Automated Painting Survey, Degree of Rusting Classification, and Mapping with Machine Learning

Abstract

Continuous fabric maintenance (FM) is crucial for uninterrupted operations on offshore oil and gas platforms. A primary FM goal is managing the onset of coating degradation across the surfaces of offshore platforms. Physical field inspection programs are required to target timely detection and grading of coating conditions. These processes are costly, time-consuming, labour-intensive, and must be conducted on-site. Moreover, the inspection findings are subjective and provide incomplete asset coverage, leading to increased risk of unplanned shutdowns. Risk reduction and increased FM efficiency is achieved using machine learning and computer vision algorithms to analyze full-facility imagery for coating degradation and subsequent ‘degree-of-rusting’ classification of equipment to industry inspection standards. Inspection data is collected for the entirety of an offshore facility using a terrestrial scanner. Coating degradation is detected across the facility using machine learning and computer vision algorithms. Additionally, the inspection data is tagged with unique piping line numbers per design, fixed equipment tags, or unique asset identification numbers. Computer vision algorithms and the detected coating degradation are subsequently used as input to determine the ‘degree-of-rusting’ throughout the facility, and coating condition status is tagged to specific piping or equipment. The degree-of-rusting condition rating follows common industry standards used by inspection engineers (e.g., ISO 4628-3, ASTM D610-01, or European Rust Scale). Atmospheric corrosion is the number one asset integrity threat to offshore platforms. Utilizing this automatic coating condition technology, a comprehensive and objective analysis of a facility's health is provided. Coating condition results are overlaid on inspection imagery for rapid visualisation. Coating condition is associated with individual instances of equipment. This allows for rapid filtering of equipment by coating condition severity, process type, equipment type, etc. Fabric maintenance efficiencies are realized by targeting decks, blocks, or areas with the highest aggregate coating degradation (on process equipment or structurally, as selected by the user) and concentrating remediation efforts on at-risk equipment. With the automated classification of degree-of-rusting, mitigation strategies that extend the life of the asset can be optimised, resulting in efficiency gains and cost savings for the facility. Conventional manual inspections and reporting of coating conditions has low objectivity and increased risk and cost when compared to the proposed method. Drawing on machine learning and computer vision techniques, this work proposes a novel workflow for automatically identifying the degree-of-rusting on assets using industry inspection standards. This contributes directly to greater risk awareness, targeted remediation strategies, improving the overall efficiency of the asset management process, and reducing the down-time of offshore facilities.