Automated detection of tunnel excavation (Technion)
Current approaches for detecting tunnels, activities in tunnels or tunnel excavation include electromagnetic induction sensors or acoustic ones to detect mechanical waves, and radar-type waves propagating between two boreholes. All of the approaches mentioned above are limited to large tunnels (>1m in diameter), or require constant personnel to operate.Underground excavation in soil cause substantial deformations and strains in the medium. A sufficient sensitive device can detect these strains and hence the excavation can be monitored. The proposed detection system is based on wavelet decomposition of the BOTDR signal, followed by a neural network that is trained to recognize the tunnel signature in the wavelet coefficients. Simulations and field test results showed extremely high detection rate of tunnels (0.5m in diameter), while remaining mostly insensitive to noise and above-ground disturbances. Figure 1 (see attached PDF file) shows a possible configuration for the suggested smart underground fence, consisting of a horizontal fiber buried at shallow depth.
• Ability to monitor tens of kilometers along borders with cheap conventional optic fibers.
• Automated system can distinguish tunneling activities from measurement noise and above-ground disturbances.
• Detection of small tunnels (0.5m in diameter) up to significant depth.
Security – detection of smuggling tunnels.
CIV-1108
以色列
