Automated Corrosion Mapping AI & Machine Learning
Abstract: Objective Risk reduction and increased Fabric Maintenance efficiency using Artificial Intelligence and Machine Learning algorithms to analyze full-facility imagery for atmospheric corrosion detection and classification. Following imagery capture and processing, deficiencies are identified, and targeted mitigation strategies are executed at greatly reduced cycle time and cost. Methods, Procedures, Process A pre-mobilization fa… Show more
Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Cited by 4 publications
References 3 publications
Automated Painting Survey, Degree of Rusting Classification, and Mapping with Machine Learning
Objective 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. Methods, Procedures, Process 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). Results, Observations, Conclusions 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. Novel/Additive Information 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.
Automated Painting Survey, Degree of Rusting Classification, and Mapping with Machine Learning
Objective 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. Methods, Procedures, Process 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). Results, Observations, Conclusions 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. Novel/Additive Information 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.
Case Study on the Impacts of an Automated Condition Assessment System Deployed Across Offshore Production Facilities
Objectives / Scope Continuous Fabric Maintenance (FM) is crucial for uninterrupted operations on offshore oil and gas platforms. A primary FM goal is managing equipment degradation onset across the production facilities. General Vision Inspection (GVI) programs target timely detection and grading of defects such as corrosion severity, coating condition, and likelihood-of-failure. These processes are costly, time-consuming, labor-intensive, and must be conducted on-site. Moreover, inspection findings are subjective and provide incomplete asset coverage, leading to increased risk of unplanned shutdowns. Insights from inspection programs feed into the prioritization of equipment maintenance and defect remediation. The impacts of an Automated Condition Assessment system on FM efficiency, risk reduction, maintenance cost reduction, and required manpower are demonstrated in practice across four offshore deep water production facilities. Methods, Procedures, Process Inspection Data is collected across the entirety of the facilities using a terrestrial scanner. Corrosion onset, coating degradation, and equipment is detected, classified, and identified across the facility using the Automated Condition Assessment System, empowered by machine learning and computer vision algorithms. Equipment is tagged with unique piping line numbers per design, fixed equipment tags, or a unique asset identification number. Detected defects and equipment tags are registered together, which results in a comprehensive equipment condition database. Each of these individual tags will be used to group together all relevant images and point out potential defects. By amalgamizing the different perspectives, the coverage on each asset will be increased. This includes imagery-based examples as well as holistic point cloud coverage which are used to better prioritize asset management and maintenance processes. Results, Observations, Conclusions Recommendations and their impacts from the Automated Condition Assessment System are compared against recommendations and impacts from the standard GVI process (i.e., physical walkdowns) conducted one year earlier. The GVI process gives gross estimations either by block/ or paint region. The Automated Condition Assessment System uses volumetric data given by scans to report results in various segmentations. These include: per block, line, area, and height groupings. Reported results are averaged across the four deep water production facilities. The Automated Condition Assessment System achieved increased inspection coverage, at a reduced cost, with decreased PoB (Person on Board) requirements. Facility inspection coverage rose from 15% to >95%, with a 6% of the usual PoB requirement, and at a 50% inspection cost reduction. Work packs are created based on the Automated Condition Assessment System recommendations. Better prioritization of maintenance resulted in an estimated 86% reduction in maintenance costs, over a two year period. Novel/Additive Information The Automated Condition Assessment system contributes directly to greater risk awareness, targeted remediation strategies, improving the overall efficiency of the asset management process, reducing maintenance costs, and the down-time of offshore facilities. Fabric Maintenance campaigns vary across many operators in the offshore oil and gas space and can largely depend on cost of PoB. Since painting, remediation, and coating can be such a high-volume task, a large number of people are required to paint a portion of the platform in a short period of time. Many operators cannot afford to have large PoB requirements for their offshore Fabric Maintenance campaigns, so they employ strategies to reduce the time and personnel allocation. For example, an operator may choose to have a parallel strategy where two separate teams address Fabric Maintenance related problems offshore. One team will be dedicated to pursuing issues which are in more critical condition and in risk of becoming nominated for a complete replacement. When an item is replaced instead of remediated, painted, or re-coated the implications of cost increase ten-fold. One paint job’s associated cost could be as low as a few thousand dollars while a full replacement job offshore could be requiring a significant engineering, construction and planning effort amassing to several hundred thousand dollars. Another team could be dedicated to painting by block or designated region. The focus of this team is to address all non-critical issues while also repainting any defects found during their campaign. However, the critical issues cannot be addressed by this team due to the delicate nature of the asset condition. Varying approaches to Fabric Maintenance can also include a dedicated on-site team for painting and remediation or a rotational program that addresses the entire facility. It should also be clear that remediation, coating and painting is not limited to process equipment but can also include structural and safety equipment.
Successful Development and Deployment of a Global ROP Optimization Machine Learning Model
Drilling rate of penetration (ROP) is a major contributor to drilling costs. ROP is influenced by many different controllable and uncontrollable factors that are difficult to distinguish with the naked eye. Thus, machine learning (ML) models such as neural networks (NN) have gained momentum in the drilling industry. Existing models were either field-based or tool-based, which impacted the accuracy outside of the trained field. This work aims to develop one generally applicable global ROP model, reducing the effort needed to re-develop models for every application. A drilling dataset was gathered from exploration and development wells in both onshore and offshore operations from a variety of fields and regions. The wells were curated to have different water depths, down hole drive such as Rotary Steerable System (RSS), PDM, Standard Rotary, bit types (Mill Tooth, TCI, PDC) and inclinations (vertical or deviated). A deep neural network was used for modelling the relationship between ROP and inputs taken from real-time surface data, such as Torque, Weight-on-Bit (WOB), rotary speed (RPM), flow and pressure measurements. The performance of the ROP model was analyzed using historical data via summary statistics such as Mean Absolute Percentage Error, as well as graphical results such as residuals distributions, cumulative distribution functions of errors, and plots of ROP vs depth for independent holdout testing wells not included in the model fitting process. Analysis was done both in aggregate, and for each specific well. The ROP model was demonstrated to generalize effectively in all cases, with only minor increases in error metrics for the holdout test wells, where the Mean Absolute Percentage Error averaged across wells was ~20%, compared to 17.5% averaged across training wells. Furthermore, residuals distributions were centered close to zero, indicating low systematic error. This work proves the case for a "global" ROP prediction model applicable "out-of-the-box" to a broad set of drilling operations. A global ROP model has the potential to eliminate learning curves, reducing time and costs associated with having to develop a new model for every field. Furthermore, a model that effectively captures the relationships between parameters controllable by drillers and ROP can be used for automatically identifying drilling parameters that improve ROP. Preliminary field-testing of the ROP optimization system yielded positive results, with many examples of increased ROP realized after following drilling parameter recommendations provided by the software.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
Contact Info
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Product
Resources
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.
