Marine robotics for offshore wind – nice to have or a necessity?

The appetite for increased automation and a reduced need for sending people offshore in offshore renewable energy operations is fast evolving, with trust in robotics systems increasing and the use of uncrewed vessels becoming commonplace.

The appetite for increased automation and a reduced need for sending people offshore in offshore renewable energy operations is fast evolving, with trust in robotics systems increasing and the use of uncrewed vessels becoming commonplace. The primary drivers for this are to improve health and safety and to reduce the cost of wind farm development and operations and maintenance (O&M) activity.

As the number and size of wind turbines increases and development sites move deeper offshore, O&M will become increasingly uncomfortable and more costly for humans to perform and so the benefits of using robotics and uncrewed systems (UxV) will increase.

According to research by ORE Catapult, the UK’s leading technology innovation and research centre for offshore renewable energy, integrating USVs into a 2GW cluster site could help reduce upfront capital costs by £7.5 million and cut annual operating expenditure by £850,000, or £21 million over a 25-year operating life. In a world where a global pandemic, such as we are experiencing, severely limits travel, the benefits of enabling more work to be done remotely, using UxV, are even greater. Furthermore, robotics systems could increase net capacity factors due to faster servicing.

Underwater robotics, such as remotely operated vehicles (ROVs) and autonomous underwater vehicles (AUVs) are already being used today on a routine basis and uncrewed surface vessels (USVs) and aerial drones (UAVs) are starting to be adopted.

For those in any doubt, it’s worth considering a world without UxV. Without them, the industry is reliant on fully crewed hydrographic survey ships for all initial survey and site characterisation operations. Without underwater robotics UXO surveys and remedial action has to be done using divers, dive support vessels and their crews. Sensors used to profile tidal currents and the sea-state have to be deployed and recovered every few months by crewed survey boats for the data to be analysed. In short, development projects will take longer and cost more.

The difference will be even greater in the O&M space, where there is so much more scope for UxV, especially as these activities continue to scale-up across the increasing gigawatts of capacity we have installed and due to be installed. A 500MW wind farm may require the operation of around seven crewed vessels, depending upon distance from shore, according to ORE Catapult research. Across all O&M spend, vessels and people make up 60 – 65% of costs, not to mention the associated carbon footprint. How much of that could be replaced with UxV operations?

How viable will it be to meet national targets for offshore wind buildout, such as the UK’s goal for 40GW of offshore wind by 2030, without UxV? The Global Wind Energy Council believes offshore wind capacity will reach more than 234GW by 2030, up from about 29GW at the end of 2019. The Ocean Renewable Energy Action Coalition, led by Ørsted and Equinor, is even more ambitious and believes 1,400GW by 2050, globally, is an achievable target. Can we do that without more UxV? And what does a robotics world in offshore wind look like?

There could be subsea vehicles that work out of seabed garages to carry out underwater inspections on demand in a repeatable, quantitative and qualitative way; USVs that deploy ROVs, AUVs and aerial inspection systems to carry out a majority of inspection requirements and a proportion of maintenance needs. USVs could support survey, site characterisation, UXO, construction, logistics, security and environmental monitoring. Some of these capabilities are already here and being deployed, especially around coastal survey and data harvesting. More is coming. In 2021, Ocean Infinity, with its Armada fleet, and Fugro with its SEA-KIT vessels, will bring the first USVs able to deploy ROV systems remotely in the field to market. More will come as confidence and functionality increase.

The challenge will be to make these systems robust, capable and reliable for long periods of time in what can be remote harsh environments. A large part of that challenge is about hardware. These will need to be robust, low-maintenance, electric, automated platforms. But they’ll also need remote control and a degree of autonomy (e.g. situational awareness and an ability to respond to their environment), which will increase over time, underpinned by excellent navigation capability, secure communications links for command and control, status updates, tracking and data transfer. This capability will also need to be extended to below the surface of the sea.

