Gaining insight in wind turbine drivetrain dynamics by means of automatic operational modal analysis combined with machine learning algorithms
Gioia, N.; Daems, P.J.; Peeters, C.; Guillaume, P.; Helsen, J.; Medico, R.; Deschrijver, D. (2019). Gaining insight in wind turbine drivetrain dynamics by means of automatic operational modal analysis combined with machine learning algorithms, in: ASME 2019 38th International Conference on Ocean, Offshore and Arctic Engineering - Volume 10: Ocean Renewable Energy. pp. 7 In: (2019). ASME 2019 38th International Conference on Ocean, Offshore and Arctic Engineering - Volume 10: Ocean Renewable Energy. ASME: [s.l.]. ISBN 978-0-7918-5889-9. , more |
| Authors | | Top | - Gioia, N.
- Daems, P.J., more
- Peeters, C.
- Guillaume, P., more
| - Helsen, J., more
- Medico, R.
- Deschrijver, D.
| |
| Abstract | Detailed knowledge about the modal model is essential to enhance the NVH behavior of (rotating) machines. To have more realistic insight in the modal behavior of the machines, observation of modal parameters must be extended to a significant amount of time, in which all the significant operating conditions of the turbine can be investigated, together with the transition events from one operating condition to another. To allow the processing of a large amount of data, automated OMA techniques are used: once frequency and damping values can be characterized for the important resonances, it becomes possible to gain insights in their changes. This paper will focus on processing experimental data of an offshore wind turbine gearbox and investigate the changes in resonance frequency and damping over time. |
|
