Open AccessPrediction of salt contamination in the rotating blade of wind turbine under lightning strike occurrence using fuzzy c‐means and k‐means clustering approaches
Author(s) -
Huang ShengLu,
Chen JiannFuh,
Liang TsorngJuu,
Su MingShou,
Chen Chienyi
Publication year - 2020
Publication title -
iet science, measurement and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.418
H-Index - 49
eISSN - 1751-8830
pISSN - 1751-8822
DOI - 10.1049/iet-smt.2018.5676
Subject(s) - lightning (connector) , turbine , lightning detection , lightning strike , wind power , environmental science , contamination , cluster analysis , marine engineering , ground , meteorology , engineering , power (physics) , electrical engineering , mathematics , statistics , aerospace engineering , thunderstorm , geography , physics , ecology , quantum mechanics , biology
This study proposes an alternative methodology for predicting salt contamination in rotating blade of wind turbine under lightning strike using fuzzy c‐means (FCM) and k‐means (KM) clustering approaches. The salt contamination states of wind turbine blades are classified with four different levels of equivalent salt deposit density (ESDD) classes. The lightning strike experiments are set up for simulating the condition when the blades are struck by lightning with four rotational speeds under various ESDD classes. Then, the absolute peak value of the measured current signals in grounding line using the high‐frequency current transformer and the average power are used to represent the input vectors of FCM and KM to predict the class of the salt contamination. The experimental results validated that the proposed approach can effectively classify the measured current signal and accurately predict the ESDD class on lightning strike occurrence.