System-level Probabilistic Remaining Useful Life Prognostics and Predictive Inspection Planning for Wind Turbines

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Davide Manna Mihaela Mitici Matteo Davide Lorenzo Dalla Vedova

Abstract

Wind energy plays a crucial role in the energy transition. However, it is often seen as an unreliable source of energy, with many production peaks and lows. Some of the drivers of uncertainty in energy production are the unexpected wind turbine (WT) failures and associated unscheduled maintenance.

To support an effective health management and maintenance planning of WTs, we propose an integrated data-driven framework for Remaining Useful Life (RUL) prognostics and inspection planning of WTs. We propose a Long-short term memory (LSTM) neural network with Monte Carlo dropout to estimate the distribution of the RUL of WTs, i.e. we develop probabilistic prognostics. Different from existing studies focused on prognostics for single components, we consider the simultaneous health-monitoring of multiple components of the WTs, thus seeing the turbine as an integrated system. The obtained prognostics are further included into a stochastic planning model which determines optimal moments for inspections. For this, we pose the problem of WT inspections as a renewal reward process. We illustrate our framework for four offshore WTs which are continuously monitored by Supervisory Control and Data Acquisition (SCADA) systems. The results show that LSTMs are able to estimate well the RUL of the WTs, even in the early phase of their usage. We also show that the prognostics are informative for maintenance planning and are conducive to conservative inspections.

How to Cite

Manna, D., Mitici, M., & Dalla Vedova, M. D. L. (2024). System-level Probabilistic Remaining Useful Life Prognostics and Predictive Inspection Planning for Wind Turbines. PHM Society European Conference, 8(1), 13. https://doi.org/10.36001/phme.2024.v8i1.3991
Abstract 231 | PDF Downloads 160

##plugins.themes.bootstrap3.article.details##

Keywords

stochastic maintenance planning, probabilistic prognostics, prognostics for wind turbines, predictive maintenance

References
%% This BibTeX bibliography file was created using BibDesk.
%% http://bibdesk.sourceforge.net/


%% Created for José R. Celaya at 2012-01-19 16:34:22 -0800


%% Saved with string encoding Unicode (UTF-8)



@phdthesis{chen,
Author = {Chen, W.},
Owner = {lkuhn},
School = {Technical University of Napoli},
Timestamp = {2009.05.21},
Title = {Nonlinear Analysis of Electronic Prognostics},
Year = {1991}}

@inproceedings{ferrell,
Author = {Ferrell, B. L.},
Booktitle = {Proceedings of IEEE Aerospace Conference},
Owner = {lkuhn},
Timestamp = {2009.05.21},
Title = {JSF Prognostics and Health Managemen},
Year = {1999}}

@inproceedings{hyndman,
Author = {Hyndman, R. J. and Koehler, A. B.},
Booktitle = {International Journal of Forecasting},
Owner = {lkuhn},
Timestamp = {2009.05.21},
Title = {Another Look at Measures of Forecast Accuracy},
Year = {2006}}

@techreport{iso,
Author = {ISO},
Date-Modified = {2012-01-19 16:34:21 -0800},
Institution = {International Organization for Standardization},
Number = {ISO13381-1},
Title = {Condition Monitoring and Diagnostics of Machines, Prognostics part 1: General Guidelines},
Volume = {ISO/IEC Directives Part 2},
Year = {2004}}

@inproceedings{Schwabacher,
Author = {Schwabacher, M. and Goebel, K.},
Booktitle = {Proceedings of AAAI Fall Symposium},
Owner = {lkuhn},
Timestamp = {2009.05.21},
Title = {A Survey of Artificial Intelligence for Prognostics},
Year = {2007}}

@inproceedings{vachtsevanos,
Author = {Vachtsevanos, G. and Lewis, F. L. and Roemer, M. and Hess, A. and Wu, B.},
Booktitle = {1st ed. Hoboken},
Owner = {lkuhn},
Timestamp = {2009.05.21},
Title = {Intelligent Fault Diagnosis and Prognosis for Engineering Systems},
Year = {2006}}

@book{bhattacharyya,
Editor = {Bhattacharyya, S. S. and Deprettere, E. and Leupers, R. and Takala, J.},
Publisher = {Springer},
Title = {Handbook of Signal Processing Systems},
Year = {2010}}

@article{wunsch,
Author = {Wunsch, D. C. and Bell, R. R.},
Journal = {IEEE Transactions on Nuclear Science},
Number = {6},
Pages = {244-259},
Title = {Determination of Threshold Failure Levels of Semiconductor Diodes and Transistors Due to Pulse Voltages},
Volume = {15},
Year = {1968}}

