A System Reliability Analysis Method for Offshore Wind Turbine Foundation

 

Kang Haigui, Li Yugang, Wu Fanghe,
Guo Wei, and Huan Caiyun

State Key Laboratory of Coastal and Offshore Engineering,
Dalian University of Technology, Dalian. 116024, China
Email: li_yg2003@163.com

 

ABSTRACT

Offshore wind energy is one of the most attractive sources of renewable energy. During the last decade, offshore wind turbines were extensive application throughout Europe. However, the reliability of offshore wind turbines especially foundations is one of the currently challenges. Simulation based methods are often used to calculate an accurate value for the reliability of structures, one of the major disadvantages however is the large number of simulations required to obtain an accurate estimate of the failure probability. To meet this disadvantage, a new simulation method based on support vector machine (SVM) is proposed in this paper, SVM is a relatively new computational learning method, it is especially efficient in classification problem. In the proposed method, Latin hypercube sampling (LHS) is adopted for the preliminary samples and the SVM response surface indicator is refined by adaptively increasing the sample points, then the MCS scheme is implemented. The objective of this paper is to further increase the efficiency of simulation based reliability methods. The overall performance of the technique is addressed referring to a benchmark example.

Keywords: Renewable energy; Offshore wind turbines; Foundations; Reliability; Support vector machine; Monte Carlo Simulation.

Get the entire paper (pdf)     Go back to the TOC