Unambiguous signal demodulation extending the measuring range of fiber Bragg gratings sensors using artificial neural networks: a temperature case

This paper presents a novel approach that uses Artificial Neural Networks - ANN to extend the measurement range of Fiber Bragg Gratings - FBG interrogators based on fixed narrow band filter demodulation. Interrogators with fixed spectral filters use only one edge of the filter to demodulate the signal. The system proposed uses narrow band FBG's filters, where the entire filter bandwidth is applied to demodulate the signal. Furthermore, the approach has possibility to concatenate n filters, obtaining a measuring range n×bandwithF, where bandwithF is the bandwidth of a demodulating FBG filter. The great advantage of this method relies on the use of ANN to combine these signals, mitigating the ambiguities created in the both edges of each FBG filters, and generating a continuous linear output measuring range. Despite of this proposed demodulation method can be used for strain measurements, yet it is in the temperature sensing that the method offers better contribution. Wide temperature measuring ranges are common in the petrochemical industry, such as distillation columns (0 to 700°C), or in power plants to measure the temperature of transformer windings (-30 to 150°C). This paper presents theoretical results of a temperature measurement system in power transformers application.