23 mars 2020 | International, Terrestre, C4ISR

Raytheon AI: Fix That Part Before It Breaks

A modern mechanized military lives or dies by maintenance. But what if a computer could warn you when your weapons and vehicles were about to break, so you could fix them before they ever let you down?

By

WASHINGTON: Raytheon is working with the military on multiple pilot projects for AI-driven predictive maintenance.

What's that? Traditionally, military mechanics spend a huge amount of time on what's called preventive maintenance: They carry truckloads of spare parts to war, they consult historical tables of roughly how often certain parts wear out or break down, and they preemptively crack open the access hatches to check those parts on a regular basis. The idea behind predictive maintenance is to feed all that historical data into a machine learning algorithm so it can tell maintainers, vehicle by vehicle and part by part, when something is likely to fail.

It's a tremendous technical challenge that requires scanning in years of old handwritten maintenance forms, downloading digital records, and then constantly updating the database. Ideally, you want up-to-the-minute reports on things like engine temperature and suspension stress from diagnostic sensors installed in frontline vehicles.

You need to account not only for what kind of equipment you're operating, but how hard it's running for a particular mission and even where in the world it's operating, because environmental conditions like heat, moisture, dust, and sand make a huge difference to wear and tear. And you can't just push out a single software solution and call it done. You have to constantly update your data so the algorithm can continue to learn, evolve, and adapt to different situations.

But, Raytheon's Kevin Frazier and Butch Kievenaar told me, artificial intelligence and machine learning have advanced dramatically over just the last five years. Now Raytheon – a long-established defense contractor – is partnered with a flock of niche innovators to make it happen.

Currently, they told me, Raytheon is already conducting or about to launch several multi-month pilot projects, seeking to prove the technology's value to the military:

  • For the Army, they're working with a commercial partner on the M2 Bradley Infantry Fighting Vehicle, the mainstay armored troop transport of the heavy combat brigades, and the hulking M88 Hercules, a tracked “armored recovery vehicle” designed to tow broken-down battle tanks back for repair, if necessary under enemy fire.
  • For the V-22 Joint Program Office – which supports the Osprey tiltrotor for the Marines, Air Force Special Operations Command, and now the Navy – they're working on the V-22's collision-avoidance radar, a Raytheon product.
  • And across their customer base, they're looking at ways to do predictive maintenance on the many complex components Raytheon provides for a host of programs.

How does this work? Let's hear from Kevin and Butch in their own words (edited for clarity and brevity from a highly technical 50-minute interview):

Q: What kinds of problems can this technology help the military solve?

Kevin: Right now, maintenance is conducted either on a scheduled timeline or when something breaks. What we are trying to do is replace that one piece because you know it's about to wear out and prevent it from breaking.

Butch: One of the biggest things is you've got to understand what mission you're trying to achieve. If I'm trying to answer platform readiness questions, then I have to have certain data that's related to that topic. If I am trying to do supply chain analysis, I'm asking questions about where are critical parts and what size stockages we have to have to reduce turnaround time. So I'm answering a different question, and I'm looking at a different data set.

So the key to setting all this up is what you do on the front end with your data to give the data scientists so that we can refine the algorithm appropriately.

Q: AI/ML requires a lot of data. Is that data really available for all these different military systems?

Kevin: It is. It's in different states. Some vehicles have sensors on them. Some do self-diagnostics. Some of the older equipment, especially the support equipment, doesn't have any sensors on them — but they all have files. They all are in the maintenance system, so the data exists.

Data doesn't have to purely digital. It does have to be digitized at some point, but it doesn't necessarily have to start being digital. It could be maintenance logs that are hand-written, or the operator of a particular vehicle does a walk around and does an inspection report, writes that up — that's something that you actually can scan and input.

Now we can add so many different types of data that your whole data environment becomes much richer. It helps you get to that algorithm — and then to continue to take in that data and refine that model. You're still recording that data and getting data from both handwritten and digital sources to update your model and tune it, so that you're just that much more accurate.

Butch: What we're talking about is discrete algorithms solving for discrete problem sets. You look at the environment, and what the algorithm does is it learns.

You keep ingesting data. You can get it a bunch of different ways so your analytical tool continues to learn, continues to refine. I can do a physical download from the vehicle, or scan maintenance records, or get it all fed off of a downloader that automatically feeds to the cloud. It can be as fast as we can automate the process of that piece of equipment feeding information back.

For the Army and the Air Force especially, there is sufficient data over the last 15 that pertains to the impacts of combat. And we have it for different environments that you can then use to help train and refine the algorithms that you're using as it learns.

