aalto1 untyped-item.component.html

Drone-based bridge health monitoring and inspection

Loading...
Thumbnail Image

URL

Journal Title

Journal ISSN

Volume Title

Insinööritieteiden korkeakoulu | Bachelor's thesis

Department

Mcode

ENG3082

Language

en

Pages

26 + 6

Series

Abstract

Unmanned aerial vehicles (UAVs) are displacing bucket trucks and rope access in bridge inspections by delivering safer, data-rich, repeatable workflows. This thesis is a state-of-the-art review that benchmarks multirotor, fixed-wing, and hybrid VTOL airframes, finding multirotors optimal for close imaging and hybrids for kilometer-scale corridors. It reviews payloads, RGB, infrared thermography, LiDAR, ultrasonic echo, and ground-penetrating radar, and shows photogrammetry now yields sub-millimeter orthomosaics, while LiDAR point clouds provide centimetric geometry for deformation analysis. Deep-learning detectors (YOLO variants) reach 98 % crack-detection precision; lightweight segmentation networks enable onboard, real-time feedback. Field trials halve site time, eliminate lane closures, and lower inspector risk, yet 20-30 min battery endurance and GNSS drop-outs beneath decks still constrain operations. The study concludes that fusing multi-sensor UAV data with Bridge Information Models and Bridge Management Systems yields objective condition ratings; wider adoption hinges on open data schemas, longer-endurance airframes, and resilient vision-based navigation.

Description

Supervisor

St-Pierre, Luc

Thesis advisor

Lin, Weiwei

Other note

Citation

Endorsement

Review

Supplemented By

Referenced By