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

  • Italy to send second air defence system to Ukraine, foreign minister says
  • Contract Awards by US Department of Defense - July 20, 2020

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

    Contract Awards by US Department of Defense - July 20, 2020

    NAVY Lockheed Martin Corp., Lockheed Martin Aeronautics Co., Fort Worth, Texas, is awarded an $861,731,778 modification (P00040) to previously-awarded fixed-price incentive (firm target), firm-fixed-price contract N00019-17-C-0001. This modification exercises options to procure eight Lot 14 F-35A Lightning II repositioned aircraft as a result of the Republic of Turkey's removal from the F-35 program, and six Lot 14 F-35A aircraft for the Air Force. Additionally, this modification establishes undefinitized line items that provides recurring engineering in support of the modification of the eight Lot 14 F-35A Lightning II repositioned aircraft to a full operationally capable F-35A Air Force configuration. Work will be performed in Fort Worth, Texas (63%); El Segundo, California (14%); Warton, United Kingdom (9%); Orlando, Florida (4%); Nashua, New Hampshire (3%); Baltimore, Maryland (3%); San Diego, California (2%); various locations within the continental U.S. (1.3%); and various locations outside the continental U.S. (0.7%). Work is expected to be completed by May 2026. Fiscal 2020 aircraft procurement (Air Force) funds for $848,881,778 will be obligated at time of award. No funds will expire at the end of the current fiscal year. The Naval Air Systems Command, Patuxent River, Maryland, is the contracting activity. Undersea Signal Systems Inc., Columbia City, Indiana, is awarded a $28,323,687 cost-plus-fixed-fee-contract to develop a prototype sonobuoy, known as Extended Range Directional Frequency Analysis and Recording (ER-DIFAR), to address new and quiet threat submarine targets. Work will be performed in Columbia City, Indiana, and is expected to be completed by July 2024. The total cumulative value of this contract is $28,323,687. This is a three-year base contract with one one-year option period. The base period is $24,128,769 and the option year is $4,194,918. Fiscal 2019 research, development, test and evaluation (Navy) funds in the amount of $50,000; and fiscal 2020 research, development, test and evaluation (Navy) funds in the amount of $4,061,000 are obligated at time of award. Funds in the amount of $50,000 will expire at the end of the current fiscal year. This contract was competitively procured under N00014-19-S-B001, “Long Range Broad Agency Announcement (BAA) for Navy and Marine Corps Science and Technology.” Since proposals are received throughout the year under the long range BAA, the number of proposals received in response to the solicitation is unknown. The Office of Naval Research, Arlington, Virginia, is the contracting activity (N00014- 20-C-2015). General Dynamics Missions Systems Inc., McLeansville, North Carolina, is awarded a $13,553,807 cost-plus-fixed-fee and cost-only modification to previously-awarded contract N61331-11-C-0017 to exercise an option for engineering support for ongoing development, test and production of the Surface Mine Countermeasure Unmanned Undersea Vehicle (SMCM UUV) program, also known as Knifefish. Work will be performed in Quincy, Massachusetts (52%); McLeansville, North Carolina (27%); Braintree, Massachusetts (10%); Hanover, Maryland (5%); Reston, Virginia (5%); and Ann Arbor, Michigan (1%). The Knifefish program will provide persistent volume and bottom mine hunting capability in a contested environment. This option exercise is for engineering support hours to support a number of efforts, including test and evaluation, engineering change proposal development and upgrade initiatives. Work is expected to be completed by September 2021. Fiscal 2020 research, development, test and evaluation (Navy); and fiscal 2020 other procurement (Navy) funding in the amount of $12,500,000 will be obligated at time of award. Funds will not expire at the end of the current fiscal year. The Naval Sea Systems Command, Washington, D.C., is the contracting activity. Navatek LLC,* Honolulu, Hawaii, is awarded a $9,170,852 cost-plus-fixed-fee completion contract with no option periods for the talent and technology for Navy Power and Energy Systems. Work will be performed in Honolulu, Hawaii (50%); and Columbia, South Carolina (50%). The work to be performed will advance the state-of-the-art autonomous command and control of shipboard power systems, to include next-generation integrated power and energy systems, in order to harness the full energy available in the Navy's ships to meet critical mission needs. Work is expected to be completed by July 2023. The total cumulative value of this contract is $9,170,852. Fiscal 2020 research, development, test and evaluation (Navy) funds in the amount of $9,170,852 are obligated at time of award. Funds will not expire at the end of the current fiscal year. This contract was competitively procured under N00014-19-S-B001, “Long Range Broad Agency Announcement (BAA) for Navy and Marine Corps Science and Technology.” Since proposals are received throughout the year under the long range BAA, the number of proposals received in response to the solicitation is unknown. The Office of Naval Research, Arlington, Virginia, is the contracting activity (N00014-20-C-1106). AIR FORCE BAE Systems Technology Solutions and Services Inc., Rockville, Maryland, has