Automated External Corrosion Detection for Process Equipment With Ai

Abstract Atmospheric corrosion poses the most significant threat to the integrity of offshore Oil and Gas (O&G) platforms in the Gulf of Mexico (GoM). Traditional manual inspection of topside equipment on these platforms is not only expensive, time-consuming, and labor-intensive but also subjective and incomplete, leading to an increased risk of unplanned shutdowns due to overlooked repairs. To address these challenges, computer vision and machine learning algorithms can be employed to detect and categorize corrosion accurately. This approach enables an objective and comprehensive management of corrosion throughout the facility. By identifying and reporting areas with detected corrosion, the system can prioritize high-risk equipment, which is prone to failure and can have severe consequences, for prompt remediation, thereby significantly reducing the likelihood of unplanned downtime. This paper introduces a pioneering AI-based system that revolutionizes corrosion management and inspection processes, specifically designed for offshore O&G platforms. The authors present a case study illustrating the application of this AI-based corrosion management system on a large GoM offshore platform. The practical impacts of this technology on corrosion management are demonstrated, showcasing how machine learning and computer vision algorithms vastly enhance inspection, maintenance, and overall management processes, ultimately leading to reduced operating costs and risks associated with offshore O&G platforms.