Kevin: You have to understand the impacts the environment has on how the vehicle is functioning and what type of a mission you're doing, because that will cause different things to wear out sooner or break sooner.

That's what the AI piece does. The small companies that we partner with, who are very good at these algorithms, already do this to some extent in the commercial world. We're trying to bring that to the military.

Butch: The really smart data scientists are in a lot of the smaller niche companies that are doing this. We combine their tools with our ability to scale and wrap around the customer's needs.

These are not huge challenges that we're talking about trying to solve. It is inside the current technological capability that exists. We have currently several pilot programs right now to demonstrate the use cases, that this capability that actually works.

https://breakingdefense.com/2020/03/raytheon-ai-fix-that-part-before-it-breaks

Sur le même sujet

  • Northrop Grumman gets a start on next-gen missile warning satellites

    30 août 2018 | International, C4ISR

    Northrop Grumman gets a start on next-gen missile warning satellites

    By: Daniel Cebul WASHINGTON — The Air Force awarded Northrop Grumman a contract worth as much as $47 million for an analysis of system and payload requirements for a new missile warning satellite system in polar orbit. Specifically, the contract will be used for the Next Generation Overhead Persistent Infrared Polar (OPIR) space vehicles 1 and 2. Work will be performed in Redondo Beach, California, and is expected to be completed by June 25, 2020, according to a contract announcement. The OPIR polar space vehicles will be part of a five-satellite constellation that will augment the legacy Space-based Infrared Satellite (SBIRS), which operates as the U.S. military's early warning missile system. During the fiscal year 2019 budget release, the Air Force announced its plans to cancel the 7th and 8th SBIRS satellites in favor or reallocating funds towards OPIR systems. In May 2018, the Air Force released a notice of intent to sole-source contracts to Lockheed Martin and Northrop for the new program. Lockheed Martin will produce three geosynchronous orbiting satellites and Northrop Grumman is responsible for two polar orbiting satellites. The first geosynchronous OPIR satellite is scheduled to be launched in 2023, and the first polar satellite is scheduled to launch in 2027. The Air Force wants the entire “block O” architecture to be operational by FY 2029. Lockheed Martin is the prime contractor on the SBIRS satellites. Northrop Grumman provides the sensors, a scanner and a starer, on those satellites. Full article: https://www.c4isrnet.com/c2-comms/satellites/2018/08/29/northrop-grumman-gets-a-start-next-gen-missile-warning-satellites

  • The Army and Marine Corps are looking at what troops will need to fight in megacities, underground

    10 janvier 2019 | International, Terrestre, C4ISR

    The Army and Marine Corps are looking at what troops will need to fight in megacities, underground

    By: Todd South A recent Army and Marine war game that included engineers, academics and other defense representatives evaluated how troops could use experimental technologies to fight in dense urban areas and underground. The U.S. Army Subterranean and Dense Urban Environment Materiel Developer Community of Practice is a working group that has conducted three prior workshops that set the challenges of fighting in those environments. “Fighting in dense urban environments and the unique challenges it presents is still not totally understood, and this study was the front-end look at identifying and defining those materiel challenges to drive where investments need to be for this operational environment,” said Bob Hesse, technical lead coordinator for the Community of Practice. The most recent “tabletop” exercise looked at the gear troops might need to get through those intense battle scenarios, according to an Army release. Soldiers and Marines worked as friendly and enemy forces during the exercise, evaluating 48 experimental future technologies. One such piece of tech would be using sensors that attach to the exterior building wall to help troops visualize the interior layout. And every advantage in these terrains can help. “Everything that Marine formations or Army formations have to do is more difficult when you take it into an urban environment,” explained Marine Corps Brig. Gen. Christian Wortman, commanding general of the Marine Corps Warfighting Laboratory, and vice chief of Naval Research. The Marines recently launched Project Metropolis II, a five-year effort to better prepare Marines for likely future urban battles. “Across the warfighting functions — whether it's intelligence, surveillance or reconnaissance, collections, maneuver, force protection, command and control, logistics and sustainment — all of those things are complicated and challenged by the compartmentalized terrain that's present in the urban environment and the three-dimensional nature of the urban environment,” Wortman said. And that multi-dimension challenge grows with the subterranean. For both above ground and underground, robotics will play a major role. The Squad X project by Defense Advanced Research Projects Agency, for example, is blending robots into dismounted formations. Soldiers with the 10th Mountain Division and 101st Airborne Division along with Marines at Camp Lejeune, North Carolina, are experimenting with four submissions for the Squad Multipurpose Equipment Transport gear mule that will carry fuel, water, ammunition and equipment for a squad through rough terrain over 60 miles on a 72-hour mission. Lt. Col. Calvin Kroeger, battalion commander for the 35th Engineering Battalion, ran one of the blue teams during the tabletop exercise. Participants ran scenarios such as a high-intensity fight, a traditional counter-insurgency and a security force-assisted mission, all under the conditions of a megacity. But the wargaming went beyond simply clearing buildings and attacking objectives. Teams countered enemy social media campaigns, communicated underground, and assessed the second- and third-order effects of engaging the enemy with lethal munitions, which could impact local power, gas and water networks. “How we employ our capabilities changes as you move from a high-rise platform to urban cannons,” Kroeger explained. “But you're also looking at everything under the ground as well, where you can't use a conventional means like a mortar system to shape the battlefield, so that the enemy doesn't shape it for you.” As team members fix on what materiel needs might best serve troops, Hesse said the subject matter experts will assess how well the tech will meet military goals. For example, if there is an aerial technology that might help troops locate enemy forces, even though the troops can't see them because of the skyline, his team would then analyze that technology and determine how well it meets Army standards and if it needs to be modified. “We will now transition from the workshop learning to live experiments and replicate the unique conditions in real venues. We're taking the materiel campaign of learning and now transforming that into action,” Hesse said. https://www.armytimes.com/news/your-army/2019/01/09/the-army-and-marine-corps-are-looking-at-what-troops-will-need-to-fight-in-megacities-underground/

