Autonomous Inspection of Flare Stacks Using a Visual Servoing Controlled Unmanned Aerial Vehicle (UAV)

Abstract

Flare stack systems are a crucial component in the operation of oil refineries and petrochemical plants as they safely release the excess gas generated during the plant’s operation. Performance and structure inspection of these systems is an essential and challenging task due to the flare stacks’ harsh operation environment. Flare stacks go through various types of faults both in their mechanical structure and combustion operation, including cracks in the structure, abnormal pilot flame operation, and incomplete combustion of the released gas. The occurrence of such faults could lead to leakage of dangerous emissions to the environment and deadly fires and explosions in the petrochemical plant. The application of autonomous robotic systems in the inspection of such systems is a promising solution for minimizing the involved hazards and costs.

The goal of this research is to design an autonomous low-cost unmanned aerial vehicle (UAV) for inspecting the flare stack. The developed UAV system uses the video stream obtained from an on-board camera for analyzing the observed scene, controlling the UAV’s movement, and obtaining conclusions on the flare stack’s operation. Visual servoing control is employed for autonomously collecting a visual inspection databases for structure and operation inspection. For inspecting the flare stack’s operation, deep learning detection models are implemented for analyzing the flare stack’s scene and obtaining useful conclusions regarding the operation. Finally, the proposed system and techniques were applied for multi-view operation inspection of flare stack systems.

Date of Award	Dec 2022
Original language	American English
Supervisor	Jorge Dias (Supervisor)