Magnetic Characterization of MR Fluid by Means of Neural Networks DOI Open Access
Paweł Kowol, Grazia Lo Sciuto, Rafał Brociek

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(9), P. 1723 - 1723

Published: April 29, 2024

Magnetorheological and electrorheological fluids manifest a change in rheological behavior when subjected to magnetic or electric field, respectively, such that they require electrical characterization. In this paper, simple accurate mathematical model based on small number of parameters provides the relative permeability magnetorheological as function applied field. Furthermore, for testing characterization fluids, new metering equipment setup is implemented. Starting with achieved experimental data, relation μr=f(B) represented by means radial basis neural network, neurons having Gaussian activation function; post-training pruning procedures, trained network using proposed data. Therefore, obtained good agreement an approximate error 8%.

Language: Английский

Magnetic Characterization of MR Fluid by Means of Neural Networks DOI Open Access
Paweł Kowol, Grazia Lo Sciuto, Rafał Brociek

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(9), P. 1723 - 1723

Published: April 29, 2024

Magnetorheological and electrorheological fluids manifest a change in rheological behavior when subjected to magnetic or electric field, respectively, such that they require electrical characterization. In this paper, simple accurate mathematical model based on small number of parameters provides the relative permeability magnetorheological as function applied field. Furthermore, for testing characterization fluids, new metering equipment setup is implemented. Starting with achieved experimental data, relation μr=f(B) represented by means radial basis neural network, neurons having Gaussian activation function; post-training pruning procedures, trained network using proposed data. Therefore, obtained good agreement an approximate error 8%.

Language: Английский

Citations

1