To diagnose the attachment of marine current turbine, this article proposes a method based on convolutional neural network and the concepts of depthwise separable convolution to achieve feature extraction. The method consists of three steps: data preprocessing, feature extraction and fault diagnosis. This method can diagnose the fault degree of blade imbalance and uniform attachment in underwater environment with strong currents and complex spatiotemporal variability. It can extract distinct image feature in harsh marine environments by using a convolutional neural network. In addition, this method is robust for the recognition of blurred pictures under high-speed rotation.
MüllerNKouroSMalinowskiM, et al. Medium-voltage power converter interface for multigenerator marine energy conversion systems. IEEE T Ind Electron2016; 64(2): 1061–1070.
2.
FerreiraRMEstefenSFRomeiserR. Under what conditions SAR along-track interferometry is suitable for assessment of tidal energy resource. IEEE J Select Topic Appl Earth Observ Remote Sens2016; 9(11): 5011–5022.
3.
LawrenceJSedgwickJJeffreyH, et al. An overview of the UK marine energy sector. Proc IEEE2013; 101(4): 876–890.
4.
Sapena-BanoARiera-GuaspMPuche-PanaderoR, et al. Harmonic order tracking analysis: a speed-sensorless method for condition monitoring of wound rotor induction generators. IEEE T Ind Appl2016; 52(6): 4719–4729.
5.
ZhangMTangTWangT. Multi-domain reference method for fault detection of marine current turbine. In: IECON 2017-43rd annual conference of the IEEE industrial electronics society, Beijing, China, 29 October–1 November 2017, pp.8087–8092. New York: IEEE.
6.
ShiXCaoYWangZ, et al. Fault diagnosis of planetary gear based on wavelet real modulation zooming and resonance demodulation. In: 2017 IEEE international conference on information and automation (ICIA), Macau, China, 18–20 July 2017, pp.231–235. New York: IEEE.
7.
ZhangMWangTTangT. A multi-mode process monitoring method based on mode-correlation PCA for marine current turbine. In: 2017 IEEE 11th international symposium on diagnostics for electrical machines, power electronics and drives (SDEMPED), Tinos, 29 August–1 September 2017, pp.286–291. New York: IEEE.
8.
ZhangMWangTTangT, et al. Imbalance fault detection of marine current turbine under condition of wave and turbulence. In: IECON 2016-42nd annual conference of the IEEE industrial electronics society, Florence, 23–26 October 2016, pp.6353–6358. New York: IEEE.
9.
ShaoHGaoZBusawonK. LPV modelling and LPV observer-based fault detection for wind turbine systems. In: 2016 IEEE 14th international conference on industrial informatics (INDIN), Poitiers, 19–21 July 2016, pp.467–470. New York: IEEE.
10.
KrishnaCRYadavPS. A hybrid localization scheme for underwater wireless sensor networks. In: 2014 International conference on issues and challenges in intelligent computing techniques (ICICT), Ghaziabad, India, 7–8 February 2014, pp.579–582. New York: IEEE.
11.
WangYKarimiHRLamHK, et al. Fuzzy output tracking control and filtering for nonlinear discrete-time descriptor systems under unreliable communication links. IEEE T Cybernet2019; 50: 2369–2379.
12.
AlvarezACaitiAOnkenR. Evolutionary path planning for autonomous underwater vehicles in a variable ocean. IEEE J Ocean Eng2004; 29(2): 418–429.
13.
McGeeJCatipovicJSchoeneckerS, et al. Interference suppression in congested undersea environments. In: OCEANS 2015-Genova, Genoa, 18–21 May 2015, pp.1–8. New York: IEEE.
14.
WuZKarimiHRDangC. An approximation algorithm for graph partitioning via deterministic annealing neural network. Neural Netw2019; 117: 191–200.
15.
KarimiHR*Jabedar MaralaniPLohmannB, et al. H∞ control of parameter-dependent state-delayed systems using polynomial parameter-dependent quadratic functions. Int J Control2005; 78(4): 254–263.
16.
WangYZhouWLuoJ, et al. Reliable intelligent path following control for a robotic airship against sensor faults. IEEE/ASME T Mechatron2019; 24: 2572–2582.
17.
HuangLZhaoXHuangX, et al. Underwater camera model and its use in calibration. In: 2015 IEEE international conference on information and automation, Lijiang, China, 8–10 August 2015, pp.1519–1523. New York: IEEE.
18.
KrizhevskyASutskeverIHintonGE.Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, Lake Tahoe, Nevada, 3–6 December 2012, pp.1097–1105.
19.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition, 2014, https://arxiv.org/abs/1409.1556
20.
HeKZhangXRenS, et al. Deep residual learning for image recognition In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, 27–30 June 2016, pp.770–778. New York: IEEE.
21.
SzegedyCLiuWJiaY, et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, MA, 7–12 June 2015, pp.1–9. New York: IEEE.
22.
SzegedyCVanhouckeVIoffeS, et al. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, 27–30 June 2016, pp.2818–2826. New York: IEEE.
23.
SzegedyCIoffeSVanhouckeV, et al. Inception-V4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence, San Francisco, CA, 4–9 February 2017. Palo Alto, CA: AAAI Press.
24.
IoffeSSzegedyC. Batch normalization: accelerating deep network training by reducing internal covariate shift, 2015, https://arxiv.org/abs/1502.03167
25.
ZhouFYangSFujitaH, et al. Deep learning fault diagnosis method based on global optimization GAN for unbalanced data. Knowl Based Syst2020; 187: 104837.
26.
LeCunYBottouLBengioY, et al. Gradient-based learning applied to document recognition. Proc IEEE1998; 86(11): 2278–2324.
27.
ChenHTangTAït -AhmedN, et al. Attraction, challenge and current status of marine current energy. IEEE Access2018; 6: 12665–12685.
28.
ZhangMWangTTangT, et al. An imbalance fault detection method based on data normalization and EMD for marine current turbines. ISA Trans2017; 68: 302–312.
29.
ZhengYWangTXinB, et al. A sparse autoencoder and softmax regression based diagnosis method for the attachment on the blades of marine current turbine. Sensors2019; 19(4): 826.
30.
CholletF. Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, 21–26 July 2017, pp.1251–1258. New York: IEEE.
31.
HowardAGZhuMChenB, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications, 2017, https://arxiv.org/abs/1704.04861
32.
SandlerMHowardAZhuM, et al. MobilenetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, 18–23 June 2018, pp.4510–4520. New York: IEEE.
33.
HowardASandlerMChuG, et al. Searching for mobilenetV3. In: Proceedings of the IEEE international conference on computer vision, Seoul, 27 October–2 November 2019, pp.1314–1324. New York: IEEE.
34.
ZophBVasudevanVShlensJ, et al. Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, 18–23 June 2018, pp.8697–8710. New York: IEEE.
35.
HuangGLiuZVan Der MaatenL, et al. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, 21–26 July 2017, pp.4700-4708. New York: IEEE.