%%%%%%%%%%%%
@article{apunda2017challenges,
title={Challenges and opportunities of wind energy technology},
author={Apunda, Moses Otieno and Nyangoye, Benard Oloo},
journal={International Journal of Development Research},
volume={9},
number={06},
pages={14174--14177},
year={2017}
}

@article{sawant2021review,
title={A review on state-of-the-art reviews in wind-turbine-and wind-farm-related topics},
author={Sawant, Manisha and Thakare, Sameer and Rao, A Prabhakara and Feij{\'o}o-Lorenzo, Andr{\'e}s E and Bokde, Neeraj Dhanraj},
journal={Energies},
volume={14},
number={8},
pages={2041},
year={2021},
publisher={MDPI}
}

@book{letcher2023wind,
title={Wind energy engineering: a handbook for onshore and offshore wind turbines},
author={Letcher, Trevor},
year={2023},
publisher={Elsevier}
}

@article{rezamand2020critical,
title={Critical wind turbine components prognostics: A comprehensive review},
author={Rezamand, Milad and Kordestani, Mojtaba and Carriveau, Rupp and Ting, David S-K and Orchard, Marcos E and Saif, Mehrdad},
journal={IEEE Transactions on Instrumentation and Measurement},
volume={69},
number={12},
pages={9306--9328},
year={2020},
publisher={IEEE}
}

@article{astolfi2022discussion,
title={Discussion of wind turbine performance based on SCADA data and multiple test case analysis},
author={Astolfi, Davide and Pandit, Ravi and Terzi, Ludovico and Lombardi, Andrea},
journal={Energies},
volume={15},
number={15},
pages={5343},
year={2022},
publisher={MDPI}
}

@article{tchakoua2014wind,
title={Wind turbine condition monitoring: State-of-the-art review, new trends, and future challenges},
author={Tchakoua, Pierre and Wamkeue, Ren{\'e} and Ouhrouche, Mohand and Slaoui-Hasnaoui, Fouad and Tameghe, Tommy Andy and Ekemb, Gabriel},
journal={Energies},
volume={7},
number={4},
pages={2595--2630},
year={2014},
publisher={MDPI}
}

@article{tautz2017using,
title={Using SCADA data for wind turbine condition monitoring--a review},
author={Tautz-Weinert, Jannis and Watson, Simon J},
journal={IET Renewable Power Generation},
volume={11},
number={4},
pages={382--394},
year={2017},
publisher={Wiley Online Library}
}

@article{yang2014wind,
title={Wind turbine condition monitoring: technical and commercial challenges},
author={Yang, Wenxian and Tavner, Peter J and Crabtree, Christopher J and Feng, Yanhui and Qiu, Yingning},
journal={Wind Energy},
volume={17},
number={5},
pages={673--693},
year={2014},
publisher={Wiley Online Library}
}

@inproceedings{griffith2016study,
title={A study of rotor and platform design trade-offs for large-scale floating vertical axis wind turbines},
author={Griffith, D Todd and Paquette, Joshua and Barone, Matthew and Goupee, Andrew J and Fowler, Matthew J and Bull, Diana and Owens, Brian},
booktitle={Journal of Physics: Conference Series},
volume={753},
number={10},
pages={102003},
year={2016},
organization={IOP Publishing}
}

@book{tong2010fundamentals,
title={Fundamentals of wind energy},
author={Tong, Wei},
volume={44},
year={2010},
publisher={WIT press Southampton, UK}
}

@article{errichello1994design,
title={Design requirements for wind turbine gearboxes},
author={Errichello, Robert and Muller, Jane},
journal={NASA STI/Recon Technical Report N},
volume={9},
year={1994}
}

@inproceedings{ragheb2010wind,
title={Wind turbine gearbox technologies},
author={Ragheb, Adam and Ragheb, Magdi},
booktitle={1st International nuclear \& renewable energy conference (INREC)},
pages={1--8},
year={2010},
organization={IEEE}
}

@inproceedings{wagner2020introduction,
title={Introduction to wind energy systems},
author={Wagner, Hermann-Josef},
booktitle={EPJ Web of Conferences},
volume={246},
pages={00004},
year={2020},
organization={EDP Sciences}
}

@article{yang2013wind,
title={Wind turbine condition monitoring by the approach of SCADA data analysis},
author={Yang, Wenxian and Court, Richard and Jiang, Jiesheng},
journal={Renewable energy},
volume={53},
pages={365--376},
year={2013},
publisher={Elsevier}
}

