Temperature Compensation Strategy of Fiber Bragg Grating Sensor Based on Improved Neural Network Optimization Algorithm

Fiber Bragg grating (FBG) sensors are widely used in the field of transmission line ice monitoring, but the cross-sensitivity of temperature and stress seriously affects their measurement accuracy. To address this problem, this paper proposed a temperature compensation strategy based on the improved back propagation (BP) neural network algorithm. A whale optimization algorithm is used to optimize the BP neural network to improve its performance for eliminating the influence of cross-sensitivity of temperature and stress on FBG sensors. To address the issue of a small sample size, a K-fold cross validation method is adopted to improve the reliability of network prediction. The simulation verifies that the proposed strategy could effectively achieve higher accuracy in monitoring the icing thickness of transmission lines.