March 23, 2020 | International, Land, C4ISR
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:
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
July 18, 2023 | International, Aerospace
The Tunisian defense ministry said on Tuesday it had received four T-6C training aircraft from the United States, as part of cooperation to renew its fleet of training aircraft for the air force.
January 15, 2019 | International, Naval
By: David B. Larter WASHINGTON — As the U.S. Navy's surface fleet moves into 2019, a radical shift is coalescing among its leaders: a move away from a model that has driven the way the service has built its ships for decades. When the Navy built its Arleigh Burke-class destroyers, installing the Aegis combat system into the hull meant a large suite of hardware — computers, servers, consoles and displays — designed and set up specifically to run Aegis software. Any significant upgrades to the suite of systems already installed, or to the Aegis system in general, required cutting a hole in the ship and swapping out all the computers and consoles — a massively expensive undertaking. And what's more, Aegis isn't the only combat system in the fleet. Raytheon's Ship Self-Defense System runs on many of the amphibious ships and the Ford-class carriers. Both classes of littoral combat ship run different combat systems, one designed by Lockheed Martin and the other by General Dynamics. And in regard to the ships themselves, there are multiple, siloed systems that don't feed into the main combat system. If Navy leaders get their way, that's going to change. What the surface fleet wants is a single combat system that runs on every ship, and runs everything on the ship, and that doesn't mind what hardware you are running so long as you have the computing power for it. The goal here is that if a sailor who is trained on a big-deck amphibious ship transfers to a destroyer, no extra training will be necessary to run the equipment on the destroyer. “That's an imperative going forward — we have to get to one, integrated combat system,” Rear Adm. Ron Boxall, the chief of naval operations' director of surface warfare, said in a December interview at the Pentagon with Defense News. Boxall describes the current situation to an integrated combat system as the difference between a flip phone and an iPhone. When buying a flip phone, most of the hardware and software are already included, leaving you with a limited ability to upgrade the phone. And if you want to run more advanced applications, you need a new phone. Instead, Boxall wants the combat systems to run like the iPhone. “For us to get faster, we either have to keep going with the model we had where we upgrade our flip phones, or we cross over the mentality to where it says: 'I don't care what model of iPhone you have — 7 or X or whatever you have — it will still run Waze or whatever [applications] you are trying to run,” he said. On a ship, that means that if the Navy adds a new radar, missile or laser, the software that runs the new equipment is developed as an application that interfaces with the single integrated combat system, the way Waze integrates with the iPhone or Android software. This has the benefit of having everything linked into the central nervous system for operators in the combat information center, sonar control, on the bridge or in the ship's intelligence-gathering center. It also means that new systems are quickly integrated, skipping the expensive process of ripping out old servers and consoles. And it means the companies that develop the myriad combat systems in service today — say, Raytheon or Lockheed Martin — won't have a lock on developing software for Navy ships because the Navy wants the combat system to be developed with interfaces that are accessible by outside application developers. “We need to continue down the path to be more aggressive and get a lot more competition in the open-architecture space,” Boxall said. “I wouldn't call it completely open, but as open as we can be, and then share that with people who can, if they are properly classified and secured, they should be able to come into a common space and apply their expertise to develop products that we may or may not want to buy. That's where I'd like to get to.” The vision The grand vision for this operating system from the deck-plates perspective would be the merging what are, today, disparate functions into one unified system, said Bryan McGrath, a retired destroyer skipper and consultant who heads The FerryBridge Group. One of the areas in which this segmentation creates limitations falls between the combat information center — which collects and displays information gathered by ships' sensors — and the intelligence hub known as the Ship's Signals Exploitation Space — which uses top-secret sources to collect data on the theater in which the ship is operating. “We need to break down the barrier between CIC and SSES, and the barrier is both a physical bulkhead and computing systems and platforms,” McGrath said. “That's what an integrated combat system is: You have the traditional combat system function, and the intelligence, surveillance and reconnaissance functions — non-real-time and [top-secret information] functions — merged into one multilevel