@article{zaher2009online,
title={Online wind turbine fault detection through automated SCADA data analysis},
author={Zaher, ASAE and McArthur, SDJ and Infield, DG and Patel, Y},
journal={Wind Energy: An International Journal for Progress and Applications in Wind Power Conversion Technology},
volume={12},
number={6},
pages={574--593},
year={2009},
publisher={Wiley Online Library}
}

@inproceedings{kim2011use,
title={Use of SCADA data for failure detection in wind turbines},
author={Kim, Kyusung and Parthasarathy, Girija and Uluyol, Onder and Foslien, Wendy and Sheng, Shuangwen and Fleming, Paul},
booktitle={Energy sustainability},
volume={54686},
pages={2071--2079},
year={2011}
}

%%%Table
@article{chen2013wind,
title={Wind turbine pitch faults prognosis using a-priori knowledge-based ANFIS},
author={Chen, Bindi and Matthews, Peter and Tavner, Peter J},
journal={Expert Systems with Applications},
volume={40},
number={17},
pages={6863--6876},
year={2013},
publisher={Elsevier}
}

@article{chen2015automated,
title={Automated on-line fault prognosis for wind turbine pitch systems using supervisory control and data acquisition},
author={Chen, Bindi and Matthews, Peter C and Tavner, Peter J},
journal={IET Renewable Power Generation},
volume={9},
number={5},
pages={503--513},
year={2015},
publisher={Wiley Online Library}
}

@article{elasha2019prognosis,
title={Prognosis of a wind turbine gearbox bearing using supervised machine learning},
author={Elasha, Faris and Shanbr, Suliman and Li, Xiaochuan and Mba, David},
journal={Sensors},
volume={19},
number={14},
pages={3092},
year={2019},
publisher={MDPI}
}

@inproceedings{cao2018remaining,
title={Remaining useful life prediction of wind turbine generator bearing based on EMD with an indicator},
author={Cao, Lixiao and Qian, Zheng and Pei, Yan},
booktitle={2018 Prognostics and System Health Management Conference (PHM-Chongqing)},
pages={375--379},
year={2018},
organization={IEEE}
}

@article{zhao2021feature,
title={Feature extraction for data-driven remaining useful life prediction of rolling bearings},
author={Zhao, Huimin and Liu, Haodong and Jin, Yang and Dang, Xiangjun and Deng, Wu},
journal={IEEE Transactions on Instrumentation and Measurement},
volume={70},
pages={1--10},
year={2021},
publisher={IEEE}
}

@article{merainani2022integrated,
title={An integrated methodology for estimating the remaining useful life of high-speed wind turbine shaft bearings with limited samples},
author={Merainani, Boualem and Laddada, Sofiane and Bechhoefer, Eric and Chikh, Mohamed Abdessamed Ait and Benazzouz, Djamel},
journal={Renewable Energy},
volume={182},
pages={1141--1151},
year={2022},
publisher={Elsevier}
}

@article{teng2016prognosis,
title={Prognosis of the remaining useful life of bearings in a wind turbine gearbox},
author={Teng, Wei and Zhang, Xiaolong and Liu, Yibing and Kusiak, Andrew and Ma, Zhiyong},
journal={Energies},
volume={10},
number={1},
pages={32},
year={2016},
publisher={MDPI}
}

@article{herp2018bayesian,
title={Bayesian state prediction of wind turbine bearing failure},
author={Herp, J{\"u}rgen and Ramezani, Mohammad H and Bach-Andersen, Martin and Pedersen, Niels L and Nadimi, Esmaeil S},
journal={Renewable Energy},
volume={116},
pages={164--172},
year={2018},
publisher={Elsevier}
}

@article{pan2019performance,
title={Performance degradation assessment of a wind turbine gearbox based on multi-sensor data fusion},
author={Pan, Yubin and Hong, Rongjing and Chen, Jie and Singh, Jaskaran and Jia, Xiaodong},
journal={Mechanism and machine theory},
volume={137},
pages={509--526},
year={2019},
publisher={Elsevier}
}

@article{carroll2019wind,
title={Wind turbine gearbox failure and remaining useful life prediction using machine learning techniques},
author={Carroll, James and Koukoura, Sofia and McDonald, Alasdair and Charalambous, Anastasis and Weiss, Stephan and McArthur, Stephen},
journal={Wind Energy},
volume={22},
number={3},
pages={360--375},
year={2019},
publisher={Wiley Online Library}
}

