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

  • Millennium to apply Victus Nox lessons to missile warning satellites

    13 décembre 2023 | International, Aérospatial

    Millennium to apply Victus Nox lessons to missile warning satellites

    The company in November passed a key design review for the Missile Track Custody program, which aims to develop a constellation of satellites in MEO.

  • What’s industry role in DoD information warfare efforts?

    20 juillet 2020 | International, Aérospatial, C4ISR

    What’s industry role in DoD information warfare efforts?

    Mark Pomerleau Government leaders are telling industry they need help with integration as the Department of Defense and individual services push toward a unifying approach to information warfare. Information warfare combines several types of capabilities, including cyber, intelligence, electronic warfare, information operations, psychological operations and military deception. On a high-tempo battlefield, military leaders expect to face against a near peer or peer adversary. There, one-off solutions, systems that only provide one function, or those that can't feed information to others won't cut it. Systems must be multi-functional and be able to easily communicate with other equipment and do so across services. “A networked force, that's been our problem for years. Having built a lot of military systems, a lot in C4 and mission command, battle command, we build them and buy them in stovepipes. Then we think of integration and connecting after the fact,” Greg Wenzel, executive vice president at Booz Allen, told C4ISRNET. “My whole view ... networking the force really is probably the best thing to achieve overmatch against our adversaries.” Much of this networking revolves around new concepts DoD is experimenting with to be better prepared to fight in the information environment through multi domain operations or through Joint All-Domain Command and Control (JADC2). The former aims to seamlessly integrate the capabilities of each domain of warfare – land, sea, air, space and cyber – at will. It also aims to integrate systems and capabilities across the services under a common framework to rapidly share data. While not an official program, JADC2 is more of a framework for the services to build equipment. “It's more likely a mish-mash of service level agreements, pre-scripted architecting and interoperability mandates that you got to be in keeping with those in order to play in the environment,” Bill Bender, senior vice president of strategic accounts and government relations at Leidos, told C4ISRNET of JADC2. “It's going to take a long journey to get there because, oh by the way, we're a very legacy force and ... a limited amount of technology has the interoperability that is absolutely required for that mission to become a reality.” The “information warfare” nomenclature can fell nebulous and hard to understand for industry officials that provide solutions to the Pentagon. “It's a pretty broad definition. I think it's something that the DoD is struggling with, that's what we're struggling with in industry and it also makes it challenging because no one really buys equipment that way,” Anthony Nigara, director of mission solutions for electronic warfare at L3Harris, said. “No one really buys stuff to an abstract term like information warfare.” Others agreed that the term “information warfare” may be too broad, an issue that's further complicated as each service tackles information warfare in their own way. Most members of industry C4ISRNET talked with on the need to integrate described the key theme of a more networked force as a unifying way to think about the new push to information warfare. “There's a lot of discussions about the Joint All Domain Operations or the multidomain operations. When we look at that and we want to say ‘okay, what is information warfare really mean to everyone?” Steven Allen, director of information operations and spectrum convergence at Lockheed Martin rotary and mission systems, told C4ISRNET. “We look at it as how can we get the right information to warfighters in order to fight or how do we get the right information for them to plan? How do we move all that data across whether it's different levels of security or different levels of the warfighting and the data associated with it.” Others expressed the need for contractors to be flexible with how DoD is describing its needs. “Industry has learned to be flexible in responding to messaging calling for new situational awareness capabilities while other established capabilities were being mandated for use in cyber exercises,” Jay Porter, director of programs at Raytheon Intelligence & Space, said. The push to a more information warfare-centric force under the guise of larger concepts to defeat adversaries is pushing the DoD as a whole to fight in a more joint manner. Paul Welch, vice president and division manager for the Air Force and defense agencies portfolio at Leidos, explained that there's a consistent view by the services and the department that they must integrate operations within the broad umbrella of activities called information warfare just as they're