Offshore wind structures are exposed to a harsh marine environment and are subject to deterioration mechanisms throughout their operational lifetime. Even if the deterioration evolution of structural elements can be estimated through physics-based deterioration models, the uncertainties involved in the process hurdle the selection of lifecycle management decisions, e.g., lifetime extension. In this scenario, the collection of relevant information through an efficient monitoring system enables the reduction of uncertainties, ultimately driving more optimal lifecycle decisions. However, a full monitoring instrumentation implemented on all wind turbines in a farm may become unfeasible due to practical and economical constraints. Besides, certain load monitoring systems often become defective after a few years of marine environment exposure. Addressing the aforementioned concerns, a farm-wide virtual load monitoring scheme directed by a fleet-leader wind turbine offers an attractive solution. Fetched with data retrieved from a fully instrumented wind turbine, a model can be first trained and then deployed, yielding load predictions for non-fully monitored wind turbines, from which only standard data are available, e.g., supervisory control and data acquisition. During the deployment stage, the pretrained virtual monitoring model may, however, receive previously unseen monitoring data, leading to inaccurate load predictions. In this article, we propose a virtual load monitoring framework formulated via Bayesian neural networks (BNNs) and provide relevant implementation details needed for the construction, training, and deployment of BNN data-based virtual monitoring models. As opposed to their deterministic counterparts, BNNs intrinsically announce the uncertainties associated with generated load predictions and allow to detect inaccurate load estimations generated for non-fully monitored wind turbines. The proposed virtual load monitoring is thoroughly tested through an experimental campaign in an operational offshore wind farm and the results demonstrate the effectiveness of BNN models for “fleet-leader”-based farm-wide virtual monitoring.
FarhanMSchneiderRThönsS.Predictive information and maintenance optimization based on decision theory: a case study considering a welded joint in an offshore wind turbine support structure. Struct Health Monit2022; 21(1): 185–207.
2.
HlaingNMoratoPGNielsenJS, et al. Inspection and maintenance planning for offshore wind structural components: integrating fatigue failure criteria with Bayesian networks and Markov decision processes. Struct Infrastruct Eng2022; 18(7): 983–1001.
3.
ZhaoHXuFLiangB, et al. A condition-based opportunistic maintenance strategy for multi-component system. Struct Health Monit2019; 18(1): 270–283.
4.
NielsenJS.Value of information of structural health monitoring with temporally dependent observations. Struct Health Monit2022; 21(1): 165–184.
5.
SchedatMFaberTSivanesanA.Structural health monitoring concept to predict the remaining lifetime of the wind turbine structure. In: 2016 International conference on the domestic use of energy (DUE), Cape Town, South Africa, pp. 1–5. IEEE.
6.
MaiQAWeijtjensWDevriendtC, et al. Prediction of remaining fatigue life of welded joints in wind turbine support structures considering strain measurement and a joint distribution of oceanographic data. Marine Struct2019; 66: 307–322.
7.
PachecoJPimentaFPereiraS, et al. Fatigue assessment of wind turbine towers: review of processing strategies with illustrative case study. Energies2022; 15(13): 4782.
8.
SmarslyKHartmannDLawKH.A computational framework for life-cycle management of wind turbines incorporating structural health monitoring. Struct Health Monit2013; 12(4): 359–376.
9.
MoratoPG.Optimal inspection and maintenance planning for deteriorating structures via Markov decision processes and deep reinforcement learning: application to offshore wind substructures. PhD Thesis, University of Liege, Liege, 2021.
10.
HlaingNMoratoPGRigoP.Probabilistic virtual load monitoring of offshore wind substructures: a supervised learning approach. In: The proceedings of the 32nd international ocean and polar engineering conference, ISOPE-2022, Shanghai, China, pp. 3137–3144.
11.
CosackN.Fatigue load monitoring with standard wind turbine signals. PhD Thesis, Universitat Stuttgart, Stuttgart, 2010.
XuYNikitasGZhangT, et al. Support condition monitoring of offshore wind turbines using model updating techniques. Struct Health Monit2020; 19(4): 1017–1031.
14.
ZhangZSunC.Structural damage identification via physics-guided machine learning: a methodology integrating pattern recognition with finite element model updating. Struct Health Monit2021; 20(4): 1675–1688.
15.
MaesKIliopoulosAWeijtjensW, et al. Dynamic strain estimation for fatigue assessment of an offshore monopile wind turbine using filtering and modal expansion algorithms. Mech Syst Signal Process2016; 76–77: 592–611.
16.
Pérez CampuzanoDde las Heras-CarbonellEGGallego CastilloC, et al. Modelling damage equivalent loads in wind turbines from general operational signals: exploration of relevant input selection methods using aeroelastic simulations. Wind Energy2018; 21(6): 441–459.
17.
de Nolasco SantosFNoppeNWeijtjensW, et al. SCADA-based neural network thrust load model for fatigue assessment: cross validation with in-situ measurements. J Phys: Conf Ser2020; 1618(2): 022020.
18.
NoppeNIliopoulosAWeijtjensW, et al. Full load estimation of an offshore wind turbine based on SCADA and accelerometer data. J Phys: Conf Ser2016; 753: 072025.
19.
KennedyMCO’HaganA.Bayesian calibration of computer models. J R Stat Soc, B: Stat Methodol2001; 63(3): 425–464.
20.
PimentaFPachecoJPereiraS, et al. Reconstructing the bending moments time history of wind turbine tower from acceleration measurements using Gaussian processes. J Phys: Conf Ser2022; 2265(3): 032080.
