A Novel Probabilistic Long-Term Fault Prediction Framework Beyond SCADA Data - With Applications in Main Bearing Failure

Jürgen Herp*, Niels L. Pedersen, Esmaeil S. Nadimi

*Kontaktforfatter for dette arbejde

Publikation: Bidrag til tidsskriftKonferenceartikelForskningpeer review

18 Downloads (Pure)

Resumé

Prognostic and health monitoring addresses the issue of detecting faults and monitoring the current state of a wind turbine. Details about the fault's progression, and from there, the remaining useful lifetime, are key features in monitoring and industrial operation and maintenance planning. In order to avoid increase in operation and maintenance cost, as well as subjective human involvement, we present an online and automated monitoring framework for prediction of the remaining useful lifetime based on deep learning models. This framework includes training and re-training of predictive models with minimal oversight by the operators.

Further, we explore the dependency of various models' predictive abilities based on the input variables available, such as SCADA and secondary measurements. Especially deep learning approaches, such as neural networks, benefit greatly from the volume of data that can be extracted from modern-day turbines. This work utilizes upon the volume of data to present a case study on main bearing failures for 108 turbines. In the presented setting, predictions of the remaining useful lifetime of more than 90 days can be expected on average, outperforming the closest state-of-the-art estimate by almost a factor of two on average.
OriginalsprogEngelsk
BogserieJournal of Physics: Conference Series (Online)
Vol/bind1222
Antal sider10
ISSN1742-6596
DOI
StatusUdgivet - 2019
BegivenhedWind Europe Conference and Exhibition 2019 - Bilbao, Spanien
Varighed: 2. apr. 20194. apr. 2019

Konference

KonferenceWind Europe Conference and Exhibition 2019
LandSpanien
ByBilbao
Periode02/04/201904/04/2019

Fingeraftryk

turbines
life (durability)
learning
maintenance
education
predictions
wind turbines
progressions
health
planning
costs
operators
estimates

Citer dette

@inproceedings{9eea1ba27f2841c8b0d7913785d2709c,
title = "A Novel Probabilistic Long-Term Fault Prediction Framework Beyond SCADA Data - With Applications in Main Bearing Failure",
abstract = "Prognostic and health monitoring addresses the issue of detecting faults and monitoring the current state of a wind turbine. Details about the fault's progression, and from there, the remaining useful lifetime, are key features in monitoring and industrial operation and maintenance planning. In order to avoid increase in operation and maintenance cost, as well as subjective human involvement, we present an online and automated monitoring framework for prediction of the remaining useful lifetime based on deep learning models. This framework includes training and re-training of predictive models with minimal oversight by the operators.Further, we explore the dependency of various models' predictive abilities based on the input variables available, such as SCADA and secondary measurements. Especially deep learning approaches, such as neural networks, benefit greatly from the volume of data that can be extracted from modern-day turbines. This work utilizes upon the volume of data to present a case study on main bearing failures for 108 turbines. In the presented setting, predictions of the remaining useful lifetime of more than 90 days can be expected on average, outperforming the closest state-of-the-art estimate by almost a factor of two on average.",
author = "J{\"u}rgen Herp and Pedersen, {Niels L.} and {S. Nadimi}, Esmaeil",
year = "2019",
doi = "10.1088/1742-6596/1222/1/012043",
language = "English",
volume = "1222",
journal = "Journal of Physics: Conference Series (Online)",
issn = "1742-6596",
publisher = "IOP Publishing",

}

TY - GEN

T1 - A Novel Probabilistic Long-Term Fault Prediction Framework Beyond SCADA Data - With Applications in Main Bearing Failure

AU - Herp, Jürgen

AU - Pedersen, Niels L.

AU - S. Nadimi, Esmaeil

PY - 2019

Y1 - 2019

N2 - Prognostic and health monitoring addresses the issue of detecting faults and monitoring the current state of a wind turbine. Details about the fault's progression, and from there, the remaining useful lifetime, are key features in monitoring and industrial operation and maintenance planning. In order to avoid increase in operation and maintenance cost, as well as subjective human involvement, we present an online and automated monitoring framework for prediction of the remaining useful lifetime based on deep learning models. This framework includes training and re-training of predictive models with minimal oversight by the operators.Further, we explore the dependency of various models' predictive abilities based on the input variables available, such as SCADA and secondary measurements. Especially deep learning approaches, such as neural networks, benefit greatly from the volume of data that can be extracted from modern-day turbines. This work utilizes upon the volume of data to present a case study on main bearing failures for 108 turbines. In the presented setting, predictions of the remaining useful lifetime of more than 90 days can be expected on average, outperforming the closest state-of-the-art estimate by almost a factor of two on average.

AB - Prognostic and health monitoring addresses the issue of detecting faults and monitoring the current state of a wind turbine. Details about the fault's progression, and from there, the remaining useful lifetime, are key features in monitoring and industrial operation and maintenance planning. In order to avoid increase in operation and maintenance cost, as well as subjective human involvement, we present an online and automated monitoring framework for prediction of the remaining useful lifetime based on deep learning models. This framework includes training and re-training of predictive models with minimal oversight by the operators.Further, we explore the dependency of various models' predictive abilities based on the input variables available, such as SCADA and secondary measurements. Especially deep learning approaches, such as neural networks, benefit greatly from the volume of data that can be extracted from modern-day turbines. This work utilizes upon the volume of data to present a case study on main bearing failures for 108 turbines. In the presented setting, predictions of the remaining useful lifetime of more than 90 days can be expected on average, outperforming the closest state-of-the-art estimate by almost a factor of two on average.

U2 - 10.1088/1742-6596/1222/1/012043

DO - 10.1088/1742-6596/1222/1/012043

M3 - Conference article

VL - 1222

JO - Journal of Physics: Conference Series (Online)

JF - Journal of Physics: Conference Series (Online)

SN - 1742-6596

ER -