integrating warfighting capabilities between the services and across the domains. This goes beyond merely deconflicting activities or cooperation, but must encompass true integration of combat capabilities. Some members of industry described this idea as one part of convergence. “When I talk about convergence, my observation is there is a convergence in terms of of a family of technologies and of a family of challenge problems and how do they come together,” Ravi Ravichandran, chief technology officer of the intelligence and security sector at BAE, told C4ISRNET. Ravichandran provided five specific challenge problems the military may have in which a married suite of technologies can help provide an advantage against adversaries. They include JADC2, overmatch or the notion of assembling technologies in a way better than enemies, joint fires where one service's sensors may be acquiring a target and passing that target off to another service to prosecute it, sensing in the electromagnetic spectrum and strategic mobility to get forces and resources to a particular place at a particular time. Similarly, Welch provided the notional example of an F-35 flying over an area, seeing something on its sensors and sending that information to either an Army unit, a carrier strike group, a Marine Corps unit, or even a coalition partner to seamlessly and rapidly understand the information and act upon it. These sensors must be incorporated into a joint kill chain that can be acted upon, coordinated and closed by any service at any time. Allen noted that when looking at information warfare, his business is examining how to take a variety of information from sensor information to human information to movement information and pull it all together. “There's a lot of discussion on [artificial intelligence] AI and machine learning and it's very, very important, but there's also important aspects of that, which is hey what's the technology to help the AI, what's that data that's going to help them,” he said. “We tend to look very closely with the customers on how do we really shape that in terms of the information you're getting and how much more can you do for the warfighter.” By bringing all these together, ultimately, it's about providing warfighters with the situational awareness, command and control and information they need to make decisions and cause the necessary effects, be it cyber C4ISR, intelligence or electronic warfare, Nigara said. Porter said at Raytheon's Intelligence & Space outfit, they view information warfare as “the unification of offensive and defensive cyber missions, electronic warfare and information operations within the battlespace.” Integrating EW and IO with cyber will allow forces to take advantage of a broader set of data to enable high-confidence decision-making in real time, he added, which is particularly important in the multi-domain information environment to influence or degrade adversary decision making. From a Navy perspective, the ability to share data rapidly across a distributed force within the Navy's distributed maritime operations concept will be critical for ensuring success. “We will certainly have to include the mechanisms with which we share information, data and fuse that data from node to node. When I say node to node, a node may be a ship, a node may be an unmanned vehicle and a node may be a shore based facility,” Kev Hays, director of information warfare programs at Northrop Grumman, who mostly supports the Navy, said regarding areas Northrop is investing. “Linking all those participants into a network ... is critically important. We have quite a bit of technology we're investing in to help communicate point to point and over the horizon and a low probability of intercept and low probability of detection fashion.” Ultimately, the information space is about affecting the adversary's cognitive space, they said. “When it comes to information warfare, it's a lot less tangible ... It's not tank on tank anymore. You're trying to affect people's perception,” James Montgomery, capture strategy lead for information operations and spectrum convergence at Lockheed Martin rotary and mission systems, told C4ISRNET. As a result, he said, it is critical to take the time with the customer to truly understand the concepts and capabilities and how they all fit together in order to best support them. “Really spending time with them [the customer] and understanding what it is that they're attempting to get at. It helps us better shape the requirements but it also helps us better understand what is it they're asking for,” he said. “When you're moving forward and attempting to come together with both a software hardware based solution to something, it takes a lot of talking time and a lot of touch time with that customer to understand where their head's at.” https://www.c4isrnet.com/information-warfare/2020/07/19/whats-industry-role-in-dod-information-warfare-efforts

  • Army picks two companies to build prototypes for a new cannon-toting vehicle to back up infantry

    18 décembre 2018 | International, Terrestre

    Army picks two companies to build prototypes for a new cannon-toting vehicle to back up infantry

