Extreme learning machine for fault detection and isolation in wind turbine
Ayoub El Bakri, Miloud Koumir, Ismail Boumhidi · 2016
This paper proposes a new scheme for fault detection and isolation (FDI) in variable speed wind turbine. The proposed scheme is based on an intelligent data-driven fault detection scheme using the extreme learning machine approach (ELM). The ELM is a kind of single hidden layer feed-forward neural network (SLFNN) with a fast learning. The basic idea is the use of a certain number n of ELM classifiers to deals with n types of faults affecting the wind turbine. Different parts of the process were investigated including actuators and sensors faults. The effectiveness of the proposed approach is illustrated through simulation.