Autonomous robotic pipeline inspection technologies

¹ Renewable Energy, University of Hull, United Kingdom
² Computing University of Sunderland, United Kingdom.

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it. , This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Pipeline infrastructure carries oil, gas, water, and industrial fluids across vast distances, and require careful maintenance. Visual inspections, scheduled digs, inline gauging tools, etc. have been industry standards for years, but struggle with expensive operations, scheduled downtime, and the inability to provide continuous monitoring. Autonomous robots have the potential to improve pipeline inspection workflows. Some robotic inspection platforms are equipped with advanced locomotion technologies like wheels, tracks, as well as embedded sensor payloads to detect corrosion, cracks, leakage, etc. Optical inspections can be augmented with ultrasonic testing, magnetic flux leakage, thermal imaging, acoustic sensors to provide comprehensive pipeline assessments. AI and machine learning allow for increased automation of anomaly detection and failure prediction. Beyond sensing, data storage and transfer allows for processed information to be used by operational teams and management. Edge computing allows for time-critical processes to be run on-board, while cloud computing allows for data storage and big-data analysis. SCADA integration can connect robotic inspections to enterprise-level risk analysis. Current limitations of pipeline inspection robots include limited energy storage, complex data analysis, deployment in difficult terrains/depths, and a lack of skilled pipeline operators. Some areas of development include energy harvesting robots, swarm robotics for distributed inspection, and multi-modal sensing/data fusion.