The detection of non-Gaussian vibration with improved sensing performance in Φ-OTDR

In structural health monitoring, vibrations often behave as non-Gaussian process, such as gear and engine failure. In this paper, a high-order cumulants algorithm-based phase-sensitive optical time-domain reflectometry is proposed to detect and analyze non-Gaussian vibration. When disturbances with non-Gaussian probability distribution are applied on the sensing fiber, the probability distribution of the Rayleigh backscattering deviates from the standard Gaussian distribution. The 3rd-order cumulant of the Rayleigh backscattering is calculated to extract the non-Gaussian signal from background white noises. Simulations and experiments are carried out. The experimental results indicate that the signal-to-noise ratio is improved by up to similar to 14 dB with 1500 m long sensing fiber. Due to the cubic operation of the algorithm, the spatial resolution is further enhanced to 5 m with pulse width of 100 ns.