Advertisement

State-of-the-Art and Future Directions for Predictive Modelling of Offshore Structure Dynamics Using Machine Learning

  • U. T. Tygesen
  • K. Worden
  • T. Rogers
  • G. Manson
  • E. J. Cross
Conference paper
Part of the Conference Proceedings of the Society for Experimental Mechanics Series book series (CPSEMS)

Abstract

Ramboll Oil and Gas are leading the field in the development of Structural Health Monitoring Systems (SHMS) for offshore structures. This paper outlines the State-of-the-Art process for predictive maintenance that Ramboll have developed and implemented for offshore structures. This system is one of the first, if not the only one, that creates a maintenance schedule based on knowledge of the structure’s current state.

The State-of-the-Art methods of today, as adopted by Ramboll, encompass advanced analysis methods ranging from linear and non-linear system identification, expansion processes, Bayesian FEM updating, wave load calibration, quantification of uncertainties from measured data, damage detection and structural re-assessment analysis to Risk- and Reliability-Based Inspection Planning (RBI) analysis.

The paper will be the first in a series of papers that will outline various promising methods contributing to an even better understanding of the issues at stake in the offshore structures context.

Keywords

Linear and nonlinear system identification FEM updating Modal expansion Wave load calibration Digital twin Uncertainties Predictive maintenance Machine learning Grey-box 

Notes

Acknowledgement

The authors wish to thank the oil and gas operators in the Danish North Sea: Maersk Oil, Hess Denmark and DONG Energy for their participation in several projects forming the basis for the developed methods as of today. TR specially wishes to thank Ramboll for providing financial support for this work.