been awarded a $495,482,136 firm-fixed-price, cost-plus-fixed-fee and cost-reimbursable indefinite-delivery/indefinite-quantity contract for the Instrumentation Range Support Program. This contract provides for serviceable components and subsystems for instrumentation tracking systems, worldwide for both foreign and domestic government agencies to include radars, telemetry and optical range mission systems, flight termination systems, data acquisition systems and Global Positioning Systems. Work will be performed on participating ranges in the program, including Air Force, Army, Navy, NASA, Department of Energy, as well as foreign ranges in the United Kingdom, Germany, Norway, Sweden, Republic of Korea and Switzerland. Work is expected to be completed Sept. 30, 2027. This award is the result of a competitive acquisition and three offers were received. Fiscal year 2020 operations and maintenance funds in the amount of $116,235 are being obligated, on a delivery order, at the time of award. This contract has a ceiling amount of $945,234,462. The 45th Contracting Squadron, Patrick Air Force Base, Florida, is the contracting activity (FA2521-20-D-0005). National Native American Construction Inc., Coeur D Alene, Idaho (FA4620-20-D0005); Northcon Inc., Hayden, Idaho (FA4620-20-D-0006); Alutiiq General Contractors LLC, Tacoma, Washington (FA4620-20-0008); RORE Inc., San Diego, California (FA4620-20-0009); M.J. Takisaki Inc., Seattle, Washington (FA4620-20-D-0010); and WHH Nisqually-Garco JV 2, Olympia, Washington (FA4620-20-D-0012), have been awarded a not-to-exceed $95,000,000 firm-fixed-price, indefinite-delivery/indefinite-quantity contract for design-build construction efforts at Fairchild Air Force Base, Washington. Work will be performed at Fairchild AFB, Washington, and is expected to be completed June 30, 2025. This award is the result of a competitive acquisition, and 10 offers were received. Fiscal 2020 operations and maintenance funds in the amount of $500 are being obligated to each at the time of award. The 92nd Contracting Squadron, Fairchild AFB, Washington, is the contracting activity. Richland Industries LLC, Pulaski, Tennessee, has been awarded a $24,800,000 indefinite-delivery/indefinite-quantity, firm-fixed-price contract for simplified acquisition of base engineering requirements. This contract will provide for a streamlined means to complete minor construction projects that encompass a broad range of sustainment, maintenance and repair and research development testing and evaluation projects on real property at Arnold Engineering Development Complex, Arnold Air Force Base, Tennessee. Work will be performed at Arnold AFB, Tennessee, and is expected to be completed July 19, 2025. This award is the result of a competitive service-disabled, veteran-owned, small-business, set-aside acquisition with 10 offers received. Fiscal 2020 operations and maintenance funds in the amount of $123,731 are being obligated at the time of award. Air Force Test Center, Arnold Air Force Base, Tennessee, is the contracting activity (FA9101-20-D-0001). Vanguard Pacific LLC, Foley, Alabama, has been awarded a $7,304,129 firm-fixed-price contract for protective coating and sign maintenance. This contract provides for airfield rubber removal, striping of airfield, streets and parking lots, protective coating and sign maintenance. Work will be performed at Joint Base Andrews, Maryland, and Davidsonville and Brandywine communications sites, and is expected to be completed Aug. 4, 2025. This award is the result of a competitive service disabled veteran owned small business set aside acquisition and one offer was received. Fiscal 2020 operations and maintenance funds in the amount of $3,776 are being obligated at the time of award. The 316th Wing, Joint Base Andrews, Maryland, is the contracting activity (FA2860-20-D-0003). ARMY DRS Sustainment Systems Inc., St. Louis, Missouri, was awarded an $189,828,895 hybrid (cost-no-fee, cost-plus-fixed-fee, firm-fixed-price) contract for development, production, deployment and support of the Mobile-Low, Slow, Small Unmanned Aircraft System Integrated Defeat System. Bids were solicited via the internet with one received. Work locations and funding will be determined with each order, with an estimated completion date of July 30, 2025. U.S. Army Contracting Command, Redstone Arsenal, Alabama, is the contracting activity (W31P4Q-20-D-0031). Russell Construction Co. Inc., Davenport, Iowa, was awarded a $10,284,300 firm-fixed-price contract to construct a Special Operations Forces assessment and selection training complex. Bids were solicited via the internet with 10 received. Work will be performed at Fort Bragg, North Carolina, with an estimated completion date of Sept. 17, 2022. Fiscal 2020 military construction, defense-wide funds in the amount of $10,284,300 were obligated at the time of the award. U.S. Army Corps of Engineers, Wilmington, North Carolina, is the contracting activity (W912PM-20-C-0018). *Small Business https://www.defense.gov/Newsroom/Contracts/Contract/Article/2280473/source/GovDelivery/

  • General Atomics: New radar to turn Gray Eagles into anti-drone hunters

    11 octobre 2023 | International, Aérospatial, Terrestre, Sécurité

    General Atomics: New radar to turn Gray Eagles into anti-drone hunters

    The first batch of Gray Eagle 25Ms are now being built with the Eagle Eye radar for delivery in 2026, and General Atomics said more are on the way.

Toutes les nouvelles