High Accuracy Pressure Sensing With Sagnac Interferometry Based On Deep Learning Approach

In this paper, we proposed a pressure sensor using a Sagnac interferometer based on a side-hole fiber (SHF) with the assistance of deep learning. A convolutional neural network (CNN) was built to identify the spectra of different pressures since the traditional tracing method will face spectral overlap problems when the shift of the spectrum exceeds the free spectral range (FSR). The spectra of pressures ranging from 0 Mpa to 5 MPa with a step of 0.1 MPa will be normalized firstly and then sent to the CNN model for training. The precited result shows that the coefficient of determination
$R^{2}$
is 99.99987% with the root mean square error (RMSE) equal to
$1.6537\times 10^{-3}$
MPa. Additionally, a similar structure was constructed to demonstrate the universality of the proposed CNN model. The model can also get a good performance, although the receiving device has a low resolution, showing its great potential for developing a low-cost sensing system.