DocumentCode :
614847
Title :
Vibration characterization using Gaussian laser beam
Author :
Abbasi, Naveed A. ; Landolsi, Taha ; Dhaouadi, Rached
Author_Institution :
Grad. Program of Mechatron. Eng., American Univ. of Sharjah, Sharjah, United Arab Emirates
fYear :
2013
fDate :
28-30 April 2013
Firstpage :
1
Lastpage :
7
Abstract :
The objective of this research is to present a neural network based optical vibration sensor using a quad-cell photo-detector array. The proposed system uses a He-Ne laser source whose Gaussian beam impinges on the photo-detector array. The optical power distribution from the photo-detectors is fed to vibration monitoring system which maps the power distribution to the x-y position of the laser beam center. The vibration monitoring system uses artificial neural networks for function approximation to yield the correct mapping and estimate the x-y positions of the laser beam center which are then used for vibration characterization. An experimental setup of the system is developed and then trained using neural networks. The results obtained show the effectiveness of neural networks to estimate the vibration frequency and magnitude of a vibrating system.
Keywords :
function approximation; mechanical engineering computing; neural nets; optical sensors; photodetectors; vibration measurement; Gaussian laser beam; He-Ne laser source; artificial neural network; function approximation; optical power distribution; optical vibration sensor; quad-cell photo-detector array; vibration characterization; vibration monitoring system; Arrays; Biological neural networks; Frequency estimation; Laser beams; Monitoring; Photodiodes; Vibrations; Vibration monitoring; neural network; optical sensor; quad-cell photo detector array;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Modeling, Simulation and Applied Optimization (ICMSAO), 2013 5th International Conference on
Conference_Location :
Hammamet
Print_ISBN :
978-1-4673-5812-5
Type :
conf
DOI :
10.1109/ICMSAO.2013.6552672
Filename :
6552672
Link To Document :
بازگشت