  • Germany’s fighter jet race could start dropping bidders this summer

    22 juin 2018 | International, Aérospatial

    Germany’s fighter jet race could start dropping bidders this summer

    By: Sebastian Sprenger COLOGNE, Germany ― A multibillion dollar program to replace the German military's Tornado aircraft is nearing another round of decisions that could narrow the field of bidders. The due date for a “quality gate” review, as the wide-ranging analysis is called in Bundeswehr jargon, has been on the calendar for this month. But officials now say the exercise could last through the summer. The discussions are principally about realizing an extended service life for the 1970s-era Tornados, though exactly by how long remains to be seen. Closely linked to that question is an examination of what potential follow-on aircraft are best suited to pick up the legacy planes' roles in a variety of life-span scenarios. Officials emphasize that no decision has been made on who will build the new planes to replace roughly 90 Tornados. A formal competition is expected to begin later this year or early 2019 among those aircraft types still deemed suitable by the government at that time. In the running is the Eurofigher Typhoon, Lockheed Martin's F-35, and Boeing's F-15 and F-18. The Typhoon is made by a European consortium of Airbus, Leonardo and BAE Systems. Defence Ministry officials have said they prefer the Eurofighter option, arguing that keeping the European aircraft industry busy will be key in strengthening the continent's defense capabilities. That goes especially for the Franco-German alliance in charge of developing a combat-capable aerial drone and, later, a sixth-generation Future Combat Air System. Some in the Luftwaffe, the German air force, are rooting for the F-35. The affinity partly stems from personnel exchanges with the U.S. Air Force, giving German pilots some exposure to the marquee American defense program. All companies delivered their formal offers to the Defence Ministry in April, coinciding with the ILA Berlin air show. Lockheed Martin staged a sizable promotional showing at the event for its F-35, mixing promises about the jet's advanced capabilities with a professed obliviousness to the political minefield of Europe's economic powerhouse that is Germany weighing a U.S. aircraft at this time. As German analysts continue to crunch the numbers on the Tornado-replacement effort, Reuters reported this week that Berlin requested information from the Pentagon in April about what it would take to certify the Eurofighter to deliver nuclear weapons. NATO policies for nuclear burden-sharing dictate that German pilots will carry American atomic bombs in case of a war on the continent. The Luftwaffe has set aside a number of Tornados for that purpose, and any follow-on aircraft will have to be configured to carry out the mission. While the Pentagon has no say over which jet Germany will eventually pick, officials in Washington must approve the integration of American nuclear bombs on the aircraft. Citing sources on both sides of the Atlantic, Reuters reported that the process could take up to 10 years and that the F-35 was in line for the nuclear weapons integration before the Eurofighter would be considered. A wait time of seven years could conflict with Berlin's plan to begin phasing out Tornados starting in 2025. But according to officials, that's where the fine-tuning of the “quality gate” could come into play, making it possible to alter the timing accordingly. “We are confident that Eurofighter Typhoon can deliver all the capabilities the German Air Force requires and perform all the roles that are currently performed on Tornado for Germany,” a Eurofighter spokesman said. “This of course includes the nuclear role.” https://www.defensenews.com/global/europe/2018/06/21/germanys-fighter-jet-race-could-start-dropping-bidders-this-summer/

Toutes les nouvelles