Hsu, R. C.R. C.HsuCHAO-NAN WANG2023-06-072023-06-072020-01-0110234535https://scholars.lib.ntu.edu.tw/handle/123456789/631953Due to the climate change in recent years, the development of renewable energy projects has widely been promoted worldwide to reduce greenhouse gas. Despite of the contaminated environment, people tended to build the variety of renewable power systems produced by wind, sunlight, rain and other approaches which could be easily obtained from nature. The wind turbine is one of the most popular power supplies while this generally causes defects on the surface of blades based on strong wind or harsh weather besides the ocean. Thus, in order to avoid the expensive maintenance fee and prolong wind turbine’s life, an aim of this research was to build a detected system to examine whether the condition on blade surface was failure or not. Recording the sound of wind turbines on land is the main data sources since offshore wind turbine is difficult to obtain. There are 935 data including different wind speed from 4m/s to 10m/s. In this paper, we have proposed two approaches, Mel-Frequency Cepstral Coefficient (MFCC), to extract feature from the signal noise of recorded sound of wind turbine. After obtaining the coefficient from MFCC, using a classification called Support Vector Machine (SVM), to train a model which could normally present the accuracy of the result with normal or failure rotor blades. The experimental investigation indicated that MFCC features could be used for identifying the wind turbine sounds under the various wind speed, and combining the method of SVM generated the high accuracy around 97.3 percentage which could be detected immediately. The recognizing system may be useful to improve the lifetime of wind turbine as well as keeping the cost down from maintenance fee.Mel-Frequency Cepstral Coefficient | Support Vector Machine | Wind Turbinejournal article2-s2.0-85137622840https://api.elsevier.com/content/abstract/scopus_id/85137622840