Atmospheric corrosion is the biggest asset integrity threat to offshore Oil and Gas (O&G) platforms in the Gulf of Mexico (GoM). Manual inspection of an offshore platform's topside equipment is costly, time-consuming, and labor-intensive. Moreover, manual inspection findings are subjective and provide incomplete asset coverage, leading to increased risk of unplanned shutdowns due to missed repairs. Computer vision and machine learning algorithms can be used to detect and classify corrosion, allowing for the objective and comprehensive management of corrosion across a facility. Detected corrosion is associated with equipment and reported, enabling high-risk equipment (i.e., high likelihood and/or consequence of failure) to be targeted for remediation, significantly reducing the risk of unplanned downtime. This paper covers the first-in-industry application of an AI-based system to improve corrosion management and inspection processes. A case study is presented, where the AI-based corrosion management system is deployed across a large offshore O&G platform in the GoM. The impacts of this new technology for corrosion management are demonstrated, in practice. Machine learning and computer vision algorithms are leveraged to greatly improve inspection, maintenance, and management processes, reducing the operating costs and risks associated with offshore O&G platforms.
External corrosion on offshore O&G platforms is one of the biggest threats to asset integrity and its management is a large operational expense. Many operators now implement risk-based assessment (RBA) programs where all equipment is assessed periodically with the aim to reduce operational costs while maintaining integrity. Regulatory codes for offshore platforms in the GoM require a visual inspection of all pressure equipment and piping every five-years. In practice, this can equate to approximately 20% of equipment being inspected per year on a large-sized offshore platform (i.e., a topside weight of around 10,000 tons), with a rolling five-year inspection plan to balance the inspection workload evenly through time. As a result, in a five-year inspection cycle, a platform operator will not have visibility to the condition of the equipment for other times in the inspection cycle (i.e., a single equipment is only inspected once in the five-year cycle). Due to the complexity of equipment and infrastructure lay-out, equipment at-heights, spanning over-water, and difficult to inspect areas, performing equipment inspections can be costly, time-consuming, and yield varying quality of results. Variance in inspections can arise from the inspector's subjectivity, the environmental changes, and the present working conditions around the platform. Inspector's must sometimes access equipment that is difficult to reach or see and making close assessments difficult.
