Modeling the Voltage Produced by Ultrasound in Seawater by Stochastic and Artificial Intelligence Methods

Alina Bărbulescu; Cristian Ștefan Dumitriu

doi:10.3390/s22031089

Modeling the Voltage Produced by Ultrasound in Seawater by Stochastic and Artificial Intelligence Methods

Sensors (Basel). 2022 Jan 30;22(3):1089. doi: 10.3390/s22031089.

Authors

Alina Bărbulescu¹, Cristian Ștefan Dumitriu²

Affiliations

¹ Department of Civil Engineering, Transylvania University of Brașov, 5 Turnului Str., 900152 Brasov, Romania.
² Department of Installations for Constructions, Transylvania University of Brașov, 5 Turnului Str., 900152 Brasov, Romania.

Abstract

Experiments have proved that an electrical signal appears in the ultrasonic cavitation field; its properties are influenced by the ultrasound frequency, the liquid type, and liquid characteristics such as density, viscosity, and surface tension. Still, the features of the signals are not entirely known. Therefore, we present the results on modeling the voltage collected in seawater, in ultrasound cavitation produced by a 20 kHz frequency generator, working at 80 W. Comparisons of the Box-Jenkins approaches, with artificial intelligence methods (GRNN) and hybrid (Wavelet-ARIMA and Wavelet-ANN) are provided, using different goodness of fit indicators. It is shown that the last approach gave the best model.

Keywords: Generalized Regression Neural Network (GRNN); Wavelet-ARIMA; autoregressive integrated moving average (ARIMA); cavitation; voltage; wavelet-artificial neural network (ANN).

MeSH terms

Artificial Intelligence*
Incidence
Seawater*
Ultrasonography