Yet, despite the billions spent annually on maintenance and inspections, unexpected failures still happen. Downtime still costs millions. And integrity teams are still fighting to get ahead of problems before they escalate.

“Corrosion impacts the industry with 3 trillion US dollars annually. We need subject matter experts who understand AI and help create more opportunities in the corrosion industry. There is a use case in which we need experts to create value by reducing corrosion using process data in terms of identifying where the corrosion is and how you can reduce it.“

Amin Nasser, President and CEO of Saudi Aramco

So, why is asset integrity so challenging, and what needs to change?

The Problem: A Perfect Storm of Pressure

Across oil and gas, power generation, and industrial facilities, companies are grappling with a mix of old infrastructure, harsh environments, tight budgets, safety risks and growing regulatory scrutiny. Add to that a shrinking workforce and a mountain of disconnected data, and you’ve got a perfect storm.

“We’re working with equipment that’s decades old in some cases,” said a senior reliability engineer at a global energy company. “And we’re trying to make decisions with incomplete data, under constant pressure to reduce costs. That’s a tough place to be.”

Here’s a closer look at what teams are up against:

• Disjointed inspection data spread across spreadsheets, PDFs, and legacy systems, making it hard to get a clear picture of asset health.
• Aging assets that are being pushed beyond their design life, often without clear visibility into their current condition.
• Corrosion and material degradation that can’t always be seen—or predicted—until it’s too late.
• Talent gaps as experienced personnel retire, leaving behind tribal knowledge that isn’t always captured or passed on.
• Budget and access constraints that limit how much of the asset base can be inspected—and add complexity with scaffolding, permits, and coordination that slow down even routine tasks.
• Increased safety risks and costs tied to sending personnel onsite or offshore for manual inspections—especially in hazardous environments where even routine checks can carry high exposure for Person-on-Board (PoB).

It’s not just a technical problem. It’s an operational and HSE one too. And it’s putting integrity teams in a reactive position, when they’d rather be ahead of the curve.

The Insight: Integrity is a Data Problem

One of the biggest shifts in thinking is recognizing that asset integrity is as much a data challenge as it is an engineering one.

There’s no shortage of inspection data—ultrasonic scans, drone footage, sensor readings, maintenance logs. But the problem is fragmentation. The insights live in different systems, departments, and formats. The teams that need the full picture often don’t have access to it.

Interviews with offshore operators in the Arabian Gulf often reveal that the challenge isn’t a lack of data, but rather the need to make better use of the data already available. Many highlight the importance of connecting existing information into a single, accessible view—emphasizing that this would significantly improve the speed and quality of their decision-making.

Innovation: Connecting the Dots

With modern digital asset management platforms, organizations can bring together accurate inspection results—significantly reducing subjectivity in assessments of defects/anomalies, historical databases for temporal analysis, and even 3D visualizations into one centralized view. This isn’t about replacing engineers—it’s about giving them the tools to see the full picture and act confidently.

Features like:

• Interactive digital twins that overlay inspection data on actual asset geometry.
• Dashboards that highlight trends and anomalies.
• Automated workflows that ensure critical findings are tracked, followed up on, and closed out.
• Role-based access so inspectors, engineers, and leadership can all see what matters to them.
• Integration of existing data i.e. Asset Performance Management (APM) database to the updated tool or vice versa.

These innovations shift integrity teams from reactive fire-fighting to proactive planning—enabling them to prioritize high-risk areas, strategically plan inspection and fabric maintenance campaigns, optimize resource utilization, and prevent failures before they occur.

Abyss Point of View: Simple, Powerful, Scalable

At Abyss, we’ve seen this transformation firsthand.

Our work with clients in the energy sector has made one thing clear: when you make asset integrity data visual, connected, and structured—you unlock a whole new level of control. Abyss is actively engaged in R&D collaborations with several energy supermajors to drive the level of precision and reliability the industry demands.

We believe that the future of integrity isn’t about more tools. It’s about simplifying how teams interact with the tools they already use, and making their insights easier to access, trust, and act on.

From offshore platforms to onshore terminals, we’ve worked across a wide range of critical assets—both above and below the waterline—to help operators digitize their integrity workflows without overcomplicating them. That experience has shown us that the right solution isn’t just about software—it’s about meeting the realities of field inspections, complex logistics, and high-stakes operational timelines by understanding the operator’s workflows.

Digital transformation in asset integrity is gaining momentum, but it’s not without challenges. Much of the analysis still depends heavily on the quality of data collected—and how effectively it’s interpreted by users. While this evolving space is helping surface common patterns from global inspections, it’s clear that further R&D is needed to make these solutions more practical, scalable, and adaptable to real-world field conditions. 

“Technology keeps evolving but these new tools and systems should always remain backward compatible so any existing workflow is not disrupted”, said an integrity lead at Gulf of America operator.

Conclusion: Integrity You Can See, Share, and Trust

Asset integrity isn’t getting easier, but it doesn’t have to stay this hard.

By recognizing the challenges as rooted in data fragmentation, and by adopting smarter ways to unify and visualize that data, energy operators can reduce risk, increase uptime, and give their teams the clarity they need to act with confidence.

In an industry where safety, performance, and reputation are on the line, that clarity makes all the difference.

Want to learn how leading operators are transforming their asset integrity workflows? Let’s talk!

The post Asset Integrity in the Energy Sector: Unprecedented Challenges and Solutions appeared first on Abyss.

