Germany’s Fraunhofer Institute is piloting a road-monitoring fabric woven from flax fibers and conductive threads that, paired with machine-learning software, detects subsurface stress and cracking before damage appears at the surface. The system continuously collects data from beneath asphalt and relays it to an AI platform that forecasts deterioration and helps agencies prioritize maintenance, potentially cutting costs, extending pavement life and reducing traffic delays. Unlike traditional core sampling and drill tests, the approach is non-destructive and designed for continuous monitoring, with results displayed on a web dashboard for planners. The pilot, dubbed SenAD2, is being tested in an industrial zone and underscores how materials science and AI are converging to modernize infrastructure management. If adopted broadly, the technology could shift public-works spending from reactive patchwork to data-driven preventive maintenance.
Related articles:
Structural health monitoring
U.S. DOT Intelligent Transportation Systems Joint Program Office
Nondestructive testing
TRID: Transport Research International Documentation
