Open AccessMachine learning application for magnetohydrodynamic pump research
Author(s) -
Nikolay V. Tarchutkin,
Ivan Smolyanov
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/950/1/012019
Subject(s) - magnetohydrodynamic drive , multiphysics , computer science , basis (linear algebra) , machine learning , sample (material) , experimental data , artificial intelligence , finite element method , magnetohydrodynamics , mathematics , physics , thermodynamics , statistics , plasma , geometry , quantum mechanics
The article is devoted to finding out best machine learning model used for the analysis of magnetohydrodynamic pump. The machine learning model was created on the basis of data obtained as a result of numerical simulation of the unit using COMSOL Multiphysics. The paper compares errors of output data collected by using various machine learning methods for out-of-sample data.