Work on the contract is set to commence in January 2025.

Since its founding over a decade ago, Abyss Solutions has pioneered industry-leading solutions for scalable inspections in the energy, marine, and critical infrastructure sectors. The company’s foundation is built on unparalleled technical expertise, a robust intellectual property portfolio, and a globally recognized team excelling in computer vision, machine learning, sensing, software engineering, and artificial intelligence.

“This new award strengthens our diverse portfolio of projects with major energy companies and demonstrates our long-term commitment to the Brazilian market, providing innovative and efficient solutions to meet our clients’ needs”, said Paulo Martins, Regional Director for South America.

“The expected capability provided by Abyss Solutions, involving the automatic identification of scene elements based on all the information available in Ativo360 digital assets, will enhance the significant benefits of the solution, including reduced MHER (man hours exposed to risk) in activities reliant on field dimensional surveys and inspections. Additionally, the solution aims to lower OPEX (operational expenditures) through improved maintenance planning and reduced demand for support vessels during production stops, thanks to more efficient activity scheduling. The service will initially cover Petrobras’ entire fleet of offshore platforms, with potential expansion to onshore assets in the future”, says Lucas Castelli, Petrobras Ocean Engineering R&D Manager

The post Abyss Solutions Signs Research & Development Contract with Petrobras appeared first on Abyss.

HOUSTON, Dec. 4, 2024 /PRNewswire/ — Applus+, a global leader in the Inspection, Testing and Certification sector, is pleased to announce a strategic partnership with Abyss Solutions (Abyss), a cutting-edge provider of Artificial Intelligence (AI) and machine-learning solutions for inspection and maintenance. This collaboration marks a significant milestone in advancing Non-Destructive Testing (NDT) capabilities through the integration of AI-driven technologies.

By bringing together the extensive experience of Applus+ in NDT with Abyss’ innovative AI algorithms and software platforms, this collaboration aims to revolutionize asset inspection processes, enabling faster, more accurate, and data-driven decision-making.

“We are excited to partner with Abyss Solutions to unlock the full potential of artificial intelligence within inspection and testing,” said Adam Alessandrino, Executive Vice President of the Pacific region at Applus+. “By integrating AI-driven technologies into our inspection processes, we are well positioned to deliver unparalleled value to our clients by enhancing efficiency, reliability, and safety.”

Through this partnership, Applus+ and Abyss will focus on developing AI-powered inspection solutions that enable predictive maintenance, asset optimization, and risk mitigation for clients across various industries, including oil and gas, mining, manufacturing, and infrastructure across the Pacific and South-East Asia

“We are thrilled to collaborate with Applus+, a global leader in Inspection, Testing, and Certification services,” said Gary Hill, Regional Director at Abyss Solutions. “By leading a disruption in the inspection industry, Applus+ is addressing challenges once considered unsolvable due to workforce shortages. We are excited to partner with them on this transformative journey.”

About Applus+:

Applus+ is one of the world’s leading and most innovative companies in the Testing, Inspection and Certification (TIC) sector, offering a broad portfolio of services and solutions for customers across various industries. Its solutions ensure that assets and products meet quality, health & safety and environmental standards and regulations, while also enhancing performance. Headquartered in Spain, the company operates in more than 70 countries and employs over 26,000 people. The Applus+ Group drives profitable revenue growth through sustainable services and digitalisation at all levels.

About Abyss Solutions:

Abyss is pioneering the future of inspection at scale, providing products and solutions that enables autonomous robots to capture and analyze data at an unprecedented level. Its industry-leading technology is pushing the boundaries of the possible, going beyond the status quo to deliver billions of dollars in risk reduction for some of the world’s biggest companies. We’ve curated the brightest minds in autonomy who strive to help protect the world’s most valuable assets and resources, delivering the insights needed to inform preventative maintenance programs, exceed health and safety targets, and significantly reduce CO₂.

The post Applus+ in Australia partners with Abyss Solutions appeared first on Abyss.

The Thames Tideway Tunnel was a critical project designed to protect the tidal River Thames from increasing pollution, as London’s outdated sewerage system discharges millions of tonnes of untreated sewage mixed with rainwater into the river annually. The tunnel spans approximately 31km, can be more than 7m wide and 68m deep. To mitigate health and safety risks during inspections, Tideway sought to employ robots, necessitating the development of a robot capable of meeting specific requirements.

The main tunnel imposes challenging demands on the robotic inspection system, including the ability to traverse 7km within an 8-hour window, identify a range of defects in the extensive tunnels and shafts, and achieve detection accuracy within +/- 0.5m. Following a global search, it was concluded that a custom solution would be needed to fulfill these requirements.

The Solution

Building on our extensive experience in autonomous infrastructure inspections, the team of robotics, computer vision, and machine learning engineers developed the ATARI (Abyss Tunnel and Aqueduct Robotic Inspector). Equipped with six computer vision cameras, four strobe lights, two lidar scanners, and various other sensors, the ATARI can travel autonomously, capturing brightly illuminated, 360-degree images of the tunnel interior. It can operate continuously along a 10km tunnel and be launched and retrieved via drop shafts, eliminating the need for personnel to enter the confined space.

The Results

During the testing phase, the ATARI system navigated autonomously through the tunnel collecting detailed visual and 3D data. Abyss’s data pipeline was able to map all the data into a reality twin 3D representation of the tunnel. Its unique AI/ML analytics pipeline could then robustly identify various features and defects and localize them with high precision across the tunnel. The result is an accurate 3D reconstruction of the scene with all findings highlighted and tracked in an objective, accurate and scalable manner.