21.
ZouJCicirelloAIliopoulosA, et al. Gaussian process latent force models for virtual sensing in a monopile-based offshore wind turbine. In: EWSHM 2022: European workshop on structural health monitoring, pp. 290–298. Springer International Publishing.
22.
SinghDDwightRPLaugesenK, et al. Probabilistic surrogate modeling of offshore wind-turbine loads with chained Gaussian processes. J Phys: Conf Ser2022; 2265(3): 032070.
23.
NoppeNHüblerCDevriendtC, et al. Validated extrapolation of measured damage within an offshore wind farm using instrumented fleet leaders. J Phys: Conf Ser2020; 1618(2): 022005.
24.
WeijtjensWNoppeNVerbelenT, et al. Offshore wind turbine foundation monitoring, extrapolating fatigue measurements from fleet leaders to the entire wind farm. J Phys: Conf Ser2016; 753: 092018.
25.
de Nolasco SantosFNoppeNWeijtjens, et al. Data-driven farm-wide fatigue estimation on jacket-foundation OWTs for multiple SHM setups. Wind Energy Sci2022; 7(1): 299–321.
26.
MbuvhaRJonssonMEhnN, et al. Bayesian neural networks for one-hour ahead wind power forecasting. In: 2017 IEEE 6th international conference on renewable energy research and applications (ICRERA), San Diego, USA, pp. 591–596. IEEE.
27.
WangYHuQMengD, et al. Deterministic and probabilistic wind power forecasting using a variational Bayesian-based adaptive robust multi-kernel regression model. Appl Energy2017; 208: 1097–1112.
28.
MbuvhaRMongweWTMarwalaT.Separable shadow Hamiltonian hybrid Monte Carlo for Bayesian neural network inference in wind speed forecasting. Energy AI2021; 6: 100–108.
29.
JospinLVLagaHBoussaidF, et al. Hands-on Bayesian neural networks — A tutorial for deep learning users. IEEE Comput Intell Mag2022; 17(2): 29–48.
30.
RitterHBotevABarberD.A scalable Laplace approximation for neural networks. In: ICLR 2018-Conference track proceedings: 6th international conference on learning representations, Vancouver, Canada.
31.
OsawaKSwaroopSKhanMEE, et al. Practical deep learning with Bayesian principles. In: Advances in neural information processing systems, Vancouver, Canada, vol. 32.
32.
WenzelFRothKVeelingB, et al. How good is the Bayes posterior in deep neural networks really? In: International conference on machine learning, 2020, pp. 10248–10259. PMLR. (online).
33.
MetropolisNRosenbluthAWRosenbluthMN, et al. Equation of state calculations by fast computing machines. J Chem Phys1953; 21(6): 1087–1092.
34.
HastingsWK.Monte Carlo sampling methods using Markov chains and their applications. Biometrika1970; 57(1): 97–109.
35.
RobertCPCasellaGCasellaG.Monte Carlo statistical methods. New York, USA: Springer, 1999, vol. 2.
36.
GravesA.Practical variational inference for neural networks. In: Proceedings of the 24th International Conference on Neural Information Processing Systems, Granada, Spain, 2011; pp. 2348–2356.
37.
KullbackSLeiblerRA.On information and sufficiency. Ann Math Statist1951; 22(1): 79–86.
38.
JamesGWittenDHastieT, et al. An introduction to statistical learning: with applications in R. New York, USA: Springer, 2013.
RichterLBoustatiANüskenN, et al. Vargrad: a low-variance gradient estimator for variational inference. Adv Neural Inf Process Syst2020; 33: 13481–13492.
41.
BengioYLéonardNCourvilleA.Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:13083432, 2013.
42.
DepewegSHernandez LobatoJMUdluftS, et al. Sensitivity analysis for predictive uncertainty in Bayesian neural networks. In: ESANN 2018 - Proceedings European symposium on artificial neural networks, computational intelligence and machine learning, Bruges, Belgium), pp. 279–284.
43.
DepewegSHernandez LobatoJMDoshi VelezF, et al. Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning. In: Proceedings of the 35th international conference on machine learning, vol. 80, pp. 1184–1193. PMLR.
44.
WangPBouaynayaNCMihaylovaL, et al. Bayesian neural networks uncertainty quantification with cubature rules. In: 2020 International joint conference on neural networks (IJCNN), Glasgow, UK, pp. 1–7.
WenYVicolPBaJ, et al. Flipout: efficient pseudo-independent weight perturbations on mini-batches. In: ICLR 2018-conference track proceedings: 6th international conference on learning representations, Vancouver, Canada.
50.
OstachowiczWSomanRMalinowskiP.Optimization of sensor placement for structural health monitoring: a review. Struct Health Monit2019; 18(3): 963–988.
51.
MoratoPGPapakonstantinouKGAndriotisCP, et al. Optimal inspection and maintenance planning for deteriorating structural components through dynamic Bayesian networks and Markov decision processes. Struct Saf2022; 94: 102140.
52.
PapakonstantinouKGShinozukaM.Planning structural inspection and maintenance policies via dynamic programming and Markov processes. Part II: POMDP implementation. Reliab Eng Syst Saf2014; 130: 214–224.
53.
AndriotisCPPapakonstantinouKG.Managing engineering systems with large state and action spaces through deep reinforcement learning. Reliab Eng Syst Saf2019; 191: 106483.
54.
MoratoPGAndriotisCPPapakonstantinouKG, et al. Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning. Reliab Eng Syst Saf2023; 235: 109144.
