Owing to its ability to harvest more power in deeper waters than other types of offshore wind turbines, the floating offshore wind turbine (FOWT) has attracted significant interest from both academics and industry. However, deterioration in system performance and unscheduled shutdowns will significantly increase operation and maintenance costs. To avoid system damage and ensure operation safety, there is a great demand for developing FOWT fault diagnosis to detect and identify faults as early as feasible. Due to the enormous complexity of FOWT including dynamics and nonlinearity, effective FOWT fault diagnosis poses a significant challenge. This paper develops a novel FOWT fault diagnosis method using bidirectional long short-term memory (BiLSTM) with sliding window. Firstly, the dynamics are embedded by stacking time-dependent measurements using the sliding window technique. Then, the augmented data is fed into a BiLSTM network to exploit the nonlinearity of FOWT. Consequently, a softmax classifier is used for fault diagnosis. A high-fidelity 10 MW spar FOWT benchmark based on the NREL Fatigue, Aerodynamics, Structures, and Turbulence (FAST) model is used to validate the capability and effectiveness of the proposed method. Experimental results show that the proposed method outperforms other related methods in diagnosing critical faults in FOWTs under various operating conditions.
KumarYRingenbergJDepuruA, et al.Wind energy: trends and enabling technologies. Renew Sustain Energy Rev2016; 53: 209–224.
2.
DeCastroMSalvadorSGómez-GesteiraM, et al.Europe, China and the United States: three different approaches to the development of offshore wind energy. Renew Sustain Energy Rev2019; 109: 55–57.
3.
ButterfieldSMusialWJonkmanJ, et al.Engineering challenges for floating offshore wind turbines. Golden, CO (United States): National Renewable Energy Lab.(NREL), 2007.
4.
SubbulakshmiAVermaMKeerthanaM, et al.Recent advances in experimental and numerical methods for dynamic analysis of floating offshore wind turbines—an integrated review. Renew Sustain Energy Rev2022; 164: 112525.
5.
JiangZ. Installation of offshore wind turbines: a technical review. Renew Sustain Energy Rev2021; 139: 110576.
6.
OtterAMurphyJPakrashiV, et al.A review of modelling techniques for floating offshore wind turbines. Wind Energy2022; 25(5): 831–857.
7.
LiuYFerrariRWuP, et al.Fault diagnosis of the 10MW floating offshore wind turbine benchmark: a mixed model and signal-based approach. Renew Energy2021; 164: 391–406.
8.
KangJSunLSoaresCG. Fault Tree Analysis of floating offshore wind turbines. Renew Energy2019; 133: 1455–1467.
9.
RenZVermaASLiY, et al.Offshore wind turbine operations and maintenance: a state-of-the-art review. Renew Sustain Energy Rev2021; 144: 110886.
10.
GaoZLiuX. An overview on fault diagnosis, prognosis and resilient control for wind turbine systems. Processes2021; 9(2): 300.
11.
BadihiHZhangYJiangB, et al.A comprehensive review on signal-based and model-based condition monitoring of wind turbines: fault Diagnosis and lifetime prognosis. Processes2022; 110(6): 754–806.
12.
JlassiIEstimaJOKhilE, et al.Multiple open-circuit faults diagnosis in back-to-back converters of PMSG drives for wind turbine systems. IEEE Trans Power Electron2014; 30(5): 2689–2702.
13.
SimaniSFarsoniSCastaldiP. Fault diagnosis of a wind turbine benchmark via identified fuzzy models. IEEE Trans Ind Electron2014; 62(6): 3775–3782.
14.
ShaoHGaoZLiuX, et al.Parameter-varying modelling and fault reconstruction for wind turbine systems. Renew Energy2018; 116: 145–152.
15.
WeiXVerhaegenMvan EngelenT. Sensor fault detection and isolation for wind turbines based on subspace identification and Kalman filter techniques. Int J Adapt Control Signal Process2010; 24(8): 687–707.
16.
BessaDValenteIPalharesRM, et al.Data-driven fault detection and isolation scheme for a wind turbine benchmark. Renew Energy2016; 87: 634–645.
17.
ZhangDQianLMaoB, et al.A data-driven design for fault detection of wind turbines using random forests and XGboost. IEEE Access2018; 6: 21020–21031.
18.
ZhengXWangSQianY. Fault feature extraction of wind turbine gearbox under variable speed based on improved adaptive variational mode decomposition. Proc Inst Mech Eng A J Power Energy2023; 234(6): 848–861.
