Open AccessWavelet decomposition algorithm for machine learning model in wind turbines
Author(s) -
Marina M. Pukhova,
Evgeniy Lopatin,
Natalia Sokolinskaya,
S. I. Tarakanov
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1515/4/042017
Subject(s) - wind power , decomposition , vibration , energy (signal processing) , wavelet , computer science , wavelet transform , renewable energy , power (physics) , wavelet packet decomposition , algorithm , engineering , artificial intelligence , acoustics , mathematics , electrical engineering , ecology , statistics , physics , quantum mechanics , biology
The paper considers the wavelet decomposition for machine learning model to solve the problem of analyzing the shape of vibration signals in wind energy turbines. The questions of training and optimization of the parameters of the classmate method are highlighted. The principle of constructing a training sample is described. The algorithm for the instance recognition of circuit elements by vibration signals removed from wind turbines. Thus, the method of recognition of equipment elements based on sparse wavelet decomposition of vibration signals can be used in practical renewable energy. The research results will stimulate of the development of generating facilities based on wind energy with an installed capacity of up to 15 kW will contribute to the stimulation of the development of wind power with a vertical axis in the urban environment.