At the surface, Wifi, 4G/5G and satellite communications are now largely available in most operating regions, but interruptions are possible, so multiple sensors will be needed to underpin accurate navigation and control. Just as today’s autonomous cars need multiple sensor inputs (visual, GNSS, inertial measurement units (IMU), etc.) to make sure that if one goes awry the system can still navigate without risk of collision, uncrewed vessels will require the same, on and below the surface.

This requires instruments and data fusion, such as interfacing GNSS at the surface with, for example, subsea acoustic Doppler and inertial navigation systems. As well as being able to verify GNSS data, these systems can also act alone, supporting navigation even without a GNSS input – in a fjord, for example – but will also provide valuable underwater current profile data for both wind farm seabed and scour monitoring and subsea vehicle deployment. It’s potentially complex, but doesn’t have to be with single instruments, such as SPRINT-Nav, able to provide all of that subsea data input via only one interface. SPRINT-Nav has been tested in Navy trials, where precision is paramount, and it will be installed on USVs entering the market in coming months.

Simultaneous tracking, communicating with, command and control of multiple underwater robotics can also be taken care of with a single system, such as a robotics-enabled Ranger 2 Ultra-Short BaseLine (USBL) system, which can also support survey operations. Fitted with our Mini-Ranger 2 USBL system running our Robotics Pack, these USVs will enable users to deploy, track, command and control ROVs during inspection, survey and data harvesting projects, from onshore remote operations centres, unlocking real-time data upload and quality control.

These are well established, off the shelf technologies, with long and deep track records across multiple sectors. For example, Sonardyne instruments have been supporting nearly all of the leading USV manufacturers for more than a decade to perform operations from tectonic plate movement in deep water for ocean science to seismic surveys for oil and gas.

It’s also been supporting industry collaborative projects, such as the Autonomous Robotic Intervention System For Extreme Maritime Environments (ARISE) project, with ASV Ltd. (now part of L3 Harris). Its systems will be onboard robotic ships that enter the offshore renewables market in 2021.

Sonardyne’s latest projects include working with HydroSurv Unmanned Survey (UK) Ltd. to develop an environmental monitoring capability for the offshore renewable energy sector that will be demonstrated at Vattenfall’s European Offshore Wind Deployment Centre (EOWDC) near Aberdeen. By combining new Sonardyne seafloor and vessel-mounted instruments with HydroSurv’s REAV-40 USV, the project will show how combined technologies can provide an end-to-end service for ’seabed data to desk’ without swamping communications bandwidth.

Undoubtedly, however, there will be challenges to fully adopting these new ways of working within the offshore wind sector. There is still a need for clear regulatory requirements surrounding the use of USVs around offshore wind assets, where they need to operate safely together with other marine traffic and operations. There will also be learnings around cyber and physical security, as USVs and their payloads go out into the open ocean. This is inevitable and needed. Like any new way of doing things, it’s about getting involved, deploying and learning how to make the best use of these new systems. In 10 years’ time, we’ll likely look back at the advances that have been made, just as the terrestrial robotics industry is now looking back at robotics that can backflip. It’s only a matter of time.

Source:Riviera, Nov 10, 2020

AI is Helping Scientists Understand an Ocean’s Worth of Data

If you had about 180,000 hours of underwater recordings from the Pacific Ocean, and you needed to know when and where, in all those different hours, humpback whales were singing, would you Google it?

That is what Ann Allen, a research ecologist at the National Oceanic and Atmospheric Administration, did. Sort of.

In January 2018, she approached Google and asked if they might be able to help her find the signal of humpback whale songs amid all the other ocean noise, like dolphin calls or ship engines. Using 10 hours of annotated data, in which the whale songs and other noises were identified, Google engineers trained a neural network to detect the songs, based on a model for recognizing sounds in YouTube videos, said Julie Cattiau, a product manager at Google.

About nine months later, Dr. Allen had a model for identifying humpback whale songs, which she is using in her research on the occurrence of the species in islands in the Pacific and how it may have changed over the last decade. Google used similar algorithms to help Canada’s Department of Fisheries and Oceans monitor in real time the population of the endangered Southern Resident Orca, which is down to around 70 animals.

