Physical Model-Assisted Hybrid Neural Network Enabling High Spatial Resolution Distributed High-Temperature Sensing With Single-Crystal Fiber

Raman distributed high-temperature sensing (DHTS) offers unique advantages, particularly in addressing crosstalk issues of the traditional point sensors, as well as the challenges associated with the multipoint deployment of sensors and complex wiring in temperature field measurements. However, due to the limitations of the system hardware, achieving ultrahigh spatial resolution (SR) in distributed high-temperature sensing systems remains challenging, thereby hindering the acquisition of dense temperature data required for comprehensive temperature field measurements. To break through these intrinsic hardware limitations and challenges, we proposed a hybrid neural network model combined with the convolution neural network (CNN) and bidirectional long short-term memory (Bi-LSTM) for the DHTS system with the specialty yttrium aluminum garnet (YAG) single-crystal fiber (SCF). Based on experimental data acquired from room temperature to high temperature of $1400~^{\circ } $ C, the SR was shown to improve significantly, and further validation through point heat source experiments demonstrated a maximum enhancement in SR of 4.43 cm. The hybrid model of the CNN and Bi-LSTM effectively achieves both denoising and SR enhancement. In addition, the optimized hybrid model can reconstruct high-fidelity signal traces that align closely with the experimental system. Furthermore, the system is capable of processing and reconstructing frame-by-frame signals, enabling high-speed temperature response capabilities.