Remaining useful lifetime prediction via deep domain adaptation

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Uittreksel

In Prognostics and Health Management (PHM) sufficient prior observed degradation data is usually critical for Remaining Useful Lifetime (RUL) prediction. Most previous data-driven methods assume that training (source) and testing (target) condition monitoring data have similar distributions. However, due to different operating conditions, fault modes and noise, distribution and feature shift exist across different domains. This shift reduces the performance of predictive models when no target observed run-to-failure data is available. To address this issue, this paper proposes a new data-driven approach for domain adaptation in prognostics using Long Short-Term Neural Networks (LSTM). We use a Domain Adversarial Neural Network (DANN) approach to adapt remaining useful life estimates to a target domain containing only sensor information. We analyse our approach using the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPPS). The results show that the proposed method can provide more reliable RUL predictions than models trained only on source data for varying operating conditions and fault modes.
TaalEngels
Artikelnummer106682
Aantal pagina's13
TijdschriftReliability Engineering and System Safety
Volume195
DOI's
StatusGepubliceerd - 1 mrt 2020

Vingerafdruk

Neural networks
Condition monitoring
Propulsion
NASA
Health
Degradation
Sensors
Testing

Citeer dit

@article{feed2430445946e789a891e5cb28ebb2,
title = "Remaining useful lifetime prediction via deep domain adaptation",
abstract = "In Prognostics and Health Management (PHM) sufficient prior observed degradation data is usually critical for Remaining Useful Lifetime (RUL) prediction. Most previous data-driven methods assume that training (source) and testing (target) condition monitoring data have similar distributions. However, due to different operating conditions, fault modes and noise, distribution and feature shift exist across different domains. This shift reduces the performance of predictive models when no target observed run-to-failure data is available. To address this issue, this paper proposes a new data-driven approach for domain adaptation in prognostics using Long Short-Term Neural Networks (LSTM). We use a Domain Adversarial Neural Network (DANN) approach to adapt remaining useful life estimates to a target domain containing only sensor information. We analyse our approach using the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPPS). The results show that the proposed method can provide more reliable RUL predictions than models trained only on source data for varying operating conditions and fault modes.",
author = "{da Costa}, {Paulo Roberto de Oliveira} and Alp Ak{\cc}ay and Yingqian Zhang and Uzay Kaymak",
year = "2020",
month = "3",
day = "1",
doi = "10.1016/j.ress.2019.106682",
language = "English",
volume = "195",
journal = "Reliability Engineering and System Safety",
issn = "0951-8320",
publisher = "Elsevier",

}

Remaining useful lifetime prediction via deep domain adaptation. / da Costa, Paulo Roberto de Oliveira; Akçay, Alp; Zhang, Yingqian; Kaymak, Uzay.

In: Reliability Engineering and System Safety, Vol. 195, 106682, 01.03.2020.

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

TY - JOUR

T1 - Remaining useful lifetime prediction via deep domain adaptation

AU - da Costa,Paulo Roberto de Oliveira

AU - Akçay,Alp

AU - Zhang,Yingqian

AU - Kaymak,Uzay

PY - 2020/3/1

Y1 - 2020/3/1

N2 - In Prognostics and Health Management (PHM) sufficient prior observed degradation data is usually critical for Remaining Useful Lifetime (RUL) prediction. Most previous data-driven methods assume that training (source) and testing (target) condition monitoring data have similar distributions. However, due to different operating conditions, fault modes and noise, distribution and feature shift exist across different domains. This shift reduces the performance of predictive models when no target observed run-to-failure data is available. To address this issue, this paper proposes a new data-driven approach for domain adaptation in prognostics using Long Short-Term Neural Networks (LSTM). We use a Domain Adversarial Neural Network (DANN) approach to adapt remaining useful life estimates to a target domain containing only sensor information. We analyse our approach using the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPPS). The results show that the proposed method can provide more reliable RUL predictions than models trained only on source data for varying operating conditions and fault modes.

AB - In Prognostics and Health Management (PHM) sufficient prior observed degradation data is usually critical for Remaining Useful Lifetime (RUL) prediction. Most previous data-driven methods assume that training (source) and testing (target) condition monitoring data have similar distributions. However, due to different operating conditions, fault modes and noise, distribution and feature shift exist across different domains. This shift reduces the performance of predictive models when no target observed run-to-failure data is available. To address this issue, this paper proposes a new data-driven approach for domain adaptation in prognostics using Long Short-Term Neural Networks (LSTM). We use a Domain Adversarial Neural Network (DANN) approach to adapt remaining useful life estimates to a target domain containing only sensor information. We analyse our approach using the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPPS). The results show that the proposed method can provide more reliable RUL predictions than models trained only on source data for varying operating conditions and fault modes.

U2 - 10.1016/j.ress.2019.106682

DO - 10.1016/j.ress.2019.106682

M3 - Article

VL - 195

JO - Reliability Engineering and System Safety

T2 - Reliability Engineering and System Safety

JF - Reliability Engineering and System Safety

SN - 0951-8320

M1 - 106682

ER -