Fiber Bragg Grating signal processing using artificial neural networks, an extended measuring range analysis

This paper describes and discusses the application of artificial neural networks (ANN) in fiber Bragg gratings (FBG) signal processing that use narrow band filters as demodulation paradigm to extend the measuring range. The major advantage of the proposed method relies on that the ANN signal processing enables the use of both edges of the narrow band filters without ambiguities, achieving an extended measuring range of the FBG sensors by concatenating n narrow band filters. Experimental results are presented for two different cases of a temperature measuring application in the range between 25degC and 250degC. These situations consider the relative superposition effect of the concatenation method adopted to extend the measuring range. The results are then analyzed according to the proposed solution characteristics and the relative superposition of the narrow band filters.