MODELING OF THE TONAL NOISE CHARACTERISTICS IN A FOIL FLOW BY USING MACHINE LEARNING
S. S. Abdurakipov1,2, M. P. Tokarev1,2, K. S. Pervunin1,2, V. M. Dulin1,2
1Kutateladze Institute of Thermophysics SB RAS, 630090, Novosibirsk, prosp. Akademika Lavrent'eva, 1
2Novosibirsk State University, 630090, Novosibirsk, ul. Pirogova, 2
Keywords: машинное обучение, обтекание гидропрофиля, тональный шум, machine learning, foil flow, tonal noise
Abstract
A machine learning approach for prediction the characteristics of tonal noise formed in a foil flow is tested. Experimental data are used to construct and analyze the mathematical models of pressure amplitude regression and models of classification of regimes of high-level tonal noise coming from the dimensionless parameters of the flow. Different families of algorithms are considered: from linear models to artificial neural networks. It is shown that a gradient boosting model with a determination coefficient 95 % is the most accurate for describing and predicting the spectral curves of acoustic pressure on the entire interval of values of amplitudes and characteristic frequencies.
|
