Skip to main content
SpringerLink
Log in

Sea state estimation using monitoring data by convolutional neural network (CNN)

  • Original article
  • Published:
Journal of Marine Science and Technology Aims and scope Submit manuscript

Abstract

In recent years, the size of container ships has become larger, thus requiring a more evident assurance of the hull structural safety. In order to evaluate the structural safety in operation, it is necessary to grasp the encountered sea state. The aim of this study is to estimate the encountered sea state using machine learning from measurement data of ocean-going 14,000TEU container ships. In this paper, as a first step in the study, considerable amounts of virtual sea state data and corresponding ship motion and structural response data are prepared. A convolutional neural network (CNN) is developed using these data to estimate the directional wave spectrum of encountered sea based on the hull responses. The input parameters of the formulated CNN include the spectral values of ship motion and structural response spectrum. The output of the CNN includes the sea state parameters of the Ochi-Hubble spectrum, specifically, significant wave height, modal wave frequency, mean wave direction, kurtosis, and concentration of wave energy directional distribution. It is found from the performance examination that the developed CNN is capable of accurately estimating the sea state parameters, although the level of accuracy decreases when the hull response is low. However, the decrease in accuracy when the hull response is low has a weak influence on the evaluation of the structural response to the estimated sea state.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Okada T (1994) Integrated hull condition monitoring system—technical issues (hull design and construction). Integrated Hull Condition Monitoring System (IHCMS) Seminar, Sydney, Tokyo, London

  2. Fujikubo M (2019) Digital twin for ship structures—research project in japan. In: Presented at plenary lecture, the 14th international symposium on practical design of ships and other floating structures (PRADS 2019), Yokohama

  3. Chen X, Okada T, Kawamura Y, Mitsuyuki T (2019) Estimation of on-site directional wave spectra using measured hull stresses on 14,000TEU large container ships. J Mar Sci Technol 25:690–706

    Article  Google Scholar 

  4. Okada T et al (2017) Outline of the research project on hull structure health monitoring of 14,000TEU large container ships. Conf Proc Jpn Soc Nav Archit Ocean Eng 24:31–35 (in Japanese)

    Google Scholar 

  5. Collette M, Zhan Z, Zhu L, Zanic V, Okada T, Arima T, Skjong R, Jeong H, Egorov G (2018) Committee IV.1 Design principal and criteria. In: Proceedings of the 20th international ship and offshore structures congress (ISSC 2018), pp 549–607

  6. Tannuri E, Sparano J, Simos A, Da Cruz J (2003) Estimating directional wacve spectrum based on stationary ship motion measurements. Appl Ocean Res 25(5):243–261

    Article  Google Scholar 

  7. Iseki T, Ohtsu K, Fujino M (1992) Bayesian estimation of directional wave spectra based on ship motions. J Soc Nav Archit Jpn 172:17–25

    Article  Google Scholar 

  8. Iseki T, Ohtsu K, Fujino M (1994) Bayesian estimation of directional wave spectra based on ship motions. J Soc Nav Archit Jpn 176:99–105

    Article  Google Scholar 

  9. Nielsen UD (2006) Estimation of on-site directional wave spectra from measured ship responses. Marine Struct 19(1):33–69

    Article  Google Scholar 

  10. Nielsen UD, Stredulinksy DC (2012) Sea state estimation from an advancing ship—a comparative study using sea trial data. Appl Ocean Res 34:33–44

    Article  Google Scholar 

  11. Nielsen UD, Andersen IMV, Koning J (2013) Comparisons of means for estimating sea states from an advancing large container ship. In: Proceedings of 12th PRADS, Changwon, South Korea

  12. Nielsen UD (2017a) Transformation of a wave energy spectrum from encounter to absolute domain when observing from an advancing ship. Appl Ocean Res 69:160–172

    Article  Google Scholar 

  13. Nielsen UD (2018) Sea state estimation using simultaneous data from multiple observation platforms. Conf Proc Jpn Soc Nav Archit Ocean Eng 27:37–40

    Google Scholar 

  14. Chen X, Okada T, Kawamura Y (2018) Sea state estimation using measured hull response on 14,000TEU large container ships. In: Proceedings of 7th international maritime conference, Kobe, pp 160–168

  15. Nielsen UD (2017b) A concise account of techniques available for shipboard sea state estimation. Ocean Eng 129:352–362

    Article  Google Scholar 

  16. Cheng X, Li G, Skulstad R, Chen S, Hildre H, Zhang H (2019) Modeling and analysis of motion data from dynamically positoined vessels for sea state estimation. In: 2019 internatonal conference on robotics and automation (ICRA), IEEE, pp 6644–6650

  17. Cheng X, Li G, Ellefsen A, Chen S, Hildre H, Zhang H (2020) A novel densely connected convolutional neural network for sea state estimation using ship motion data. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2020.2967115

    Article  Google Scholar 

  18. Duz B, Mak B, Hageman R, Grasso N (2019) Real time estimation of local wave characteristics from ship motions using artificial neural networks. In: Proceedings of the 14th International symposium on practical design of ships and other floating structures, Yokohama

  19. Mak B, Duz B (2019) Ship as a wave buoy—using simulated data to train neural networks for real time estimation of relative wave direction. In: Proceedings of the ASME 2019 38th international conference on ocean, offshore & artic engineering, Glasgow

  20. Yoo H, Han S, Chung K (2020) A frequency pattern mining model based on deep neural network for real-time classification of heart conditions. Healthcare 8(3):234. https://doi.org/10.3390/healthcare8030234