In summary, the system successfully identified all defects down to a size of 2cm, with location accuracy within 5cm, achieving a significant milestone in Abyss’s vision to pioneer autonomous systems for large-scale inspection.

The post Thames Tideway Tunnel Project appeared first on Abyss.

Abyss Solutions’ pioneering Lantern Eye system, now operable remotely, represents a significant advancement in subsea inspections. This article showcases its application in a remote operation context, showing the system’s efficiency, versatility, and ability to provide high-fidelity, sub-mm accurate imagery and measurements.

Introduction

Traditional subsea inspections often require onsite technicians, leading to increased costs and logistical complexities. The remote-operable Lantern Eye system offers a solution, enabling high-quality inspections from any location, significantly benefiting the oil and gas industry.

Value to Customers

• Reduced Operational Costs: Eliminates the need for an Abyss technician onsite, cutting travel and accommodation expenses.
• Increased Flexibility: Allows for inspections to be conducted from any location, enhancing operational responsiveness.
• Enhanced Safety: Minimizes the risk associated with deploying personnel in hazardous environments.
• High Efficiency: Accelerates inspection process, with potential to complete inspections within minutes.

Results

The remote operation of the Lantern Eye system proved highly effective, providing high-fidelity imagery and precise, sub-mm measurements. The ability to conduct remote inspections without compromising on data quality or accuracy marked a significant innovation in the field.

Conclusion

The remote-operable Lantern Eye system by Abyss Solutions sets a new benchmark in subsea inspection technology. Its ability to deliver high-quality, class-standard compliant inspections remotely offers unparalleled value to clients in the oil and gas sector, reducing costs, increasing safety, and enhancing operational flexibility.

The post Transforming Subsea Inspections with Remote-Operated Lantern Eye™ System appeared first on Abyss.

Introduction

Abyss Solutions developed the LEA system, a novel approach to the inspection of mooring chains in splash zones. This system, deployable by a Rope Access Technician (RAT) team, captures high-fidelity images to create accurate, contactless measurements from 3D reconstructions.

Value to Customers

• Enhanced Accuracy: LEA offers a sub-1% error margin, significantly improving upon the inconsistency of manual caliper measurements.
• Operational Efficiency: The streamlined process reduces inspection time, leading to cost savings and minimized downtime.
• Data Reliability: Objective, repeatable measurements ensure consistent inspection results, vital for effective maintenance strategies.
• Safety Improvement: Contactless, remote operation reduces the risk associated with manual inspections in challenging environments.

Background

Traditionally, splash zone inspections are dependent on manual techniques, which are not only labor-intensive but also prone to human error. LEA’s innovative approach offers a solution that is both technologically advanced and user-friendly, overcoming these historical challenges.

Case-Study Scope

In this study, LEA was applied to inspect five chain links across four mooring lines, with its measurements rigorously compared against traditional caliper measurements to establish its precision and reliability.

Methodology

LEA’s advanced stereo camera system, complemented by high-powered strobe lights, was maneuvred around the chains by RAT personnel. This allowed for comprehensive imaging, which was then used to create detailed 3D models for accurate measurement analysis.

Results

LEA’s measurements of bar diameter and inter-grip length showed a maximum deviation of 1.7% and 0.9%, respectively, from caliper measurements. These results highlight LEA’s capability to match and surpass traditional methods in accuracy.

The post How Abyss Improved Splash Zone Inspections with Lantern Eye™ Air (LEA) appeared first on Abyss.

A water utility in Australia had a critical, mile-long water supply tunnel that urgently needed renovations. It, however, was also the home to a colony of endangered microbats, i.e. Little Bent-wing and Southern Myotis bats. A record of the bat population was required before any construction activities could commence A second report was also needed after all work inside the tunnel was completed, so any impact on the bats could be assessed.

The client was searching for a way to understand where the bat colonies were located within the tunnel since the interior consisted of both rough-cut rock and concrete. Traditional surveying methods could not provide this information. It was also essential that the survey be conducted without disturbing the animals and without impacting the operation of the water supply system. Finally, the project had to be managed in a way that could be replicated in different seasons over a two year period to fully assess the health of the bat population.

The Solution

The Abyss autonomous floating inspection vehicle, called Platypus, had a proven record of conducting comprehensive surveys of aqueducts around the world and was chosen as the platform to be adapted to this specialized task.

The Platypus was able to autonomously navigate along the tunnel without disturbing the residents while collecting IR imagery of the entire tunnel’s interior from multiple camera systems, waterline to waterline. This was all managed without humans needing to enter the hazardous, confined space and without having to adjust normal water supply operations.

The Results

An accurate record of the location and the size of the bat population was obtained. More so, the bats seem very happy with their newly renovated home and have returned in healthy numbers.

The post Bat Monitoring Case Study appeared first on Abyss.

Atmospheric corrosion is the biggest asset integrity threat to offshore platforms. Manual inspection of topside equipment is labor-intensive, subjective, and provides incomplete asset coverage, increasing the risk of unplanned shutdowns. Computer Vision algorithms can be used to detect corrosion, enabling high-risk equipment to be targeted for remediation. This article covers the first-in-industry application of an artificial intelligence-based system to improve corrosion management and inspection processes. The system is deployed across a large offshore oil and gas (O&G) platform in the Gulf of Mexico, demonstrating greatly improved inspection and maintenance processes while reducing the operating costs and risks associated with offshore O&G platforms.

