A surrogate model for estimating extreme tower loads on wind turbines based on random forest proximities

ABSTRACT

In the present paper, we present a surrogate model, which can be used to estimate extreme tower loads on a wind turbine from a number of signals and a suitable simulation tool. Due to the requirements of the International Electrotechnical Commission (IEC) Standard 61400-1, assessing extreme tower loads on wind turbines constitutes a key component of the design phase. The proposed model imputes tower loads by matching observed signals with simulated quantities using proximities induced by random forests. In this way, the algorithm's adaptability to high-dimensional and sparse settings is exploited without using regression-based surrogate loads (which may display misleading probabilistic characteristics). Finally, the model is applied to estimate tower loads on an operating wind turbine from data on its operational statistics.

Keywords:

• Extreme load estimation
• matching
• random forests
• surrogate models
• wind turbines

2010 Mathematics Subject Classifications:

• 62P30
• 65C20
• 91B68

Acknowledgments

We thank James Alexander Nichols from Vestas (Loads & Control) and Jan Pedersen for fruitful discussions. Furthermore, we thank the anonymous referees for their valuable comments.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the Det Frie Forskningsråd (Danish Council for Independent Research) [grant numbers 4002-00003 and 9056-00011B].