Digital and IoT technologies enable predictive maintenance for offshore oil & gas assets
CamIn works with early adopters to identify new opportunities enabled by emerging technology.
of CamIn’s project team comprised of leading industry and technology experts
Annual cost savings identified
Year technology adoption roadmap
Cost reductions identified for one oil field asset
Predictive maintenance involves using robotics, data analytics, sensors, operational simulations, and artificial intelligence to predict equipment failures and perform maintenance activities just in time to prevent those failures. The goal is to optimise maintenance schedules, reduce downtime, and extend the lifespan of critical machinery and infrastructure.
Oil and gas firms are particularly interested in predictive maintenance for several reasons.
Maintaining on- and off-shore oil and gas assets poses a huge ongoing headache for the oil and gas industry. According to estimates, oil and gas producers suffer 32 hours of unplanned downtime each month, on average, at a cost of $220,000 per hour. As well as resulting in downtime and loss of product, leaks can result in costly fines from governments and regulators. Corrosion is not just an issue in the Oil & Gas sector. The estimated 2021 global cost in damage due to corrosion according to the National Association of Corrosion Engineers was 2.5 trillion USD.
Furthermore, because oil and gas assets are often in hard to access locations, sending teams of engineers to remote locations is expensive and poses logistical challenges.
As such, oil and gas firms increasingly cite predictive maintenance as a key strategic objective. But while the market is flooded with companies offering predictive maintenance services, few options have proven to be reliable and cost-effective.
The big opportunity in predictive maintenance is the ability to remotely monitor corrosion in real-time on an offshore oil field and identify new corrosion areas early on. This kind of monitoring is conventionally performed by engineers who physically inspect assets with equipment on average every two weeks, based upon integrity budgets. But while tried and tested, sending engineers to inspect pipelines is expensive and time-consuming for many firms and does not make use of the latest technological innovations in both fixed and robotics sensing of corrosion. The sector can expect 15-35% savings in cost from damages by adopting real-time wall thickness measurement solutions for internal and external corrosion. Our client sought a tailored technology blueprint and adoption roadmap for the next five years to help it harness enabling technologies.
.jpg)
A range of enabling technologies are behind innovations in productive maintenance. These include real time fixed sensors (magnetic flux leakage, pulsed eddy current, electromagnetic acoustic transducer, acoustic emission, ultrasound, radiographic, optical fibres), which allow maintenance engineers to monitor previously identified corrosion spots, and robotics (climbers, crawlers, legged robots, drones and wet pipe inspection gauges). The latter of which can be effective but necessitate bulk buying, especially for oil and gas firms looking to monitor remote solutions. Machine learning algorithms can also predict and profile 3D corrosion spots 6 months before they occur. Guided waves can also be used to identify new corrosion spots utilizing a fixed configuration of ultrasound spot sensors. These solutions put sensors along pipelines that can communicate with each other to determine if there is a change in wall thickness of the pipe, for example.
.svg)
Predictive maintenance technology can come in a variety of forms. Our goal was to pinpoint what would make sense for our client’s off-shore asset. To assess the attractiveness of different options, we assembled a team of experts with detailed knowledge of fixed sensing solutions, robotics solutions and commercialising industrial applications of new predictive maintenance solutions.After that, we pinpointed the right solutions and produced design for combining commercial vendors with original prototypes. Our experts conducted thorough technical analyses, which assessed the error margins of 8 metrics such as:
The final work included a quantitative benchmarking analysis that looked at 8 technical KPIs, 8 operational KPIs and 10 commercial KPIs. We assessed vendor products as well as technologies that will be commercialised over the next 5 years. Our solution helped the client fulfil technology upgrades and performance improvements to help them reduce their reliance on engineering services firms. The analysis demonstrated the possible upgrades to the solution and how it would improve our client’s KPIs. As a result, the company’s board authorised a pilot programme to execute a strategy in line with our recommendations.