External corrosion on offshore oil and gas 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 programs where all equipment is assessed periodically with the aim of reducing operational costs while maintaining integrity. Regulatory codes for offshore platforms in the Gulf of Mexico (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 tonnes), 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 piece of equipment is only inspected once in the five-year cycle). Equipment and infrastructure layout can be complex, with equipment at-heights, spanning over water, or being in difficult to access areas. This can make inspections costly, time consuming, and yield varying quality of results. Variance across inspections can arise from the inspector’s subjectivity, the environmental changes, and the present working conditions around the platform. Inspectors must sometimes access equipment that is difficult to access or see, making close assessments difficult.

An effective asset integrity monitoring requires full visibility of asset and equipment conditions. Prioritizing non-destructive examination (NDE) on high consequence of failure or high likelihood-of-failure equipment results in effective risk reduction and improved fabric maintenance planning. For instance, high consequence-of-failure equipment (such as a high-pressure gas line) with severe corrosion must be addressed as soon as possible. Further, prioritization of a complementary painting/ remediation program is also critical to preventing assets reaching this level of deterioration in the future. By prioritizing the remediation of high-risk assets and optimizing the remediation process, the overall risk decreases significantly, and the cost of remediation and inspection continues to decrease with each re-inspection. At scale, this enables operators to reduce their assigned personnel on board (PoB) per platform.

The automatic detection of corrosion in images has been explored in recent literature. 1-9 Ortiz et al.2 demonstrated the effectiveness of using a single-layer artificial neural network for the detection of corrosion and cracks in ship ballast tanks. Hoang and Tran4 used a Support Vector Machine to classify small tiles of an image as containing rust or no rust. Petriccaet et al.3 and Nash et al.5 trained a Convolutional Neural Network (CNN) to classify an entire image as either containing rust or no rust, while Nash et al.6 estimated the required effort for attaining human-level accuracy for corrosion detection by a CNN to be >65,000 labeled images. Finally, Ferguson et al.,7 Majors et al.,8 and Garcia et al.9 leverage CNNs to classify pixels in an image (i.e., semantic segmentation) as either containing rust or not, giving a detailed understanding of the scene.

A case study is presented, where an artificial intelligence (AI)-based corrosion detection and management system (using a machine learning algorithm) 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. The case study demonstrates:

• The cost reduction of inspection programs when using the AI-based system vs. traditional manned visual inspections
• Increased inspection coverage when using the AI-based system vs. traditional manual visual inspections
• A decrease in the required PoB on an offshore platform required to conduct general visual inspections (GVIs)
• The reduction of risk across a platform through the prioritization of inspection and remediation
• The benefits associated with better prioritization and optimization of painting campaigns
• The benefits associated with the improved optimization of platform maintenance

Experimental Procedure

A terrestrial scanner is used to comprehensively capture inspection data (i.e., 360 degree panoramic images and laser scans) across the topside of an offshore platform. Scans are performed at locations approximately 2.5 m apart, over the entire platform. For a large deep-water spar production platform (approximately five 200 by 200 ft [61 by 61 m] decks), the scanning process requires nearly 14 days with five data scanning personnel. An example of a captured panorama is seen in Figure 1(a), while Figure 1(b) shows a 3D point-cloud representation of two decks of an offshore platform, made by combining a number of captured scans.

All inspection imagery is processed using automated corrosion detection algorithms, which localize and categorize corrosion across the facility by severity. Figure 2 shows an example of detected and classified corrosion, overlaid on inspection imagery, with atmospheric corrosion severity represented by color. A user can virtually walk through the inspection data, and be directed to equipment, such as equipment where heavy corrosion has been detected.

Due to the spacing of scans, equipment often appears in multiple views (i.e., it is common for equipment to be imaged from multiple angles and at various distances). Since all inspection imagery is spatially located within a common frame of reference, it is possible to combine the multiple inspection viewpoints and predictions together to produce a single, comprehensive 3D-visual dataset of the asset, as seen in Figure 3. Combining multiple views has many benefits. For example, if a portion of some equipment piece is obscured at a single scan location, it is often visible in neighboring scans. This process reduces the impact of camera obstructions and helps to maximize coverage of the equipment and the platform. Furthermore, corrosion predictions from multiple viewpoints can be merged via various statistical methods to further refine predictions and increase the accuracy of classification. Figure 3 shows aggregate corrosion metrics produced from three (of 38) separate views that have been statistically combined.

By associating captured imagery and with the corresponding laser data, it is possible to calculate the physical area, dimensions, and location of detected corrosion. Providing area measurements enables improved estimation of damage and prioritization of remediation for individual pieces of equipment.

Detected corrosion anomalies are registered to individual pieces of equipment, making it possible to quickly search and show the state of every item on the platform. Association of anomolies with equiment identities allows condition reports for all equipment on a platform to be provided by the operator. Individual objects can be queried and filtered ( for instance, by pipe diameter, pressure, piping class, and/or service designation). For example, the user can query all lines of the “highpressure gas” service type which have any severe atmospheric corrosion. These can be then scheduled for priority remediation. From the automatic detection of corrosion and coating condition in inspection imagery by the AI-based system, inspection workpacks are created to facilitate NDE and remediation of faults.

