14 juillet 2020 | International, Aérospatial

Air Force to Add 12 Weapons Systems for AI/ML-Informed Predictive Maintenance This Year

The U.S. Air Force is to add a dozen weapons systems to its Enhanced Reliability Centered Maintenance (ERCM) model that employs artificial intelligence/machine learning (AI/ML) for predictive maintenance.

Those systems are the Boeing [BA] F-15 fighter, B-52 bomber, RC-135 reconnaissance plane, C-17 transport, and A-10 Thunderbolt II close air support aircraft, the Lockheed Martin [LMT] AC/MC-130 gunships, F-16 fighter, and HH-60 helicopter, the Bell [TXT] and Boeing CV-22 tiltrotor, the Northrop Grumman [NOC] RQ-4 Global Hawk and the General Atomics‘ MQ-9 Reaper.

“We have a couple of different initiatives under what we would call the umbrella of predictive maintenance,” Air Force Lt. Gen. Warren Berry, the service's deputy chief of staff for logistics, engineering and force protection, said during a July 9 Mitchell Institute for Aerospace Studies' Aerospace Nation virtual discussion. “One is Condition Based Maintenance Plus [CBM+]. We have three weapons systems in there right now: the C-5, the KC-135, and the B-1. They've been doing it for about 18 to 24 months now, and we're starting to get some real return on what it is that the CBM+ is offering us. The other element is called Enhanced Reliability Centered Maintenance [ERCM], which is really laying that artificial intelligence and machine learning on top of the maintenance information system data that we have today and understanding failure rates and understanding mission characteristics of the aircraft and how they fail, and then laying that into the algorithms that then tell us when parts are likely to fail based on failure rates and the algorithms we plug in.”

“We're in the process of adding another 12 weapons systems under the ERCM umbrella this calendar year,” Berry said. Defense Daily has asked Air Force Materiel Command (AFMC) for the names of the 12 systems.

AI/ML is to assume a significant role in predictive maintenance for the 11 combatant commands (COCOMs).

In April last year, the Pentagon said that the new Joint Artificial Intelligence Center (JAIC) had delivered its first product, a predictive Engine Health Model (EHM) maintenance tool for Sikorsky [LMT] Black Hawk helicopters, to U.S. Special Operations Command's 160th Special Operations Regiment (SOAR) for use with SOAR's MH-60 helicopters.

JAIC said that its Joint Logistics Mission Initiative (MI), one of six JAIC AI projects, is working “to develop a repeatable, end-to-end AI ecosystem” to bring EHM to scale across the Black Hawk fleet.

EHM, developed in partnership with Carnegie Mellon University, “predicts the probability of an engine hot start so decision-makers can consider next steps,” including replacing the engine or holding it back for training missions instead of deployments in high-risk missions, Army Col. Kenneth Kliethermes, JAIC's Joint Logistics MI lead, said in a recent JAIC blog post.

Another JAIC mission initiative, the Joint Warfighting MI, “is working with several COCOMs to build, test, and expand its Smart Sensor, a video processing AI prototype that rides on unmanned aerial vehicles and is trained to identify threats and immediately transmit the video of those threats back to manned computer stations for real-time analysis,” according to the JAIC blog post.

Army Col. Bradley Boyd, the lead for the Joint Warfighting MI, said that the Smart Sensor could lead to “a dramatic reduction in the amount of data that has to be pushed back for a human to cull through.”

“Instead of staring at one video feed and hours and hours of trees and rocks and nothing happening, that person can instead be monitoring 10 video feeds because they are only seeing the stuff that really matters,” Boyd said in the JAIC blog post.

https://www.defensedaily.com/air-force-add-12-weapons-systems-ai-ml-informed-predictive-maintenance-year/army/

