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?


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.


Sur le même sujet

  • DoD must modernize infrastructure to support cutting-edge technology research

    9 juillet 2020 | International, Aérospatial, Naval, Terrestre, C4ISR, Sécurité

    DoD must modernize infrastructure to support cutting-edge technology research

    By: JihFen Lei If you're reading this over the internet, you're using technology developed by the Department of Defense science and technology enterprise. For decades, the DoD has cultivated a wide-ranging ecosystem of technical professionals, research infrastructure and partnerships that has made vast contributions to U.S. national security and economic strength. From microchips to the GPS satellites that enabled a revolution in precision warfare, the department's S&T enterprise has been central to creating the security and prosperity our nation enjoys today. Although technology dominance has long been central to the American way of war, U.S. military superiority is increasingly under threat. American adversaries are making rapid technological advancements and incorporating them into newly modernized forces. In response, the department has been working to aggressively position its S&T enterprise to meet the security needs of the 21st century. Long-term success will require concentration in three fundamental areas: First, we must invest for the future while focusing on the present. This requires investing in foundational research that will create the next generation of military superiority. Second, we must cultivate a workforce of scientists and engineers ready to solve the DoD's hardest problems. Finally, we must create and maintain world-class defense laboratories and research facilities, enabling us to work with academic and industrial partners to quickly transition technology into capabilities. Each of these elements are critical to nurturing an innovation ecosystem optimized for the department's needs. The road to the next great scientific or technological advance starts with basic science and research. Basic research is central to the DoD's long-term competitive strategy to create and maintain military superiority for the nation. The DoD has a long history of conducting and sponsoring basic research, focusing on understanding how and why things work at a fundamental scientific level. Although basic research is often performed without obvious or immediate benefit and requires long timelines to realize its impact, the importance of continued investment cannot be overlooked. Without the department's basic research investments — made years ago — in the new areas of autonomy, quantum science, artificial intelligence and machine learning, or biotechnology, the DoD would not possess the innovative and advanced capabilities it does today. Basic research enables the U.S. to create strategic surprise for its adversaries and insulates the nation from technological shocks driven by the advancements of others. Stable and healthy investment in basic research is not only good to have, it is a vital component of the nation's strategy to maintain a competitive advantage. The DoD must use all of the tools at its disposal to develop a skilled, diverse workforce of technical professionals who are knowledgeable about the DoD's missions and capable of advising DoD leaders on technology decisions. This includes the scientists and engineers who will conduct research in DoD laboratories and engineering centers, our industry partners, and the academic research community with whom the department closely collaborates. There is nothing more critical to the American military's ability to innovate than its people. For these reasons, the department relies on authorities provided by Congress to conduct flexible, direct hiring of technical professionals to work in DoD research institutions. The department looks for the best technical professionals to join its ranks as researchers, engineers and trusted advisers to the DOD's senior leaders. When the department attempts to incorporate new knowledge from academia or new technologies from industry, the DoD's S&T workforce must be capable of making smart buying decisions based on sound technical judgment and an understanding of the DoD's unique mission needs. At a time when other nations are prioritizing the recruitment of technology professionals to bolster their military strength, the department must view its S&T workforce as a strategic resource that is fundamental to long-term technological superiority. Many capabilities found at DoD labs are unique national treasures and cannot be found elsewhere. On average, these laboratories, which span 63 locations across 22 states and the District of Columbia, are over 45 years old. As part of its strategy to recruit and retain a world-class S&T workforce, the department must modernize its technical infrastructure, laboratories and engineering centers. The DoD should invest wisely to modernize these outdated facilities and their equipment to support the modern, cutting-edge research that our national defense demands. As the nation once again prepares to engage in long-term strategic competition, the DoD's S&T enterprise is the key to success. Sufficiently resourcing long-term research and technology development activities will ensure America avoids technology surprise while creating a disproportionate advantage for the war fighter. The department must make the investments necessary to educate, attract and retain the world's best talent. As the DoD's National Defense Strategy makes clear, advanced technologies will be central to America's ability to fight and win future wars. https://www.defensenews.com/opinion/commentary/2020/07/08/dod-must-modernize-infrastructure-to-support-cutting-edge-technology-research/

  • Pentagon re-awards multibillion-dollar office tools contract to CSRA

    2 novembre 2020 | International, C4ISR

    Pentagon re-awards multibillion-dollar office tools contract to CSRA

    Andrew Eversden WASHINGTON ― The Pentagon re-awarded its Defense Enterprise Office Solutions contract to CSRA on Friday, nearly 14 months after it awarded it to the General Dynamics Information Technology subsidiary last year. The award to CSRA was delayed several times after the General Services Administration twice took corrective action after protests by Perspecta, the other contractor in the competition. According to the announcement from the General Services Administration and Department of Defense, the blanket purchasing agreement is estimated to be worth $4.4 billion over a decade, with a five-year base. The contract was estimated to be worth $7.6 billion when the award was made last year. The DEOS contract will provide the DoD with productivity tools such as word processing and spreadsheets, email, collaboration, file sharing, and storage across the enterprise. “DEOS is a key part of the Department's Digital Modernization Strategy and its fit-for-purpose cloud offering will streamline our use of cloud email and collaborative tools while enhancing cybersecurity and information sharing based on standardized needs and market offerings,” DoD Chief Information Officer Dana Deasy said in a statement. “The last six months have put enormous pressure on the Department to move faster with cloud adoption. All across the Department there are demand signals for enterprise wide collaboration and ubiquitous access to information.” The DEOS environment is intended to meet DoD Impact Level 5 and Impact Level 6 cloud security standards that allow access to unclassified and classified work, respectively. "“We were determined that the Department could achieve faster department-wide adoption of cloud collaboration capabilities by moving forward in a federated manner to the DoD 365 (IL 5) cloud environment while ensuring the individual components efforts work together to create an enterprise capability,” Deasy added. “This approach required the government team to assume a greater responsibility up front to shape the enterprise standards. With the award of DEOS, the Department will be able to transfer a significant part of the ongoing technical and management load to the integrator and free up strained resources to execute other priority missions.” The DEOS contract award was marred by several errors, detailed by NextGov, including issues with the statement of work, requirements and a subsequent incident in which proprietary information about Perspecta's bid was shared with GDIT. CSRA is partnered with Dell Marketing and Minburn Technology Group for the DEOS contract. DoD components have waited a long time for delivery of the DEOS solution. When the original award was made last year, the Marine Corps deputy director of command, control, communications and computers, Kenneth Bible, said the service was looking forward to the “promise and substantial benefits” of DEOS capabilities in “disconnected, degraded, intermittent and low bandwidth [DDIL] environments that are anticipated in 21st century conflicts.” The DEOS re-award comes nearly two months after the department confirmed its other long-delayed enterprise cloud, the Joint Enterprise Defense Infrastructure, to its original winner, Microsoft. That contract has a $10 billion ceiling. https://www.c4isrnet.com/it-networks/2020/10/30/pentagon-re-awards-multibillion-dollar-office-tools-contract-to-csra/

  • Soldiers’ Super Suits Will Sense Surroundings Soon

    5 octobre 2021 | International, Terrestre

    Soldiers’ Super Suits Will Sense Surroundings Soon

    Tooth microphones and spider senses could be coming to a battlefield near you.

Toutes les nouvelles