Results

An AI-based corrosion detection and management system is deployed across an offshore oil and gas platform located in the Gulf of Mexico. The offshore platform is a 10,000 tonnage semi-submersible, with 80,000 bbl per day production. The following case study demonstrates the value of corrosion detection and management with the AI-based system. It demonstrates the cost reduction of inspection programs when using the AI system vs. traditional manual visual inspections, the reduction of risk across a platform through the prioritization of inspection and remediation, the benefits associated with prioritization and optimization of painting campaigns, and benefits associated with the optimization of platform maintenance programs. A traditional manned GVI campaign is compared directly against the AI-based corrosion detection and management system.

The coverage of equipment across the platform, the number of production lines inspected, the approximate cost, and the number of personnel on-board the platform required to complete an inspection, are all compared. Similar performance of the AI-based corrosion detection and management system have been experienced on a number of platforms in the GoM.

A direct comparison between inspection coverage from the AI-based corrosion detection/management system and inspection results from traditional inspections is provided. Approximately 75% of all equipment is covered by deck-level scans. Coverage is improved to approximately 97% through the capture of scans in positions that consider corner-cases such as tight spaces, complex pipework, and equipment at heights. In contrast, only 20% of equipment was covered in the 2019 GVI campaign. The AI system provided approximately 77% more coverage. Further, the full platform health assessment provided by the AI-system was $0.5M USD less than the proposed annual budget for traditional manned GVI. The direct recurring savings for each following year would be about $1M USD annually for the example platform. Further, the coverage of each AI-based inspection includes >97% of equipment, compared with about 20% coverage of the 2019 GVI campaign.

Inspection workpacks are created based on corrosion and coating degradation across the platform, as detected by the AI-based system. Workpacks are organized and prioritization schedules are provided, which enables optimization of remediation, follow up inspection, NDT, or replacement actions. Prioritization is achieved by automatically conducting a risk analysis for each piece of equipment and defect. Risk matrices and evaluations for each production asset are computed by comparing the severity of corrosion and coating degradation against the criticality of the equipment (e.g., a high-pressure gas line may have a high consequence of equipment failure, have severe corrosion detected, and should therefore have a high follow-up inspection or remediation priority). By prioritizing the remediation of corrosion and coating degradation based on the risk profile of equipment on which these defects are detected, asset integrity risk reduction across the entire facility is demonstrated.

The inspection outcomes of the AI-based corrosion detection and management system are summarized here:

• 83 nominations for “urgent equipment replacement”, where equipment has an estimated time-to-failure of 6 to 12 months
• 217 high-priority painting nominations, where if equipment is not painted then equipment will degrade to the point of requiring urgent equipment replacement within 12 to 24 months

The cost of equipment replacement for all 83 “urgent” items is approximately $15M USD. The total cost of failure for a single item of equipment ranges from $0.5M to $52M USD, based on the platform operators estimates. The detection of corrosion and subsequent “urgent replacement” of the equipment prioritized by the AI-based corrosion detection and management system represents a significant reduction in financial risk for facility operators.

For each of the 217 high-priority-forpainting lines, savings are approximately $100K to $250K USD, when compared against the cost of inaction. Based on operators’ estimates against the cost of “urgent replacement,” this equates to risk reduction of $21M to $55M USD. All “urgent equipment replacement” items were confirmed by the client as critical at the next planned shutdown of the platform. All nominated lines were targeted by maintenance crews for high-priority remediation, by the platform operators. The detection of coating degradation and subsequent prioritization of painting schedules by the AI-based corrosion detection and management system represents a significant reduction in financial risk for facility operators.

Conclusions

Manual offshore platform topside equipment inspection is costly, time-consuming, and labor-intensive. Moreover, inspection findings are subjective and provide incomplete asset coverage, leading to an increased risk of unplanned shutdowns due to missed repairs. Leveraging state-of-the-art machine learning algorithms to detect and classify corrosion across the entirety of a facility, along with contextualization through visual asset tagging, allows for the objective and comprehensive management of corrosion across all process equipment. This article showed this through a case study, where an AI-based corrosion detection and management system was deployed across a large offshore oil and gas platform, in the Gulf of Mexico, in 2020. The inspection outcomes by the AI-based system are compared against the traditional approach used by the operator in 2019. The AI-based system successfully detected corrosion and coating degradation across the platform and prioritized their remediation. The AI-based system provides greater inspection coverage; reduces the required number of personnel on board for general visual inspections; reduces the overall cost of inspections; reduces the risk of unplanned production downtime; and significantly reduces the financial risk associated with managing the offshore platform’s asset integrity.

References

1 E.L. Ferguson, et al., “Atmospheric Corrosion Detection and Management with AI,” 2022 AMPP Conference + Expo (Houston, TX: AMPP, 2022).

2 A. Ortiz, F. Bonnin-Pascual, E. Garcia- Fidalgo, J.P. Company, “Visual Inspection of Vessels by Means of a Micro-aerial Vehicle: An Artificial Neural Network Approach For Corrosion Detection,” Robot 2015: Second Iberian Robotics Conference (Springer, 2016) , pp. 223-234.

3 L. Petricca, et al., “Corrosion Detection Using AI: A Comparison of Standard Computer Vision Techniques and Deep Learning Model,” Proceedings of the Sixth International Conference on Computer Science, Engineering and Information Technology (2016), vol. 91, p. 99.

4 N. Hoang, V. Tran, “Image Processing-based Detection of Pipe Corrosion Using Texture Analysis and Metaheuristic-optimized Machine Learning Approach,” Computational Intelligence and Neuroscience (2019).