    Article  Google Scholar 

  21. Ochi MK, Hubble EN (1976) Six-parameter wave spectra. In: Proceedings of the 15th coastal engineering conference, vol 1, pp 301–328

  22. Goda Y, Suzuki Y (1975) Computation of refraction and diffraction of sea waves with Mitsuyasu’s directional spectrum, vol 230. Technical Note of the Port and Harbor Research Institute Ministry of Transport, Japan

  23. Ou N, Kawai T (2018) A study on sea state estimation using monitoring data of large container ships. Graduate Thesis, Department of Architecture, Infrastructure, Ocean Engineering and Ecosystem Science, College of Engineering Science, Yokohama National University (in Japanese)

  24. Ou C, et al. (2012) An advanced genetic algorithm based on automatic regulating crossover and mutation probabilities. In: Proceedings of joint conference of electrical and electronics engineering in Kyushu, vol 65, p 349 (in Japanese)

  25. Global wave statistics (1986) British Maritime Technology Limited

  26. Nielsen UD, Jensen J (2011) Onboard monitoring of fatigue damage rates in the hull girder. Marine Struct 24:182–206

    Article  Google Scholar 

  27. Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65(6):386–408

    Article  Google Scholar 

  28. Rumelhart D, Mcclelland J (1986) Parallel distributed processing. Explorations in the microstructure of cognition. MIT Press, Cambridge

    Book  Google Scholar 

  29. Goodfellow I, Bengio Y, Courville A (2016) Deep learning (adaptive computation and machine learning series). MIT Press, Cambridge

    MATH  Google Scholar 

  30. Jarret K, Kayukcuoglu K, Lecun Y, Ranzato M (2009) What is the best multi-stage architecture for object recognition? In: Proceedings of 2009 IEEE 12th international conference on computer vision, Kyoto

  31. Fukushima K, Miyake S (1982) Neocognitron: a new algorithm for pattern recognition tolerant of deformations and shifts in position. Pattern Recogn 15(6):455–469

    Article  Google Scholar 

  32. LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  33. Shelhamer E, Long J, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of CVPR, Boston

  34. Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encorder-decorder architecture for image segmentation. IEEE Transact Pattern Anal Mach Intell (TPAMI) 32(12):2481–2495

    Article  Google Scholar 

  35. Yurdakul EE, Yemez Y (2017) Semantic segmentaion of RGBD videos with recurrent fully convolutional neural networks. In: 2017 IEEE international conference on computer vision workshop (ICCVW), vol 1, pp 367–374

  36. Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of NIPS, Quebec

  37. Liu W, Anguelov D, Erhan D, et al. (2016) SSD: single shot multibox detector. In: Proceedings of 14th European conference on computer vision (ECCV 2016), Amsterdam, Part I, pp 21–37

  38. Wei S-E, Ramakrishna V, Kanade T, Sheikh Y (2016) Convolutional pose machines. In: Proceedings of 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas

  39. Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: Proceedings of 14th European conference on computer vision (ECCV 2016), Amsterdam, Part VIII, pp 483–499

  40. Kim Y (2014) Convolutional neural networks for sentence classification. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), Doha, pp 1746–1751

  41. Gehring J, Auli M, Grangier D, Dauphin YN (2017) Convolutional sequence to sequence learning. In: Proceedings of the 34th international conference on machine learning, Sydney, vol 70, pp 1243–1252

  42. Oord A, Dieleman S, Zen H, Simonyan K, et al. (2016) Wavenet: a generative model for raw audio. Google DeepMind, London.arXiv:1609.03499

  43. Hasegawa T et al (2019) Automatic electron density determination by using a convolutional neural network. J IEEE Access 7:163384–163394

    Article  Google Scholar 

  44. Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS 2011), vol 15, Florida, pp 315–323

  45. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. In: Proceedings of the 3rd international conference on learning representations (ICLR 2015), San Diego. arXiv:1412.6980

  46. McClure N (2018) TensorFlow Machine Learning Cookbook Second Edition. Packt Publishing

  47. Fisher NI, Lee AJ (1983) A correlation coefficient for circular data. Biometrika 70(2):327–332

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgements

This study was conducted as a part of the collaborative research project “Hull structure health monitoring of 14,000TEU large container ships” under the support of the Ministry of Land, Infrastructure, Transportation and Tourism of Japan for i-Shipping Operation of Advanced Vessel Technology. The authors express gratitude to the project members from Japan Marine United Corporation, ClassNK, National Maritime Research Institute, Japan Weather Association, NYK Line, and MTI Co., Ltd. for their inputs and support. This work was also supported by JSPS KAKENHI (Grant No. 19H02356); the authors are grateful for the support.

Author information

Authors and Affiliations

  1. Graduate School of Engineering, Yokohama National University, Yokohama, Kanagawa, 240-8501, Japan

    Toshiki Kawai

  2. Faculty of Engineering, Yokohama National University, Yokohama, Kanagawa, 240-8501, Japan

    Yasumi Kawamura, Tetsuo Okada, Taiga Mitsuyuki & Xi Chen

Authors
  1. Toshiki Kawai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yasumi Kawamura
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tetsuo Okada
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Taiga Mitsuyuki
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xi Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Toshiki Kawai.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kawai, T., Kawamura, Y., Okada, T. et al. Sea state estimation using monitoring data by convolutional neural network (CNN). J Mar Sci Technol 26, 947–962 (2021). https://doi.org/10.1007/s00773-020-00785-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00773-020-00785-8

Keywords

Search

Navigation