022, Institute of Electrical and Electronics Engineers Inc., 11th IEEE Conference of the Andean Council, ANDESCON 2022, Barranquilla, Colombia, 16/11/22. https://doi.org/10.1109/ANDESCON56260.2022.9989558

Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks. / Alvarez, Eduardo Apaza; Alegria, Elvis J.
2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022. ed. / Mariela Cerrada Lozada; Paul Sanmartiin Mendoza. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks

AU - Alvarez, Eduardo Apaza

AU - Alegria, Elvis J.

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - Fault detection

KW - artificial neural networks

KW - fault diagnosis

KW - four-tanks process

UR - http://www.scopus.com/inward/record.url?scp=85146430255&partnerID=8YFLogxK

U2 - 10.1109/ANDESCON56260.2022.9989558

DO - 10.1109/ANDESCON56260.2022.9989558

M3 - Conference contribution

AN - SCOPUS:85146430255

T3 - 2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022

BT - 2022 IEEE ANDESCON

A2 - Lozada, Mariela Cerrada

A2 - Mendoza, Paul Sanmartiin

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th IEEE Conference of the Andean Council, ANDESCON 2022

Y2 - 16 November 2022 through 19 November 2022

ER -

Alvarez EA, Alegria EJ. Detection and Diagnosis of Faults in a Four-Tank System using Artificial Neural Networks. In Lozada MC, Mendoza PS, editors, 2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 IEEE ANDESCON: Technology and Innovation for Andean Industry, ANDESCON 2022). doi: 10.1109/ANDESCON56260.2022.9989558

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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this