Sur le même sujet

  • What the Pentagon’s new AI strategy means for cybersecurity

    14 février 2019 | International, C4ISR

    What the Pentagon’s new AI strategy means for cybersecurity

    By: Justin Lynch The new Pentagon artificial intelligence strategy serves as a roadmap for how the American military will embrace machine learning in future cyber operations, which could be a boon for companies who invest in the technology. Released Feb 12, the Pentagon's strategy shows how the American military will rely on artificial intelligence as a defensive tool. “We will increase our focus on defensive cybersecurity of hardware and software platforms as a precondition for secure uses of AI,” the Pentagon's new strategy states. “ In order to ensure DoD AI systems are safe, secure, and robust, we will fund research into AI systems that have a lower risk of accidents; are more resilient, including to hacking and adversarial spoofing.” A particular focus of the new strategy is researching “emergent effects,” which is what happens when two artificial intelligence systems interact. The Army's Aberdeen Proving Ground, for one, is conducting studies into how artificial intelligence can protect soldiers' tactical networks and communications from cyberattacks. The Pentagon's artificial intelligence strategy comes as both the American military and hackers have embraced machine learning for cyberattacks. According to an analysis by Fifth Domain, more than half of the new challenges and programs announced by the intelligence community's research arm in 2018 involve machine learning or predictive analytics, which represents a potential boon for cybersecurity researchers. In December, the Pentagon announced that Air Force Lt. Gen. Jack Shanahan would be head of a new artificial intelligence center. Hackers are using artificial intelligence during cyberattacks, Sam Curry, the chief security officer at Cybereason, a threat intelligence firm, told Fifth Domain. Curry said that a particular risk with artificial intelligence is the use of “second order chaotic systems,” where events cause data inputs to change, using the stock market as an example. “Second order systems with badly applied, overreacting machine learning are prone to exploitation,” Curry said. With the release of the artificial intelligence strategy, the Pentagon is attempting to combat significant investments in machine learning by other countries. “Other nations, particularly China and Russia, are making significant investments in AI for military purposes, including in applications that raise questions regarding international norms and human rights,” the strategy says. “The costs of not implementing this strategy are clear. Failure to adopt AI will result in legacy systems irrelevant to the defense of our people, eroding cohesion among allies and partners, reduced access to markets that will contribute to a decline in our prosperity and standard of living, and growing challenges to societies that have been built upon individual freedoms.” https://www.fifthdomain.com/dod/2019/02/13/what-the-pentagons-new-ai-strategy-means-for-cybersecurity/

  • Here’s who will compete head-to-head to build the next homeland missile defense interceptor

    24 mars 2021 | International, Aérospatial

    Here’s who will compete head-to-head to build the next homeland missile defense interceptor

    Two teams have been chosen out of three to proceed in a competition to build the Next-Generation Interceptor to defend the U.S. against intercontinental ballistic missiles.

