To improve the capability of Fiber Bragg Grating (FBG) sensors in mine safety monitoring systems to address the cross-sensitivity problem of temperature and strain, a high-precision cross-sensitivity decoupling monitoring model was constructed by integrating a dual-grating temperature compensation method and a Gaussian process regression modeling method improved by the particle swarm optimization algorithm. The experimental results indicate that the proposed method outperforms traditional methods in both wavelength shift data fitting and prediction accuracy. The monitoring system achieves high-precision measurement of temperature and strain data in the mine environment, with the minimum monitoring error being only 0.04 mm and the fitting degree R² reaches 0.912. The system realizes high-precision dual-parameter monitoring in the mine environment, where the monitoring accuracy of temperature and strain reaches 0.961, and the data transmission rate increases by 36% compared to photosensitive and electronic sensors. This demonstrates that FBG sensors possess certain advantages in the dimensions of acquisition accuracy and real-time performance. The research results provide a reusable theoretical framework for innovation in mine safety monitoring and lay a methodological foundation for the evolution of intelligent monitoring systems.

Fiber Bragg Grating  /  Temperature  /  Strain  /  Particle swarm optimization  /  Mine safety monitoring