5 W.T. Nash, et al., “Automated Corrosion Detection Using Crowdsourced Training for Deep Learning,” Corrosion 76, 2 (2020): pp.135-141

6 W.T. Nash, et al., “Deep Learning AI for Corrosion Detection,” CORROSION 2019 (Houston, TX: NACE International, 2019).

7 E.L. Ferguson, et al., “Automatic Detection And Classification Of Corrosion With Convolutional Neural Networks,” Australasian Corrosion Assoc. Corrosion & Prevention 2020 (Perth, Australia: ACA, 2020).

8 M. Majors, et al., “Automated Corrosion Mapping AI & Machine Learning, Abu Dhabi Intl. Petroleum Exhib. & Conf. (ADIPEC, 2020).

9 R.L. Garcia, P.N. Happ, R.Q. Feitosa, “Large Scale Semantic Segmentation of Virtual Environments to Facilitate Corrosion Management,” Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2021, 465-470, https://doi.org/10.5194/isprs-archives- XLIII-B2-2021-465-2021.

E. L. FERGUSON is the machine learning lead at Abyss Solutions Pty. Ltd., Houston, Texas, USA. He was awarded his PhD in electrical engineering from the University of Sydney in 2019 for his research contributing to the fields of machine learning and signal processing. He also has a B.Eng. and B.Sc. degrees.

S. POTIRIS is a robotics and AI subject matter expert at Abyss Solutions Pty. Ltd. He was awarded his PhD in 2020 where he specialized in building machine learning algorithms for largescale data processing in agriculture. He also has a B.Eng degree.

M. CASTILLO is a product manager at Abyss Solutions Pty. Ltd. He has worked broadly across upstream oil and gas. He is passionate about transforming the energy sector with state-of-the-art technologies and bringing them into the hands of operators. He has a B.Sc degree.

T.F. DUNNE is a senior software engineer at Abyss Solutions Pty. Ltd. He is a technology entrepreneur with over 15 years of experience in research and development, software engineering, image processing, spatial data analysis, and modeling. He has a B.Eng. degree.

S. BARGOTI is the chief technology officer of Abyss Solutions Pty. Ltd. He was awarded his PhD in 2016, where he specialized in building machine learning algorithms for large-scale data processing in order to develop intelligent information systems in agriculture. As CTO of Abyss Solutions, he has led the company toward fulfilling its mission: building intelligence that will drive all unmanned robots of the future. He has a B.Eng. and B.Sc. degrees.

The post Atmospheric Corrosion Detection & Management with Artificial Intelligence appeared first on Abyss.

Introduction

Subsea mooring chain inspections, traditionally reliant on diver or ROV-operated calipers, face challenges of accuracy, time consumption, and high costs. Lantern Eye S, with its ABS-class certification, addresses these issues, offering a high-precision, efficient, and cost-effective solution.

Value to Customers

• Enhanced Accuracy with Certification: Meets and exceeds ABS-class standards, ensuring sub-mm precision in measurements.
• Operational Efficiency: Reduces inspection times from hours to minutes, aligning with the rigorous demands of class-certified operations.
• Cost-Effectiveness: Significantly cuts ship time and operational expenses, a key consideration in class-standard operations.
• Ease of Integration: Quick integration with ROVs, facilitating streamlined class-compliant inspection processes.

Project Background

A leading oil and gas company engaged Abyss Solutions to deploy the class-certified Lantern Eye S for a mooring chain inspection in the Gulf of Mexico, aiming to adhere to the highest industry standards.

Methodology

Lantern Eye S was integrated onto an ROV by an Abyss imaging specialist in collaboration with an ROV team. This setup ensured compliance with ABS class certification requirements, enabling precise and rapid chain inspections.

Results

The use of Lantern Eye S markedly improved inspection efficiency, with the high-precision camera completing tasks in minutes. The 3D models produced from this process met the rigorous accuracy standards set by ABS, providing detailed and reliable data for chain integrity assessments.

Impact & Future Developments

Post-pilot, Lantern Eye S has consistently delivered high-accuracy metrology for various clients, solidifying its position as a class-standard compliant tool. The system’s success in meeting these stringent requirements paves the way for broader adoption in the industry.

Conclusion

Abyss Solutions’ Lantern Eye S, with its ABS-class certification, sets a new standard in subsea mooring chain inspection. Its alignment with class standards significantly enhances the value delivered to customers, ensuring accuracy, efficiency, and cost-effectiveness in subsea operations.

The post Revolutionizing Subsea Inspection with ABS-Class Certified Lantern Eye™ S appeared first on Abyss.

This article outlines an optical stereo photogrammetric imaging system, called the Lantern Eye Air (LEA), for inspecting the mooring chain above the water in the area known as the splash zone. The system is mounted and deployed by a Rope Access Technician (RAT), and achieves data collection in this difficult to access region for subsequent 3D reconstruction and measurements for inspection.

Typically, splash zone mooring chain inspections are carried out using mechanical calipers which are difficult to deploy, provide measurements at discrete locations only and are dependent on the proficiency and judgement of the operator on the field.  The LEA system overcomes these problems, providing objective, accurate and repeatable measurements based on reconstructed photorealistic 3D models. Imagery of the chain links is captured systematically which was used to generate 3D reconstructions and establish measurements of bar diameter and inter-grip length.

