TY - GEN
T1 - Noise monitoring of aircrafts taking off based on neural model
AU - Fernandez, Luis Pastor Sanchez
AU - Ruiz, Arturo Rojo
AU - Pogrebnyak, Oleksiy B.
PY - 2009
Y1 - 2009
N2 - This work presents a computational model that allows the monitoring of aircraft generated noise. It makes spectral analysis and calculation of statistical indicators, as well as the aircrafts identification based on generated noise. This model also helps to foresee potential effects to health caused by this kind of noise during the aircraft takeoff, which is when the greatest impact are generated due to the sonorous levels that are reached. This model is implemented by means of software in a laptop, a data acquisition card and a calibrated sensor of acoustic pressure. The method can be included in a permanent monitoring system. The data acquisition is made at 25 KHz at 24 bits. The identification of the aircraft noise is done through two parallel neural networks combined with a weighted addition. In order to generate the inputs to the neural networks, parameters that were obtained from the auto-regressive model and the 1/12 octave analysis are used. This system has 13 categories of aircrafts and it has an identification level of 80% in real environments.
AB - This work presents a computational model that allows the monitoring of aircraft generated noise. It makes spectral analysis and calculation of statistical indicators, as well as the aircrafts identification based on generated noise. This model also helps to foresee potential effects to health caused by this kind of noise during the aircraft takeoff, which is when the greatest impact are generated due to the sonorous levels that are reached. This model is implemented by means of software in a laptop, a data acquisition card and a calibrated sensor of acoustic pressure. The method can be included in a permanent monitoring system. The data acquisition is made at 25 KHz at 24 bits. The identification of the aircraft noise is done through two parallel neural networks combined with a weighted addition. In order to generate the inputs to the neural networks, parameters that were obtained from the auto-regressive model and the 1/12 octave analysis are used. This system has 13 categories of aircrafts and it has an identification level of 80% in real environments.
UR - http://www.scopus.com/inward/record.url?scp=77949901655&partnerID=8YFLogxK
U2 - 10.1109/ETFA.2009.5347034
DO - 10.1109/ETFA.2009.5347034
M3 - Contribución a la conferencia
AN - SCOPUS:77949901655
SN - 9781424427284
T3 - ETFA 2009 - 2009 IEEE Conference on Emerging Technologies and Factory Automation
BT - ETFA 2009 - 2009 IEEE Conference on Emerging Technologies and Factory Automation
T2 - 2009 IEEE Conference on Emerging Technologies and Factory Automation, ETFA 2009
Y2 - 22 September 2009 through 26 September 2009
ER -