Smart sensors for the petroleum sector based on long period gratings supervised by artificial neural networks

Gustavo R. C. Possetti; Francelli K. Coradin; Lílian C. Côcco; Carlos I. Yamamoto; Lucia V. R. de Arruda; Rosane Falate; Marcia Muller; José L. Fabris

doi:10.1117/12.786843

16 May 2008 Smart sensors for the petroleum sector based on long period gratings supervised by artificial neural networks

Gustavo R. C. Possetti, Francelli K. Coradin, Lílian C. Côcco, Carlos I. Yamamoto, Lucia V. R. de Arruda, Rosane Falate, Marcia Muller, José L. Fabris

Author Affiliations +

Proceedings Volume 7004, 19th International Conference on Optical Fibre Sensors; 70045W (2008) https://doi.org/10.1117/12.786843
Event: 19th International Conference on Optical Fibre Sensors, 2008, Perth, WA, Australia

Abstract

This work shows the use of long period gratings in the petroleum sector, in two specific applications. The proposed sensors are employed both to identify substances in a simulated flow inside a pipeline, and to assess the gasoline conformity commercialized in gas stations. The gratings responses for each specific case were employed to train and to validate two different topologies of artificial neural networks: perceptron multilayer and radial base function. The obtained results show that fiber optic sensors supervised by artificial neural networks can constitute systems for smart measurement with high applicability in the petrochemical field.

Citation Download Citation

Gustavo R. C. Possetti, Francelli K. Coradin, Lílian C. Côcco, Carlos I. Yamamoto, Lucia V. R. de Arruda, Rosane Falate, Marcia Muller, and José L. Fabris "Smart sensors for the petroleum sector based on long period gratings supervised by artificial neural networks", Proc. SPIE 7004, 19th International Conference on Optical Fibre Sensors, 70045W (16 May 2008); https://doi.org/10.1117/12.786843

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available