See how BridgeAID’s bridge monitoring system works

A walkthrough of AI-assisted Bridge Weigh-in-Motion and a real-time Digital Twin, built and validated on the Monostori Bridge (Komarom, Hungary/Slovakia).

If you have questions about the technology, deployment options, or a specific bridge pilot, we are happy to discuss them, contact us:

Class A

COST 323 accuracy for gross weight, axle group, and heaviest axle, verified against 100 statically weighed reference vehicles

Komarom

first deployment: Monostori Bridge, Hungary/Slovakia border

24/7

monitoring. Sensors don’t take vacations.

Built and calibrated on a real bridge

Sensors installed directly on the Monostori Bridge structure, validated against static reference weighing, and calibrated on site.

Truck axle on a static reference scale, used to validate BridgeAID's Bridge Weigh-in-Motion accuracy

Static reference weighing, used to validate BridgeAID’s B-WIM measurements.

BridgeAID engineers calibrating the sensor system on site, reviewing live signal data on a monitor mounted under the bridge

On-site calibration, reviewing live sensor signal data under the bridge deck.

Sensor cabling installed along the underside of the Monostori Bridge structure

Sensors and cabling installed along the structure, not on the road surface.

Service level 1

AI-assisted Bridge Weigh-in-Motion

Real-time vehicle load and traffic data measured directly from the bridge structure. No lane closures, no roadside weigh stations. Class A accuracy under COST 323, verified against 100 statically weighed reference vehicles, improving over time via AI.

Service level 2

Real-Time Digital Twin

A continuously updated virtual replica of the bridge, designed to turn sensor data into renovation and maintenance priorities, moving from once-a-decade inspection toward minute-by-minute insight.

Academic background

Our founders’ previous academic publications on the topic.

Szinyéri B., Kővári B., Völgyi I., Kollár D., Joó, A. L.: Bridge influence line identification using convex programming from Bridge Weigh-in-Motion strain signals, ENGINEERING STRUCTURES 365: 123158 (2026), DOI: 10.1016/j.engstruct.2026.123158
Szinyéri B., Kővári B.: Handling data loss caused by strain gauge failure in Bridge Weigh-in-Motion systems using multivariate time-series linear regression, NEURAL COMPUTING & APPLICATIONS 38: 6 Paper: 161, 16 p. (2026), DOI: 10.1007/s00521-026-11895-6
Szinyéri B., Kővári B., Völgyi I., Kollár D., Joó, A. L.: A strain gauge-based Bridge Weigh-In-Motion system using deep learning, ENGINEERING STRUCTURES 277: 115472 (2023), DOI: 10.1016/j.engstruct.2022.115472
Szinyéri B., Kővári B., Völgyi I., Kollár D., Joó A. L.: Mélytanulás alapú tengelysúlybecslés nyúlásmérő bélyegek adatai alapján, MAGÉSZ ACÉLSZERKEZETEK 19: különszám pp. 58-65., 8 p. (2022)

Ready to see what this looks like for your network?

Select a bridge, a network, or a challenge you are already working on, and we will show you what real-time data would actually reveal.