19.
LiuWWangZHanJ, et al.Wind turbine fault diagnosis method based on diagonal spectrum and clustering binary tree SVM. Renew Energy2013; 50: 1–6.
20.
PashazadehVSalmasiFRAraabiBN. Data driven sensor and actuator fault detection and isolation in wind turbine using classifier fusion. Renew Energy2018; 116: 99–106.
21.
HelbingGRitterM. Deep Learning for fault detection in wind turbines. Renew Sustain Energy Rev2018; 98: 189–198.
22.
JiangGXiePHeH. Wind turbine fault detection using a denoising autoencoder with temporal information. IEEE/Asme transactions on mechatronics2017; 1: 89–100.
23.
YangLZhangZ. Wind turbine gearbox failure detection based on SCADA data: a deep learning-based approach. IEEE Trans Instrum Meas2020; 70: 1–11.
24.
LuWLiYChengY, et al.Early fault detection approach with deep architectures. IEEE Trans Instrum Meas2018; 67(7): 1679–1689.
25.
LeiJLiuCJiangD. Fault diagnosis of wind turbine based on Long Short-term memory networks. Renew Energy2019; 133: 422–432.
26.
ChoeD-EKimH-CKim, et al.Sequence-based modeling of deep learning with LSTM and GRU networks for structural damage detection of floating offshore wind turbine blades. Renew Energy2021; 174: 218–235.
27.
ChenYZhengX. Fault diagnosis of wind turbine based on multi-signal CNN-GRU model. Proc Inst Mech Eng A J Power Energy2023; 237(5): 1113–1124.
28.
SchusterMPaliwalKK. Bidirectional recurrent neural networks. IEEE Trans Signal Process1997; 45(11): 2673–2681.
29.
HuangZXuWYuK. Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.019912015.
30.
ZhaoRYanRWangJ, et al.Learning to monitor machine health with convolutional bi-directional LSTM networks. Sensors2017; 17(2): 273.
31.
ZhangCHuDYangT. Anomaly detection and diagnosis for wind turbines using long short-term memory-based stacked denoising autoencoders and XGBoost. Reliab Eng Syst Saf2022; 222: 108445.
32.
ZhangXWuPHeJ, et al.Floating offshore wind turbine fault diagnosis using stacked denoising autoencoder with temporal information. Trans Inst Meas Control2021; 2: 01423312211057994.
33.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9(8): 1735–1780.
34.
ChoSChoiMGaoZ, et al.Fault detection and diagnosis of a blade pitch system in a floating wind turbine based on Kalman filters and artificial neural networks. Renew Energy2021; 169: 1–13.
35.
OdioweiP-EPCaoY. Nonlinear dynamic process monitoring using canonical variate analysis and kernel density estimations. IEEE Trans Ind Inf2021; 6(1): 36–45.
36.
BakCZahleFBitscheR, et al. (2013) The DTU 10-MW reference wind turbine. In: Danish wind power research 2013.
37.
LemmerFAmannFRaachS, et al.Definition of the swe-triplespar floating platform for the DTU 10MW reference wind turbine. 2016.
38.
HasselmannKBarnettTPBouwsE, et al.Measurements of wind-wave growth and swell decay during the Joint North Sea wave Project (JONSWAP). In: Ergaenzungsheft zur Deutschen Hydrographischen Zeitschrift, Reihe A1973.
39.
FontanellaABayatiIBelloliM. Control of floating offshore wind turbines: reduced-order modeling and real-time implementation for wind tunnel tests. In: ASME 2018 37th Int. Conf. on Ocean, Offshore and Arctic Engineering2018, V010T09A081.
40.
OdgaardPFStoustrupJKinnaertM. Fault-tolerant control of wind turbines: a benchmark model. IEEE Trans Control Syst Technol2013; 21(4): 1168–1182.
41.
JosephVR. Optimal ratio for data splitting. Stat Anal Data Min: The ASA Data Science Journal2022; 15(4): 531–538.
42.
SmithLN. A disciplined approach to neural network hyper-parameters: Part 1-learning rate, batch size, momentum, and weight decay. arXiv preprint arXiv:1803.098202018; 15(4): 531–538.
43.
XuZBashirMYangY, et al.Multisensory collaborative damage diagnosis of a 10 MW floating offshore wind turbine tendons using multi-scale convolutional neural network with attention mechanism. Renew Energy2022; 199: 21–34.