  • Top US Navy chief talks connecting tech, recovering from accidents

    18 août 2020 | International, Naval

    Top US Navy chief talks connecting tech, recovering from accidents

    By: David B. Larter WASHINGTON — The U.S. Navy is on the brink of what could be a major shift in how it operates, but first the service's top officer wants a plan to both field technologies that have been lagging for years and develop a path forward to add new unmanned tech to the mainstream fleet. Chief of Naval Operations Adm. Michael Gilday took on his latest role in August 2019 and has since been vocal about not just the need to field new tech, but also figuring out how it all fits together. In an exclusive July 16 interview with Defense News, the CNO talked about developing and executing his plans, as well as what it will take for the Navy to recover from a series of high-profile accidents and scandals. The interview has been edited for brevity and clarity. Congress has been asking how the Navy plans to integrate unmanned surface vessels, and whether the service is prematurely committing to them. We've got a family of unmanned systems we're working on. Undersea, we've got extra-large, large and medium unmanned underwater vehicles; on the surface we have small, medium and large unmanned surface vessels; and in the air we have a number of programs. What I've asked the N9 [warfare systems directorate] to do is come to me with a campaign plan that ties all those together with objectives at the end. I've got a bunch of horses in the race, but at some point I have to put my money down on the thoroughbred that's going to take me across the finish line so I can make an investment in a platform I have high confidence in and that I can scale. What I've found is that we didn't necessarily have the rigor that's required across a number of programs that would bring those together in a way that's driven toward objectives with milestones. If you took a look at [all the programs], where are there similarities and where are there differences? Where am I making progress in meeting conditions and meeting milestones that we can leverage in other experiments? At what point do I reach a decision point where I drop a program and double down on a program that I can accelerate? Observers have questioned whether the Navy has a concrete idea of what it wants these unmanned surface vessels to do. What's the progress on that front? The concept of operations that the fleet is working on right now will be delivered in the fall, and that talks conceptually about how we intend to employ unmanned in distributed maritime operations. The other piece of this is, what would a day-to-day laydown look like of unmanned forward? The Navy has got to be forward: For obvious reasons we don't want the fight back here; the Navy exists to operate forward. That's where we need to be in numbers. And with unmanned, if you are not there at the right time, you are irrelevant. There has to be a number of unmanned [systems] forward. I can't just decide to rally unmanned out of San Diego or in the Pacific northwest at a time when they'll be too late to need. You've talked about a “Manhattan Project” to get a reliable network to deploy overseas that can bind together all these new platforms. Where are you with that? That's a critical piece of this, and a really important point of discussion with respect to unmanned, whether that's in the air, on the sea or under the sea, is the Navy Tactical Grid. Coming into the job, the projections for the Navy Tactical Grid was for delivery in about 2035. I knew that was way, way too late. We're investing in netted weapons, netted platforms, netted headquarters — but we don't have a net. So, on a handshake with [then-Air Force Chief of Staff] Gen. [David] Goldfein, I said: “Look, I am all in, and my vision is that the Navy Tactical Grid would be the naval plug into JADC2 [Joint All-Domain Command and Control].” So the Navy Tactical Grid is a very critical piece of the unmanned campaign plan because it becomes the main artery for controlling all those unmanned platforms. Without it, I have a bunch of unmanned that I shouldn't be building because I can't control it very well. I need to put a team of the best subject matter experts that I have on the Navy Tactical Grid to deliver it here within the next few years. As part of its mark on the National Defense Authorization Act, both the House and the Senate made moves to slow down the development of the large unmanned surface vessel. They cited technical glitches with the Littoral Combat Ship program and the Ford class that have resulted in delays. Do you have concerns about slowing down that development, or is there merit to taking a slower, more iterative approach to fielding technologies? First of all, I actually agree with Congress on this. It is frustrating when you get marks on “large unmanned surface vessel” because they are concerned with the command and control of the missile systems that we could potentially put on those platforms or other systems. I go back to the campaign plan: The approach has to be deliberate. We have to make sure that the systems that are on those unmanned systems with respect to the [hull, mechanical and electrical system], that they are designed to requirement, and perform to requirement. And most importantly, are those requirements sound? I go back to: Do I really need a littoral combat ship to go 40 knots? That's going to drive the entire design of the ship, not just the engineering plant but how it's built. That becomes a critical factor. So if you take your eye off the ball with respect to requirements, you can find yourself drifting. That has to be deliberate. With respect to the systems we are putting on unmanned vessels, I'd say we absolutely learned from LCS and Ford; those have to be proven systems that are prototyped and land-based tested before we start doubling down and going into production. The littoral combat ships are quickly coming off the lines. Is the Navy prepared for them? There are things in the near term that I have to deliver, that I'm putting heat on now, and one of them is LCS. One part is sustainability and reliability. We know enough about that platform and the problems that we have that plague us with regard to reliability and sustainability, and I need them resolved. That requires a campaign plan to get after it and have it reviewed by me frequently enough so that I can be sighted on it. Those platforms have been around since 2008 — we need to get on with it. We've done five deployments since I've been on the job, we're going to ramp that up two and a half times over the next couple of years, but we have got to get after it. LCS for me is something, on my watch, I've got to get right. I also have to deliver both the mine and anti-submarine warfare modules. These ships are probably going to [start going] away in the mid-2030s if the [future frigate] FFG(X) build goes as planned. But I need to wring as much as I can out of those ships as quickly as I can. Have you seen any significant successes with the ship? I do think we have it about right with manning. We were honest with ourselves that the original design wasn't going to do it. I really like the blue-and-gold construct because I get way more [operational availability] than I would with just the single crew. So I can get these ships out there in numbers doing the low-end stuff in, let's say, 4th Fleet where I wouldn't need a DDG [destroyer]. The Navy deployed the LCS Detroit to South America — the 4th Fleet area of operations — last year on a counternarcotics mission, and it returned earlier this month. Those are the kinds of missions for which the LCS is perfectly suited. I can deploy these things with a [law enforcement detachment] and a signals intelligence capability, and I can do that on LCS with carry-on gear. It's the right kind of platform for that. Also in 5th Fleet, those maritime security missions that we were heavily sighted on in the late 1990s and early 2000s: They still exist, I'd just prefer to do them with an LCS instead of a DDG if I can. What other programs have caught your attention? In unmanned, whether it's the MQ-4C Triton [long-range surveillance drone] or the MQ-25 Stingray [carrier-based tanker drone], I've got to put heat on those. We have to get them out there in numbers, operating with a high level of confidence, so we can leverage what we learn across the rest of the unmanned build. In the wake of the Fat Leonard bribery scandal, the fatal accidents in 2017 and now the most recent fire onboard the amphibious assault ship Bonhomme Richard, there are questions about systemic issues in the Navy. What are your thoughts about that? The Pentagon and Washington, D.C., drives you to focus on things. One of things [the late Air Force Col.] John Boyd talked about was that the priorities, even in a highly technical world, need to be on people, ideas and machines in that order. The issues we've faced in the Navy over the past few years all come back to people. They all come back to culture. If I draw it to Fat Leonard or to the 2017 Comprehensive Review or the review we did with the SEALs, most of that is cultural. Ninety-five percent of it is people-focused. It really comes down to leadership. That is not lost on me. It is easy in this building not to pay attention to it, but it is on my mind, and at the fleet commander level those are the things we talk most about: people, training, attitude. It's premature to judge the outcome of the investigation into Bonhomme Richard, but what questions do you have as you look at the scale of that disaster? This is a very, very serious incident that I think will force the Navy to stand back and reevaluate itself. We've got to follow the facts. We've got to be honest with ourselves and we've got to get after it. My intention, once the investigations are done, is to make this available for the public to debate, including what we need to do to get after any systemic problems that we might have. But one of things I did on the Sunday [after the fire broke out] was I read the report of the Miami fire back in 2012. That was the last mass conflagration in a shipyard environment that we had. There were a number of recommendations coming out of that incident. One of the questions I have is: Did we fully and adequately implement those recommendations? Because that fire was probably the most recent similar mass conflagration we've had. We learned from that. When we completed the investigation, did we just leave it in the rearview mirror, or did we — no kidding — take it seriously? https://www.defensenews.com/naval/2020/08/17/top-us-navy-chief-talks-connecting-tech-recovering-from-accidents/

Toutes les nouvelles