An EGLOF method for tidal stream turbine blade impact fault detection
Year: 2024
Type: conference-paper
Abstract: The fault detection of blade impact fault using the stator current signals can improve the stability of the Tidal Stream Turbine (TST) operation. However, the current signals are disturbed by waves and turbulence, which leads to a high false alarm rate for fault detection. This paper proposes an envelope geometric local outlier factor method (EGLOF) to solve this problem, which is divided into three steps: Firstly, the signal envelope samples are extracted by using the Teager-Kaiser energy operator (TKEO). Then, the geometric features of the envelope samples are calculated by the sliding window technique. Finally, the local outlier factor (LOF) model is introduced to calculate EGLOF values to detect the impact fault. The experimental results show that the proposed method has a lower false alarm rate compared with the traditional methods.
Authors: Zhen Wu, Tianzhen Wang
Institution: Shanghai Maritime University
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4401651924