A splash zone inspection was undertaken on an offshore platform. The 3D metrology bar diameter measurements were within 1.7% of caliper measurements based on 2σ (95% confidence). Similarly, the 3D metrology inter-grip length measurements were within 0.9% of caliper measurements based on 2σ (95% confidence). Application of a systematic validation procedure following the inspection placed the expected uncertainty of measurements at the 1% range. Similarly, the uncertainty in caliper measurements has been estimated to be 2% based on the use of a standard handheld caliper and measurement procedure laid out in the ABS Guide for the Certification of Offshore Mooring Chain and the 2020 Life Extension Mooring Platform Chain Inspection. Considering these uncertainty bounds, the 3D metrology measurements can also be deemed consistent with the ground truth dimensions.

Based on the results, the LEA and 3D metrology measurements are consistent with current techniques and provide a more systematic and repeatable basis for mooring chain inspection and measurement in the splash zone. This is anticipated to improve the consistency and comparability of inspections and will enable precise change tracking between inspections. 

Introduction

The authors undertook an inspection that demonstrated the technology for high-fidelity imaging and accurate contactless measurement of mooring chains within the splash zone. The authors have developed an optical stereo photogrammetric imaging system that can be deployed by a rope access technician (RAT) team. The system delivers photo-realistic 3D reconstructions and sub-mm accurate measurements. The system provides objective, accurate and repeatable measurements based on reconstructed photorealistic 3D models.

1.1      Background

The authors demonstrate its system on the inspected asset. The objective of the inspection was to validate the performance of the system against a traditional inspection using calipers. Typically, splash zone mooring chain inspections are carried out using mechanical calipers which are difficult to deploy and result in inconsistent measurements (due to variability in the placement and use of calipers). The system overcomes these problems, providing: 

• Highly accurate measurements (achieving less than 1% error after post processing).
• Objective and repeatable measurements based on reconstructed photorealistic 3D models.
• Improved change tracking between inspections enabled by the comparison of 3D models.

1.2      Experimental scope

Five chain links within the splash zone were inspected on mooring lines 1, 2, 4 and 5. This interim report presents the results of the inspection and analysis for chain link A on mooring line 2. The report provides an overview of the data collection and post processing with measurements of bar diameter and inter-grip length. These are presented alongside caliper measurements captured following inspection with the system.

Methodology

Inspection Overview 

The system was developed using technology established by the authors for high-fidelity imaging and accurate contactless measurements of mooring chains underwater. The system was adapted to be handheld and deployable by a RAT team during routine splash zone inspections. The system is tethered and connected to a topside computer on the spar deck. The handheld sensor is composed of a high-resolution computer vision stereo camera coupled with four high-powered strobe lights. 

Prior to the inspection, the system was precisely calibrated and tested to ensure the accuracy of measurements obtained. The system was also rigorously tested to perform within the harsh offshore environment and meet the demands of splash zone inspections. Field testing was used to design data collection procedures that were compatible with RAT team operations and which delivered consistent high-quality data. 

Deployment of the system on the inspected asset involved the RAT personnel navigating around each chain in 360-degree orbits with the system. The imagery was captured continuously throughout the process. Live imagery was beamed to the topside computer with a technician verifying the quality of data and providing instructions for maintaining this data quality. Multiple orbits were conducted along the chain to capture imagery of each link at various angles. 

3D Model Reconstruction and Measurement

3D models were generated from the stereo image pairs collected. The method applied relies on SIFT (Scale Invariant Feature Transform), see Figure 3. These encode basic form and color. Onsite calibration was also undertaken of the system to improve reconstruction. 

The conversion of the images to a point cloud involved the following:

1. Images had features extracted, and then associated across images, allowing relative placement of cameras (localization). The resulting localized features were “sparse” so that the point density is in the cm range.
2. Image sets from localized cameras were then used for extracting points per desired image patch. The point density was significantly higher, up to the 0.1mm range depending on patch size.
3. Local smoothing was undertaken by assuming the object has a locally smooth surface, further removing outliers and improving the accuracy of reconstruction estimates. The point density is decreased by a factor related to the desired smoothing.
4. The point cloud was then meshed by interpolating adjacent points with triangular and quadrilateral polygons. 

Measurements were then extracted from the models produced in accordance with typical inspection requirements for mooring chains, and locations corresponding to caliper measurements. The process involved:

1. Aligning the models with regards to the principal axes of measurement (i.e., defining the vertical and horizontal axes parallel to which measurements will be taken).
2. Sectioning the models at measurement locations as appropriate.
3. Applying simulated calipers along the measurement axes (composed of planes fit to the outermost point of the model along the measurement axes).  

Results

This section provides the results of the inspection and analysis of mooring lines 1, 2, 4 and 5.  Measurements for chain links A to E on each of the four mooring lines are presented herein. 

