Artificial-Intelligence and Machine-Learning Technique for Corrosion Mapping

Abstract

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 202801, “Automated Corrosion Mapping AI and Machine Learning,” by Marc Majors and Travis Harrington, Occidental, and Eric Ferguson, Abyss Solutions, et al. The paper has not been peer reviewed. The complete paper discusses risk reduction and increased fabric-maintenance (FM) efficiency using artificial-intelligence (AI) and machine-learning (ML) algorithms to analyze full-facility imagery for atmospheric corrosion detection and classification. With this tool, a comprehensive and objective analysis of a facility’s health is achievable in a matter of weeks from the time of data collection. This application of AI and ML is a novel approach aimed at gaining a comprehensive understanding of facility-coating integrity and external corrosion threats. Introduction Atmospheric corrosion is the most-significant asset-integrity threat in the Gulf of Mexico (GOM). Offshore facilities require constant inspection and FM—and the significant financial obligation of these activities—to stay ahead of rapid equipment degradation. In general, regulatory codes in the GOM require a visual inspection of pressure equipment and piping on a 5-year frequency at minimum. A common approach is to inspect 20% of the facility per year, with a rolling 5-year inspection plan, to balance the inspection work through time. As a result, in a 5-year inspection cycle, the owner or operator of the facility will not see the condition of the piping or equipment for the 4 years between inspection cycles. Considering the complexity, high areas, overwater, and other difficult-to-inspect areas, gathering data for inspection can be costly and time-consuming and can yield a variable quality of results. An effective asset-integrity program requires full visibility of asset and equipment condition. Prioritizing areas for nondestructive examination (NDE) on high-consequence equipment and piping allows for effective risk reduction and FM planning. To that end, AI and ML are being harnessed to detect, classify, quantify, and report the condition of piping and equipment in the GOM.