Summary
A major metropolitan transit authority engaged Hypotenuse to deliver a permanent SHM system across its ageing 42 km underground metro network. Covering 68 tunnel segments spanning 40 years of construction techniques, the platform provides continuous structural assessment, automated anomaly reports, and maintenance prioritisation — enabling a shift from time-based to condition-based maintenance.
Background & Context
The metro network serves 1.2 million daily commuters. Its tunnels were constructed using three different methods — cut-and-cover reinforced concrete, NATM sprayed concrete, and cast-iron segment bored tunnels — each with distinct structural behaviours and deterioration modes. The authority's infrastructure renewal budget requires careful prioritisation across a complex asset portfolio.
Monitoring System Design
The SHM system design was segmented by tunnel type:
• Cast-Iron Segments (28 km): Focus on bolt hole cracking, segment joint opening, and corrosion-driven section loss. Eddy-current sensors and crack gauges at 120 m intervals.
• NATM Sprayed Concrete (9 km): Convergence monitoring using automated laser scanning and vibrating-wire strain gauges embedded in the lining.
• Cut-and-Cover RC (5 km): Surface crack monitors, rebar corrosion probes, and load cells at prop locations.
All data streams feed into a unified Hypotenuse dashboard with GIS-linked asset condition maps.
Sensor Deployment
Anomaly Detection & Pattern Recognition
A spatial-temporal anomaly detector compares each sensor's reading against its 90-day rolling baseline and flags deviations exceeding 2.5 standard deviations. Cross-referencing adjacent sensors distinguishes genuine structural events from sensor faults.
Modal analysis of accelerometer data tracks natural frequency drift — a reliable indicator of stiffness loss in the concrete lining. A 5% frequency drop triggers an engineering inspection request.
Lessons Learned
The complexity of a heterogeneous tunnel portfolio demanded a highly configurable platform architecture. Key lesson: standardising data formats and alert escalation protocols before deployment saves significant integration effort. Also critical: the value of embedding structural engineers in the data interpretation workflow — automated anomaly detection without expert validation creates alert fatigue.
Key Outcomes & Results
Structural Events Detected
14 genuine anomalies captured in Year 1 — all confirmed by inspection
Maintenance Savings
Condition-based prioritisation delivered 28% reduction in routine inspection costs
Alert Accuracy
96% precision on anomaly classification — significantly reducing engineer call-outs
Coverage
42 km of tunnel monitored continuously — first time in the authority's history
Passenger Safety
Zero service disruptions due to undetected structural deterioration
42km
Tunnel network
2,672
Sensor channels
96%
Alert precision
28%
Inspection savings
Deployment Snapshot
Network Length
42 km
Tunnel Segments
68
Sensor Count
2,672 channels
Monitoring Mode
Permanent / real-time