Dimensional Control Summary

The locations on the chain links at which caliper and 3D metrology measurements have been taken are shown in Figure 4 to Figure 8. The measurement locations are based on typical inspection requirements. The measurement locations include:

• Inter-grip length (Zone 0): which includes two in-plane measurements at 0° relative to the vertical axis as shown in Figure 4.
• Base section (Zone 1): that includes in-plane and out-of-plane measurements at the base side straight section at 0mm from the centerline of the chain as shown in Figure 5.
• Above mid-section (Zone 2): which includes in-plane and out-of-plane measurements at the base side straight section at 200mm above the centerline of the chain as shown on the left side of the chain in Figure 6.
• Above mid-section (Zone 3): which includes in-plane and out-of-plane measurements at the weld side straight section at 200mm above the centerline of the chain as shown on the right side of the chain in Figure 6.
• Weld side (Zone 4): which includes in-plane and out-of-plane measurements at the weld side straight section at 100mm above the centerline of the chain as shown in Figure 7.
• Weld side (Zone 5): which includes in-plane and out-of-plane measurements at the weld side straight section at 100mm below the centerline of the chain as shown in Figure 7.
• Below mid-section (Zone 6): which includes in-plane and out-of-plane measurements at the base side straight section at 200mm below the centerline of the chain as shown on the left side of the chain in Figure 8Figure 6.
• Below mid-section (Zone 7): which includes in-plane and out-of-plane measurements at the weld side straight section at 200mm below the centerline of the chain as shown on the right side of the chain in Figure 8.

For each of the preceding measurement locations (Zones 1-7), in-plane and out-of-plane measurements were taken along the measurement axes accurately aligned with the plane of the chain link. This is shown in Figure 9. 

Measurement Uncertainty 

Application of a systematic validation procedure placed the expected uncertainty of measurements at the 1% range for metrology measurements. This considers a 95% confidence bound and the  underwater use of the system, a more challenging environment than in air. This  represents an upper bound estimation of uncertainty with the system. 

To calculate the caliper uncertainty measurement several sources of error were considered. These include:

• Intrinsic error of up to 0.1mm for a typical field caliper.
• Variation in the angle of the measurement of up to 5^o relative to the plane of measurement.  Based on geometry this contributes to an error of up to 0.4% of the measurement being taken.
• Variation in the angle of the measurement of up to 5^o along the plane of measurement.  Experimentation on the chain link models showed that shifting the measurement by this  angle resulted in a maximum variation of 1% of the bar diameter and inter-grip length.
• Variation of the position along the chain link at which a measurement is taken of up to 5mm.Experimentation on the chain link models showed that shifting the measurement up and down or left and right by this distance resulted in a maximum variation of 1% of the bar  diameter and inter-grip length.

Considering these sources of error to be independent the cumulative error is estimated to be in the order of 2%. Without a precise definition of the caliper measurement procedure this estimate is only intended to be for reference.

Caliper and 3D Metrology Bar Diameter Measurements 

Measurements of the bar diameter of each chain link were extracted from the models by first aligning them with the principal axes of measurement, sectioning the models at measurement locations and applying simulated calipers along the measurement axes to obtain the distance between the most extreme points on the section. An example diameter measurement is shown in Figure 10. The measurement results are presented alongside the corresponding caliper measurements in Appendix A for mooring line 1 as an example.

The 2σ (95% confidence) variation between the caliper and 3D metrology measurements is representative of the maximum deviation between measurement techniques for 95% of results.

Caliper and 3D Metrology Inter-grip Length Measurements 

Measurements of the inter-grip length between each chain link were extracted from the models by first aligning them with the principal axes of measurement, sectioning the models at measurement locations and applying simulated calipers along the measurement axes to obtain the distance between the most extreme point on adjacent links. An example inter-grip measurement is shown in Figure 11. The measurement results are presented alongside the corresponding caliper measurements in Appendix B for mooring line 1 as an example. 

The 2σ (95% confidence) variation between the caliper and 3D metrology measurements is representative of the maximum deviation between measurement techniques for 95% of results.

Conclusion

The authors successfully deployed its system to inspect splash zone links that were pulled in to be accessible in air of mooring lines 1, 2, 4 and 5 on the inspected asset. The system was deployed by a RAT team. Imagery of the chain links was captured systematically which was the used to generate 3D reconstructions and establish measurements of bar diameter and  inter-grip length.  

This report has presented the results of the inspection and analysis for chain links A to E on mooring lines 1, 2, 4 and 5. Measurements of bar diameter and inter-grip length determined from 3D metrology analysis were presented alongside caliper measurements captured onsite.  

The 3D metrology bar diameter measurements were within 1.7% of caliper measurements based on  2σ (95% confidence). Similarly, the difference in 3D metrology inter-grip length measurements was within 0.9% of caliper measurements based on 2σ (95% confidence). The application of a systematic validation procedure following the inspection placed the expected uncertainty of measurements at the  1% range. Similarly, the uncertainty in caliper measurements has been estimated to be 2% based on the use of a standard handheld caliper and measurement procedure laid out in the ABS Guide for the Certification of Offshore Mooring Chain and the 2020 Life Extension Mooring Platform Chain Inspection. Considering these uncertainty bounds, the 3D metrology measurements can also be deemed consistent with the ground truth dimensions.  

Based on the results, the system and 3D metrology measurements are relatively consistent with current techniques and provide a more systematic and repeatable basis for mooring chain inspection and measurement in the splash zone. This is anticipated to improve the consistency and comparability of inspections and will enable precise change tracking between inspections.

Appendix A

Caliper and 3D metrology measurements of bar diameter for chain links on mooring line 1 (example of measurements used to construct results table)

Appendix B

Caliper and 3D Metrology measurement of inter-grip length for mooring line 1.

Authors: Lashika Medagoda, Thomas Van Bruggen, Mitchell Galea, Hamish Morgan, Tajamul Syed, Abraham Kazzaz, Fraser Hamersley, and Jordan Jolly    

The post Stereo Image System for Inspection of Mooring Chain in the Splash Zone appeared first on Abyss.