    By: Todd South The Army has selected two companies to provide prototypes of a new armored, tracked vehicle to give infantry units necessary firepower Both Michigan-based General Dynamics Land Systems and BAE Systems will have the next 14 months to build and begin delivering 12 prototypes of the Mobile Protected Firepower vehicle. BAE Systems will build an M8 Buford Armored Gun System with new capabilities and components. GD submitted an offering that puts a version of its latest Abrams turret together with a chassis that uses past work on the United Kingdom's AJAX program. The ultimate product will be either a 105- to 120mm cannon and a tracked vehicle that can withstand a classified level of enemy fire. At least two of the vehicles should be able to fit into the back of a C-17 aircraft. The need is aimed at near-peer threats. Brig. Gen. Ross Coffman, director of the Next Generation Combat Vehicle Cross Functional Team, said that the current and future battlefield will challenge the firepower of the infantry. Right now, Infantry Brigade Combat Teams have artillery to knock out secured enemy positions. “But there's no precision munition to remove bunkers from the battlefield, to shoot into buildings in dense urban terrain,” Coffman said. The MPF vehicle and weapon will be used to “disrupt, break in and breach those secure defensive zones,” Coffman said. The requirement first emerged in the Army's vehicle modernization strategy in late 2015. The target was to give IBCTs a protected, long-range, cyber-resilient, precision, direct-fire capability for early or forcible entry operations. In February, GD and BAE, along with SAIC partnering with Singapore's ST Kinetics and CMI Defense, all submitted proposals. The SAIC team combined CMI's Cockeril 3105 turret with ST Kinetics next-generation armored fighting vehicle chassis. Officials would not discuss the reasons behind the selection. They expect a final decision to be made by fiscal year 2022. Fielding to the first units is expected by fiscal year 2025. The MPF is under the Army's NGCV CFT program, which is overseen by the Army Futures Command. The plans are for roughly 54 vehicles, initially. They will build 26 first, with an option to build 28 more and retrofit eight prototype vehicles. For the existing vehicle fleet, there's another program that's been conducting recent testing to also enhance the combat vehicle firepower and protection. The Army chose to evaluate two Active Protection Systems at a November live-fire rodeo, looking at whether either system could work as an interim protection system for one of its combat vehicles. The APS will also go onto the MPF vehicle in development at this time. The Israeli-made Trophy VPS by Rafael, a slimmer edition of the Trophy System already on the Abrams tank, and the German-made Active Defense System by Rheinmetall got a chance to showcase their products' abilities atop Strykers at the live fire, according to Military Times sister publication Defense News. Rheinmetall partnered with Michigan-based Unified Business Technologies. They've dubbed their system “Strike Shield.” Army representatives saw the Trophy VPS on a Bradley Fighting Vehicle at a demonstration in Israel in August, Defense News reported. Earlier this year, the Army awarded a $193 million contract to Leonardo DRS for its Trophy APS on the M1 Abrams tank. The program conducted four “soft kill” demonstrations using virtual threats with the system and controller. The APS is an interim solution as the Army develops its Modular Active Protection System as part of a larger suite of Vehicle Protection Systems. In late 2018, developers with the Tank Automotive Research Development and Engineering Center completed successful testing on the MAPS. The MAPS base kit is an array of sensors and countermeasures used with the Modular Active Protection Systems Controller, giving vehicle crews a single solution to run APS for incoming threats such as enemy drones or anti-tank weapons. Bill Beyer, MAPS Virtual Demonstrator lead, said in release following MAPS testing that the base kit would move into the vehicle program portfolio by mid-2019. Rafael was selected to provide its Trophy APS for the Abrams while IMI, also an Israeli company, has put forth the Iron Fist for the Bradley. Participants didn't fully install their systems on the vehicle. They put up mock rigs for testing in front of Strykers mounted their system on a Stryker. https://www.armytimes.com/news/your-army/2018/12/18/army-picks-two-companies-to-build-prototypes-for-a-whole-new-cannon-toting-vehicle-to-back-up-infantry/

Toutes les nouvelles