17 October 2012 Conventional optical fiber current measurements improved by a high accuracy artificial neural network algorithm
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.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Antonio C. Zimmermann, Antonio C. Zimmermann, Marcio Besen, Marcio Besen, Leonardo S. Encinas, Leonardo S. Encinas, Cristiano M. B. Cordeiro, 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); doi: 10.1117/12.975616; https://doi.org/10.1117/12.975616
PROCEEDINGS
4 PAGES


SHARE
Back to Top