Machine learning and artificial intelligence applications are proving to be especially useful in the ocean, where there is both so much data — big surfaces, deep depths — and not enough data — it is too expensive and not necessarily useful to collect samples of any kind from all over.

Climate change makes machine learning that much more valuable, too: So much of the data available to scientists is not necessarily accurate anymore, as animals move their habitats, temperatures rise and currents shift. As species move, managing populations becomes even more critical.

To protect the whales, scientists need to know where they are, which is what the Charles Stark Draper Laboratory and the New England Aquarium are doing in what they call “counting whales from space.” Taking data from satellites, sonar, radar, human sightings, ocean currents and more, they are training a machine-learning algorithm to create a probability model of where the whales might be. With such information, the federal, state and local authorities could make decisions about shipping lanes and speeds and fishing more quickly, helping them to better protect the whales, according to Sheila Hemami, director of global challenges at Draper.

Many fish populations are moving, too, or are overfished or nearing it, and much of that fishing is done illegally. In an effort to clamp down on illegal activity and keep populations at healthy levels in the ocean, Google also helped start Global Fishing Watch, an organization that monitors fishing around the world by collecting and making vessels’ positions and activities public.

“The oceans are a pretty exciting place to work in big data because there’s so much opportunity for improving data, which, in fisheries has historically been very poor, especially when you compare it with other extractive industries,” said David Kroodsma, Global Fishing Watch’s director of research and innovation.

“Twenty percent of fishing is illegal, unreported or unregulated,” he said. “What if we didn’t know where 20 percent of the forests were, or carbon emissions?”

Other applications are used in ocean chemistry and pollution, for tasks like monitoring ocean plastic. Using sensors similar to those that monitor air quality in the International Space Station, Draper is collecting data on the properties of microplastics found in the ocean at the request of the Environmental Protection Agency. From that information, they produce “a fingerprint of specific chemicals,” said Dr. Hemami, and use that fingerprint to train the algorithm to identify kinds of plastic.

They are still in the testing phase, but have deployed their first-generation sensor near the Northern Pacific gyre, home to the Great Pacific Garbage Patch, which helped provide information about how the system might work.

Machine learning has not yet been widely used in assessing other issues in ocean chemistry, like ocean acidification, deoxygenation or nitrate concentrations, but Dr. Hemami said there was significant promise in that area.

In at least one case, animal observation applications and the more chemically focused ones overlap. They come together in shared pursuit of the giant larvacean.

Kakani Katija, a principal engineer at the Monterey Bay Research Aquarium Institute, has been using machine learning to track the lives of these zooplankton, which build themselves elaborate houses out of mucus, and model their behavior. In their snot-bubble homes (which can exceed three feet), the tiny animals (about half the length of a new pencil) filter water, in the process capturing particles and detritus sinking from the surface of the ocean to eat.

Once the structure is clogged with this ocean dust, much of which is made up of photosynthesizing organisms that have pulled down atmospheric carbon dioxide in the process, the animals abandon their homes, which sink to the ocean floor and feed bottom dwellers. But they have another crucial function: In trapping all of that debris, the mucus houses are sequestering carbon dioxide, sending it to the bottom of the ocean.

As we burn fossil fuels, we release carbon dioxide, much of which is absorbed by the oceans. The oceans have, as a result, prevented our planet from warming by as much as 36 degrees Celsius (instead of about one degree), but all of that carbon dioxide makes the oceans more acidic. Knowing how much carbon dioxide the ocean is storing is crucial to modeling future climate changes, and given the prevalence of these creatures around the world and how much water they can filter, it is likely a significant amount.

“With the oceans or the environment, it’s really easy for us to get stuck in this doom-and-gloom narrative,” Dr. Katija said. “What I love about technology or the progress we’re seeing in A.I., I think it’s a hopeful time because if we get this right, I think it will have profound effects on how we observe our environment and create a sustainable future.”

Source: New York Times, Apr 8, 2020