Validation of artificial neural networks to model the acoustic behaviour of induction motors

Research areas:

• Applications - Engine noise prediction

Year:

2020

Type of Publication:

Article

Keywords:

Artificial neural networks, Sigmoid units, Pulse width modulation, Sound quality, Induction motor

Authors:

• Jiménez-Romero, Francisco Javier
• Guijo-Rubio, David
• Lara-Raya, Francisco Ramón
• Ruiz-González, Antonio
• Hervás-Martínez, César

Journal:

Applied Acoustics

Volume:

166

Pages:

107332

Month:

March

ISSN:

0003-682X

BibTex:

@article{ApAcoustics2020, author = "Francisco Javier Jim{\'e}nez-Romero and David Guijo-Rubio and Francisco Ram{\'o}n Lara-Raya and Antonio Ruiz-Gonz{\'a}lez and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "In the last decade, the sound quality of electric induction mjavascript:moveDown({\&}#039;liauthorsfield5{\&}#039;)otors is a hot topic in the research field. Specially, due to its high number of applications, the population is exposed to physical and psychological discomfort caused by the noise emission. Therefore, it is necessary to minimise its psychological impact on the population. In this way, the main goal of this work is to evaluate the use of multitask artificial neural networks as a modelling technique for simultaneously predicting psychoacoustic parameters of induction motors. Several inputs are used, such as, the electrical magnitudes of the motor power signal and the number of poles, instead of separating the noise of the electric motor from the environmental noise. Two different kind of artificial neural networks are proposed to evaluate the acoustic quality of induction motors, by using the equivalent sound pressure, the loudness, the roughness and the sharpness as outputs. Concretely, two different topologies have been considered: simple models and more complex models. The former are more interpretable, while the later lead to higher accuracy at the cost of hiding the cause-effect relationship. Focusing on the simple interpretable models, product unit neural networks achieved the best results: 38.77 for MSE and 13.11 for SEP. The main benefit of this product unit model is its simplicity, since only 10 inputs variables are used, outlining the effective transfer mechanism of multitask artificial neural networks to extract common features of multiple tasks. Finally, a deep analysis of the acoustic quality of induction motors in done using the best product unit neural networks.", awards = "JCR(2020): 2.639 Position: 11/32 (Q2) Category: ACOUSTICS", comments = "JCR(2020): 2.639 Position: 11/32 (Q2) Category: ACOUSTICS", doi = "10.1016/j.apacoust.2020.107332", issn = "0003-682X", journal = "Applied Acoustics", keywords = "Artificial neural networks, Sigmoid units, Pulse width modulation, Sound quality, Induction motor", month = "March", note = "JCR(2020): 2.639 Position: 11/32 (Q2) Category: ACOUSTICS", pages = "107332", title = "{V}alidation of artificial neural networks to model the acoustic behaviour of induction motors", url = "doi.org/10.1016/j.apacoust.2020.107332", volume = "166", year = "2020", }

Note:

JCR(2020): 2.639 Position: 11/32 (Q2) Category: ACOUSTICS

Abstract:

In the last decade, the sound quality of electric induction mjavascript:moveDown('liauthorsfield5')otors is a hot topic in the research field. Specially, due to its high number of applications, the population is exposed to physical and psychological discomfort caused by the noise emission. Therefore, it is necessary to minimise its psychological impact on the population. In this way, the main goal of this work is to evaluate the use of multitask artificial neural networks as a modelling technique for simultaneously predicting psychoacoustic parameters of induction motors. Several inputs are used, such as, the electrical magnitudes of the motor power signal and the number of poles, instead of separating the noise of the electric motor from the environmental noise. Two different kind of artificial neural networks are proposed to evaluate the acoustic quality of induction motors, by using the equivalent sound pressure, the loudness, the roughness and the sharpness as outputs. Concretely, two different topologies have been considered: simple models and more complex models. The former are more interpretable, while the later lead to higher accuracy at the cost of hiding the cause-effect relationship. Focusing on the simple interpretable models, product unit neural networks achieved the best results: 38.77 for MSE and 13.11 for SEP. The main benefit of this product unit model is its simplicity, since only 10 inputs variables are used, outlining the effective transfer mechanism of multitask artificial neural networks to extract common features of multiple tasks. Finally, a deep analysis of the acoustic quality of induction motors in done using the best product unit neural networks.

Comments:

JCR(2020): 2.639 Position: 11/32 (Q2) Category: ACOUSTICS