High-precision demodulation method for the cobweb FBG sensor network

To improve the demodulation accuracy and speed of the cobweb fiber Bragg grating (FBG) sensor network, a demodulation algorithm based on a one-dimensional (1D) dilated convolutional neural network (CNN) combined with improved wavelet adaptive threshold de-noising is proposed. The improved wavelet adaptive threshold de-noising algorithm is used to de-noise several highly overlapping sensing signals for accurately measuring optical fiber sensing signals. Using a well-trained 1D dilated CNN model achieves extremely low signal demodulation errors, even with highly overlapping signals. Experiments show that the demodulation scheme improves the detection accuracy of the cobweb FBG sensor network and shortens detection time. Determination of the peak wavelengths of the four highly overlapping sensing signals achieves a root-mean-square error of better than 0.10 pm and an average demodulation time of 15.2 ms.