References

  1. 1.
    OGP Standard Committee: Reliability of offshore structures – current design and potential inconsistencies, OGP report no. 486. International Association of Oil and Gas Producers (OGP, IOGP) (Mar 2014)Google Scholar
  2. 2.
    Ramboll Oil and Gas: ROSAP, program ROSA, structural analysis, user’s guide. Ramboll Offshore Structural Analysis Program Package (ROSAP), Rev. 5.1 (Feb 2017)Google Scholar
  3. 3.
    Hansen, J.B., Brincker, R., Knudsen, M.B., Tygesen, U.: Combining GPS and integrated sensor signals. In: International Operational Modal Analysis Conference, Istanbul, Turkey (2011)Google Scholar
  4. 4.
    Skafte, A., Tygesen, U., Brincker, R.: Expansion of mode shapes and responses on the offshore platform Valdemar. In: International Modal Analysis Conference (IMAC), Orlando, FL, USA (2014)CrossRefGoogle Scholar
  5. 5.
    Dascotte, E., Strobbe, J., Tygesen, U.T.: Continuous stress monitoring of large structures. In: International Operational Modal Analysis Conference (IOMAC), Guimaraes, Portugal (2013)Google Scholar
  6. 6.
    Brincker, R., Andersen, P.: Understanding stochastic subspace identification. In: Proceedings of the 24th International Modal Analysis Conference (IMAC), St. Louis, MO, USA (2006)Google Scholar
  7. 7.
    Peeters, B., Van der Auweraer, H., Guillaume, P., Leuridan, J.: The PolyMAX frequency-domain method: a new standard for modal parameter estimation Shock Vib. 11, 395–409 (2004.) IOS PressGoogle Scholar
  8. 8.
    Brincker, R., Zhang, L., Andersen, P.: Modal identification from ambient response using frequency domain decomposition. In: Proceedings of the 18th International Modal Analysis Conference (IMAC), San Antonio, TX, USA, pp. 625–630 (2000)Google Scholar
  9. 9.
    Zhang, L., Brincker, R., Andersen, P.: An overview of operational modal analysis: major development and issues. In: Proceedings of the 1st International Operational Modal Analysis Conference (IOMAC), Copenhagen, Denmark (2005)Google Scholar
  10. 10.
    Green, P.L., Tygesen, U.T., Stevanovic, N.: Bayesian modelling of offshore platforms. In: The Society for Experimental Mechanics (SEM), International Modal Analysis Conference (IMAC), Model Validation and Uncertainty Quantification, Orlando, FL, USA (2016)CrossRefGoogle Scholar
  11. 11.
    Perisic, N., Kirkegaard, P.H., Tygesen, U.T.: Load identification of offshore platform for fatigue life estimation. In: International Modal Analysis Conference (IMAC), Orlando, FL, USA (2014)Google Scholar
  12. 12.
    Perisic, N., Tygesen, U.T.: Cost-effective load monitoring methods for fatigue life estimation of offshore platform. In: Proceedings from the ASME 2014 33rd International Conference on Ocean, Offshore and Artic Engineering (OMAE), San Francisco, CA, USA (2014)Google Scholar
  13. 13.
    Lauwagie, T., Guggenberger, J., Strobbe, J., Dascotte, E.: Model updating using operational data. In: International Conference on Noise and Vibration Engineering (ISMA), Leuven, Belgium (2010)Google Scholar
  14. 14.
    O’Callahan, J., Avitabile, P., Riemer, R.: System Equivalent Reduction Expansion Process (SEREP). In: Proceeding of the 7th International Modal Analysis Conference (IMAC), pp. 29–37 (1989)Google Scholar
  15. 15.
    Sohn, H., Law, K.H.: Extraction of Ritz vectors from vibration test data. Mech. Syst. Signal Process. 15, 231–226 (2001)CrossRefGoogle Scholar
  16. 16.
    Skafte, A., Kristoffersen, J., Vestermark, J., Tygesen, U.T., Brincker, R.: Experimental study of strain prediction on wave induced structures using modal decomposition and quasi static Ritz vectors. J. Eng. Struct. 136, 261–276 (2017.) ElsevierCrossRefGoogle Scholar
  17. 17.
    Fletcher, R.: Practical Methods of Optimization, 2nd edn. John Wiley & Sons (2013).  https://doi.org/10.1002/9781118723203
  18. 18.
    Simon, D.: Evolutionary Optimization Algorithms. John Wiley & Sons, Inc., Hoboken, New Jersey (2013)Google Scholar
  19. 19.
    Ulriksen, M.D., Tcherniak, D., Hansen, L.M., Johansen, R.J., Damkilde, L., Frøyd, L.: In-situ damage localization for a wind turbine blade through outlier analysis of SDDLV-induced stress resultants. Struct. Health Monit. 16, 745–761 (2017)CrossRefGoogle Scholar
  20. 20.
    Ulriksen, M.D., Damkilde, L.: Structural Damage Localization by Outlier Analysis of Signal-processed Mode Shapes: Analytical and Experimental Validation. Mechanical Systems and Signal Processing. 68-69(February), 1–14 (2015).  https://doi.org/10.1016/j.ymssp.2015.07.021 CrossRefGoogle Scholar
  21. 21.
    Dohler, M., Hille, F.: Subspace-based damage detection on steel frame structure under changing excitation. In: International Modal Analysis Conference (IMAC), Orlando, FL, USA (2014)CrossRefGoogle Scholar
  22. 22.
    DNVGL-RP-C210: Probabilistic Methods for Planning of Inspection Planning for Fatigue Cracks in Offshore Structures. DNV-GL Recommended Practice, Edition (Nov 2015)Google Scholar
  23. 23.
    Rogers, T., Holmes, G.R., Cross, E.J., Worden, K.: On a Grey Box modelling framework for nonlinear system identification. In: Special Topics in Structural Dynamics, vol. 6, pp. 167–178. Springer Link (Mar 2017)CrossRefGoogle Scholar
  24. 24.
    Worden, K., Rogers, T., Cross, E.J.: Identification of nonlinear wave forces using Gaussian process NARX models. In: Nonlinear Dynamics, vol. 1, pp. 203–221. Springer Link (May 2017)CrossRefGoogle Scholar
  25. 25.
    Dervilis, N., Cross, E.J., Barthorpe, R.J., Worden, K.: Robust methods of inclusive outlier analysis for structural health monitoring. J. Sound Vib. 333, 5181–5195 (2014)CrossRefGoogle Scholar
  26. 26.
    Cross, E.J., Worden, K., Chen, Q.: Cointegration: a novel approach for the removal of environmental trends in structural health monitoring data. Proc. R. Soc. A. 467, 2712–2732 (2011).  https://doi.org/10.1098/rspa.2011.0023 CrossRefzbMATHGoogle Scholar

Copyright information

© The Society for Experimental Mechanics, Inc. 2019

Authors and Affiliations

  • U. T. Tygesen
    • 1
  • K. Worden
    • 2
  • T. Rogers
    • 2
  • G. Manson
    • 2
  • E. J. Cross
    • 2
  1. 1.Ramboll Oil and GasEsbjergDenmark
  2. 2.Dynamics Research Group, Department of Mechanical EngineeringUniversity of SheffieldSheffieldUK

Personalised recommendations