Naval capabilities
The USS Bulkeley will help test how best to provide predictive maintenance prompts to uniformed maintenance personnel.
$90bn
The amount spent by the US DoD each year on weapon systems maintenance.
13,363
The number of days between 2008–2018 that the US Navy’s fleet of attack submarines spent either in idle time or maintenance delays.
GAO 14
where situations appear that haven’t previously been seen before, according to Tinga. As Tinga explains, the Royal Netherlands Navy is now focusing on ensuring that relevant and high- quality data is collected and properly stored for a wide range of systems and installations on board, in order to create a long-time historic data set. At the same time, it is also exploring methods and algorithms that could be used for practical applications, such as fault detection and monitoring of usage profiles. It is heavily involved in two projects in the European Defence Fund – EDINAF, which concerns digital ship architecture, and dTHOR, which focuses on ship structural health monitoring. Looking ahead, Tinga expects to see navies increasingly invest in the ongoing development of digital models in the design and build process of new ships, which in the future may allow for the greater use of configuration management and predictive maintenance. For existing ships, however, this is still far away, so efforts need to focus on collecting pieces of data that can be directly beneficial for specific maintenance issues. “Rather than collecting everything, the focus should be on identifying specific issues and finding dedicated ways to add sensors and collect relevant data,” Tinga notes.
“In our research, we strongly focus on analysing data collected by dedicated condition monitoring techniques and sensors – vibration monitoring, motor current signature analysis – rather than data from more general process or control-related sensors – temperature, pressure – as the latter are much more indirectly related to degradation and failure,” he adds.
Increasing adoption
While the jury is still out regarding AI – at least in the short-term – practical AI solutions are gaining traction nonetheless. Case in point is a March 2023 agreement between Gecko Robotics and the US Navy. Under this deal, Gecko will use its wall- climbing robots and AI-powered software platform to build digital models of the vessels in order to increase
the speed of maintenance cycles and reduce the time navy vessels spend in dry-dock. The expansion of this work follows the approval of Gecko’s Rapid Ultrasonic Gridding (RUG) process by the US Navy. RUG creates data-rich visual grid maps identifying areas where corrosion and other damage mechanisms have caused wall-thinning. When incorporated into a risk-based inspection (RBI) programme, it improves the ability to visualise the state of mechanical assets. In the case of Gecko Robotics, its robots rapidly capture up to 176 readings per foot at maximum speeds of 60ft per minute, thereby enabling it to quickly inspect large sections of an asset and provide data density regularly exceeding a million A-scan data points. As a result, inspections are completed in a few days, rather than over many weeks. The French Navy has similarly been making moves in this area by testing numerous measurement drones underwater for hull inspection. However, for the time being, these are seen as being a complementary means of assisting decision-making and gaining access to hard-to-reach places. A spokesperson for Marine Nationale, Service de Soutien de la Flotte – otherwise known as the French Fleet Support Service (SSF) – highlights that predictive maintenance isn’t an inherently new concept, arguing it has been decades since maintenance on electric engines, based on vibration measurements, or oil change with oil analysis, has been in operation.
“It was a predictive maintenance based on a single piece of data. What is new today is data quantity and connectivity,” the spokesperson explains. “Any new equipment comes with dozens of real time instrumented parameters. [As a result,] computers and software have the ability today to do whatever we can imagine with them. “We have acquired two remotely operated vehicles (ROVs) for walls of wharf and caisson gate inspections; either for ships’ operational needs or for inspection; [but] we are at the very first step in terms of getting used to those tools and including them in the normal procedure of monitoring.” And therein lies the point; the technology of ship design needs to catch-up with AI – and for major datasets to be established for the latter to be able to fulfil its potential. “For now, we have numerous embedded monitoring solutions, the issues being to synchronise data and have a shared and easy access,” the spokesman concludes. It’s clear that, regarding predictive maintenance, the onus is now on modern navies to look forwards, not backwards. AI and ML are rapidly developing and look set to assume greater importance longer-term, as long as ship design keeps pace accordingly – otherwise historical problems will be more difficult to overcome. AI and ML need large amounts of data. For navies, the challenge is on. ●
Defence & Security Systems International /
www.defence-and-security.com
US Navy / MC2 Christine Montgomery
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45