@inproceedings{kramti2018direct,
title={Direct wind turbine drivetrain prognosis approach using Elman neural network},
author={Kramti, Sharaf Eddine and Ali, Jaouher Ben and Saidi, Lotfi and Sayadi, Mounir and Bechhoefer, Eric},
booktitle={2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)},
pages={859--864},
year={2018},
organization={IEEE}
}

@article{lundberg2017unified,
title={A unified approach to interpreting model predictions},
author={Lundberg, Scott M and Lee, Su-In},
journal={Advances in neural information processing systems},
volume={30},
year={2017}
}

@article{hochreiter1997long,
title={Long short-term memory},
author={Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
journal={Neural computation},
volume={9},
number={8},
pages={1735--1780},
year={1997},
publisher={MIT press}
}

@article{graves2012supervised,
title={Supervised sequence labelling},
author={Graves, Alex and Graves, Alex},
year={2012},
publisher={Springer}
}

@inproceedings{gal2016dropout,
title={Dropout as a bayesian approximation: Representing model uncertainty in deep learning},
author={Gal, Yarin and Ghahramani, Zoubin},
booktitle={international conference on machine learning},
pages={1050--1059},
year={2016},
organization={PMLR}
}

@article{blei2017variational,
title={Variational inference: A review for statisticians},
author={Blei, David M and Kucukelbir, Alp and McAuliffe, Jon D},
journal={Journal of the American statistical Association},
volume={112},
number={518},
pages={859--877},
year={2017},
publisher={Taylor \& Francis}
}

@article{mitici2023dynamic,
title={Dynamic predictive maintenance for multiple components using data-driven probabilistic RUL prognostics: The case of turbofan engines},
author={Mitici, Mihaela and de Pater, Ingeborg and Barros, Anne and Zeng, Zhiguo},
journal={Reliability Engineering \& System Safety},
volume={234},
pages={109199},
year={2023},
publisher={Elsevier}
}


@article{gneiting2014probabilistic,
title={Probabilistic forecasting},
author={Gneiting, Tilmann and Katzfuss, Matthias},
journal={Annual Review of Statistics and Its Application},
volume={1},
pages={125--151},
year={2014},
publisher={Annual Reviews}
}

@article{EDPDataset,
title={Dataset Wind Turbines},
author={EDP},
journal={https://www.edp.com/en/innovation/open-data/data},
year={2023}
}

@book{tijms2003first,
title={A first course in stochastic models},
author={Tijms, Henk C},
year={2003},
publisher={John Wiley and sons}
}

%%%%
@article{kramti2021neural,
title={A neural network approach for improved bearing prognostics of wind turbine generators},
author={Kramti, Sharaf Eddine and Ali, Jaouher Ben and Saidi, Lotfi and Sayadi, Mounir and Bouchouicha, Moez and Bechhoefer, Eric},
journal={The European Physical Journal Applied Physics},
volume={93},
number={2},
pages={20901},
year={2021},
publisher={EDP Sciences}
}

@article{garan2022data,
title={A data-centric machine learning methodology: Application on predictive maintenance of wind turbines},
author={Garan, Maryna and Tidriri, Khaoula and Kovalenko, Iaroslav},
journal={Energies},
volume={15},
number={3},
pages={826},
year={2022},
publisher={MDPI}
}

@article{li2022self,
title={A self-data-driven method for remaining useful life prediction of wind turbines considering continuously varying speeds},
author={Li, Naipeng and Xu, Pengcheng and Lei, Yaguo and Cai, Xiao and Kong, Detong},
journal={Mechanical Systems and Signal Processing},
volume={165},
pages={108315},
year={2022},
publisher={Elsevier}
}

@inproceedings{rajaoarisoa2024predictive,
title={Predictive maintenance model-based on multi-stage neural network systems for wind turbines},
author={Rajaoarisoa, Lala and Randrianandraina, Raubertin and Sayed-Mouchaweh, Moamar},
booktitle={2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)},
pages={1--7},
year={2024},
organization={IEEE}
}

@inproceedings{orozco2018diagnostic,
title={Diagnostic models for wind turbine gearbox components using scada time series data},
author={Orozco, Rafael and Sheng, Shuangwen and Phillips, Caleb},
booktitle={2018 IEEE International Conference on Prognostics and Health Management (ICPHM)},
pages={1--9},
year={2018},
organization={IEEE}
}
Section
Technical Papers