Conventional optical fiber current measurements improved by a high accuracy artificial neural network algorithm

Antonio C. Zimmermann; Marcio Besen; Leonardo S. Encinas; Cristiano M. B. Cordeiro

doi:10.1117/12.975616

17 October 2012 Conventional optical fiber current measurements improved by a high accuracy artificial neural network algorithm

Antonio C. Zimmermann, Marcio Besen, Leonardo S. Encinas, Cristiano M. B. Cordeiro

Author Affiliations +

Proceedings Volume 8421, OFS2012 22nd International Conference on Optical Fiber Sensors; 84213G (2012) https://doi.org/10.1117/12.975616
Event: OFS2012 22nd International Conference on Optical Fiber Sensor, 2012, Beijing, China

Abstract

This paper relies on an experiment using a conventional fiber optical current measurement system with new concept for signal processing using Artificial Neural Networks. To achieve the high accuracy results, a class 0.1% current standard was used as reference for the ANN processing. Also a large data collection was conducted to assure the high variability of the measurement process behavior, including changes in temperature and other non-linear effects. The results show 0.2% maximum error for the developed system, demonstrating the robustness and high accuracy of the proposed method, being capable of mitigate some drawbacks of FOCS system, like non-idealities compensation.

Citation Download Citation

Antonio C. Zimmermann, Marcio Besen, Leonardo S. Encinas, and Cristiano M. B. Cordeiro "Conventional optical fiber current measurements improved by a high accuracy artificial neural network algorithm", Proc. SPIE 8421, OFS2012 22nd International Conference on Optical Fiber Sensors, 84213G (17 October 2012); https://doi.org/10.1117/12.975616

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