security-protected computing platform.” In that scenario, if SSES receives information that three Iranian F-14 jets took off from Bushehr Air Base, a watchstander in the combat information center with the proper security clearance could see what information SSES has on the aircraft and their mission while stripping out top-secret information such as sources and methods that SSES needs to protect. And once CIC has a radar track associated with that intelligence, all SSES data will get merged into it so decision-makers in combat have the necessary intel at their fingertips. But the logic applies to all the ship's sensors, not just intelligence collection data. The unified combat system would associate every piece of sensor data with the track being displayed in CIC, McGrath said. Everyone connects to a single system that gives every watchstander all the information they need on every track, both real-time and non-real-time data. “The integrated combat system includes all mission areas,” he said. “It's electronic warfare, it's anti-submarine warfare — we don't segment out air and missile defense and electronic warfare, they are all just applications within the combat system. The Navy has to stop thinking of SESS, sonar, combat, electronic warfare and the bridge as different and separate elements. They have to be part of the whole.” Staggering costs There's a number of obstacles to getting the surface fleet on a unified system, but one that could be insurmountable: the staggering cost of replacing the fleet's outdated computer hardware. The Common Source Library, developed for the Navy by Lockheed, begins moving the Navy down this path of a single, unified combat system. The CSL is essentially the iOS of an iPhone: The Navy can use CSL to program applications that run sensors and weapons systems. So, if the Navy has a new missile system it wants to run, the software application to run it will be designed to run off of the CSL — and ships with the CSL will be able to rapidly integrate it, just like downloading the latest navigation or gaming software for a smartphone. But the issue is that CSL requires specific hardware to function, said Tony DeSimone, chief engineer of Lockheed Martin integrated warfare systems and sensors, in a roundtable with reporters late last year. “One of the challenges the Navy has, the constraints, is the hardware and infrastructure to support a [common integrated combat system],” DiSimone said. “So while we are marching forward with the capability to be open and take in apps, there is an antiquated architecture out there and there is hardware that doesn't support it. ... You can't run [integrated operating] systems today on UYK-43s. You're just not going to be able to do it. So let's gut them and put some blade servers in, and we'll work with you.” The UYK-43 was once the Navy's standard 32-bit computer for surface and submarine platforms. The issue with replacing a fleet full of ancient computers that run old combat systems is the astronomical cost. For example, when the Navy converted the cruiser Normandy into an Aegis Baseline 9 ship, which includes updated displays and blade servers, it cost the service about $188 million and nearly a year offline. When you stretch that over dozens of surface combatants in need of updated computers, you start eating up billions of dollars and lose decades of operational availability. So while CSL does give the Navy an interface with which developers can create applications to run various systems, it's all for naught if the service doesn't have the right equipment. “Our Common Source Library has made us radar-agnostic,” said Jim Sheridan, vice president of Lockheed Martin's naval combat and missile defense systems. “We're also weapons-agnostic. The blocker is that we are not infrastructure-agnostic.” Furthermore, even if the Navy did back-fit all the surface ships with updated servers, you'd need to get various companies to play nice in the sandbox by sharing proprietary information for the benefit of a unified combat system. Ultimately, however, the Navy must affect a paradigm shift that decouples the computer suites that run its combat systems from the system itself, Boxall said. “You can either upgrade the existing ships on that model, which is expensive and you rip the ship apart to do it — cost hundreds of millions of dollars and a year offline — or you design the ship with the idea that you are going upgrade the hardware over its time, and you separate the hardware/software layers,” Boxall said. “We know Aegis,” he added. “What we don't know [is how to] upgrade Aegis at the pace I think we need moving forward in the future. We don't have a structure in place and a process by which we do that upgrades with speed. “When we buy Aegis, it's kind of flip-phone technology: You buy the software and the hardware together. And you can upgrade it, it's just hard to do. If we don't go to a more adaptable model, we are not going to be able to pace the threat.” https://www.defensenews.com/naval/2019/01/14/the-future-of-the-us-surface-fleet-one-combat-system-to-rule-them-all/
February 1, 2024 | International, Aerospace, C4ISR
Four underwing hardpoints are visible on the prototype, indicating the unarmed drone may evolve into a combat-capable UAV.