Failure and reliability predictions by infinite impulse response locally recurrent neural networks

Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review

Autorschaft

  • Enrico Zio
  • Matteo Broggi
  • Lucia R. Golea
  • Nicola Pedroni

Externe Organisationen

  • CentraleSupélec
  • Politecnico di Milano
  • Universität Innsbruck
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)117-122
Seitenumfang6
FachzeitschriftChemical Engineering Transactions
Jahrgang26
PublikationsstatusVeröffentlicht - 2012
Extern publiziertJa

Abstract

In this paper, Infinite Impulse Response Locally Recurrent Neural Networks (IIR-LRNNs) are employed for forecasting failures and predicting the reliability of engineered components and systems. To the authors' knowledge, it is the first time that such dynamic modelling technique is used in reliability prediction tasks. The method is compared to the radial basis function (RBF), the traditional multilayer perceptron (MLP) model (i.e., the traditional Artificial Neural Network model) and the Box-Jenkins autoregressive-integrated-moving average (ARIMA). The comparison, made on case studies concerning engine systems, shows the superiority of the IIR-LRNN with respect to both the RBF and the ARIMA models, whereas a similar performance is obtained by the MLP.

ASJC Scopus Sachgebiete

Zitieren

Failure and reliability predictions by infinite impulse response locally recurrent neural networks. / Zio, Enrico; Broggi, Matteo; Golea, Lucia R. et al.
in: Chemical Engineering Transactions, Jahrgang 26, 2012, S. 117-122.

Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review

Zio, E, Broggi, M, Golea, LR & Pedroni, N 2012, 'Failure and reliability predictions by infinite impulse response locally recurrent neural networks', Chemical Engineering Transactions, Jg. 26, S. 117-122. https://doi.org/10.3303/CET1226020
Zio, E., Broggi, M., Golea, L. R., & Pedroni, N. (2012). Failure and reliability predictions by infinite impulse response locally recurrent neural networks. Chemical Engineering Transactions, 26, 117-122. https://doi.org/10.3303/CET1226020
Zio E, Broggi M, Golea LR, Pedroni N. Failure and reliability predictions by infinite impulse response locally recurrent neural networks. Chemical Engineering Transactions. 2012;26:117-122. doi: 10.3303/CET1226020
Zio, Enrico ; Broggi, Matteo ; Golea, Lucia R. et al. / Failure and reliability predictions by infinite impulse response locally recurrent neural networks. in: Chemical Engineering Transactions. 2012 ; Jahrgang 26. S. 117-122.
Download
@article{7dc0981ac9db42d7a4b4aeb6e87c39f2,
title = "Failure and reliability predictions by infinite impulse response locally recurrent neural networks",
abstract = "In this paper, Infinite Impulse Response Locally Recurrent Neural Networks (IIR-LRNNs) are employed for forecasting failures and predicting the reliability of engineered components and systems. To the authors' knowledge, it is the first time that such dynamic modelling technique is used in reliability prediction tasks. The method is compared to the radial basis function (RBF), the traditional multilayer perceptron (MLP) model (i.e., the traditional Artificial Neural Network model) and the Box-Jenkins autoregressive-integrated-moving average (ARIMA). The comparison, made on case studies concerning engine systems, shows the superiority of the IIR-LRNN with respect to both the RBF and the ARIMA models, whereas a similar performance is obtained by the MLP.",
author = "Enrico Zio and Matteo Broggi and Golea, {Lucia R.} and Nicola Pedroni",
note = "Copyright: Copyright 2018 Elsevier B.V., All rights reserved.",
year = "2012",
doi = "10.3303/CET1226020",
language = "English",
volume = "26",
pages = "117--122",

}

Download

TY - JOUR

T1 - Failure and reliability predictions by infinite impulse response locally recurrent neural networks

AU - Zio, Enrico

AU - Broggi, Matteo

AU - Golea, Lucia R.

AU - Pedroni, Nicola

N1 - Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2012

Y1 - 2012

N2 - In this paper, Infinite Impulse Response Locally Recurrent Neural Networks (IIR-LRNNs) are employed for forecasting failures and predicting the reliability of engineered components and systems. To the authors' knowledge, it is the first time that such dynamic modelling technique is used in reliability prediction tasks. The method is compared to the radial basis function (RBF), the traditional multilayer perceptron (MLP) model (i.e., the traditional Artificial Neural Network model) and the Box-Jenkins autoregressive-integrated-moving average (ARIMA). The comparison, made on case studies concerning engine systems, shows the superiority of the IIR-LRNN with respect to both the RBF and the ARIMA models, whereas a similar performance is obtained by the MLP.

AB - In this paper, Infinite Impulse Response Locally Recurrent Neural Networks (IIR-LRNNs) are employed for forecasting failures and predicting the reliability of engineered components and systems. To the authors' knowledge, it is the first time that such dynamic modelling technique is used in reliability prediction tasks. The method is compared to the radial basis function (RBF), the traditional multilayer perceptron (MLP) model (i.e., the traditional Artificial Neural Network model) and the Box-Jenkins autoregressive-integrated-moving average (ARIMA). The comparison, made on case studies concerning engine systems, shows the superiority of the IIR-LRNN with respect to both the RBF and the ARIMA models, whereas a similar performance is obtained by the MLP.

UR - http://www.scopus.com/inward/record.url?scp=84864486999&partnerID=8YFLogxK

U2 - 10.3303/CET1226020

DO - 10.3303/CET1226020

M3 - Article

AN - SCOPUS:84864486999

VL - 26

SP - 117

EP - 122

JO - Chemical Engineering Transactions

JF - Chemical Engineering Transactions

SN - 2283-9216

ER -