Back to news

May 16, 2018 | International, Aerospace

The US Air Force Is Adding Algorithms to Predict When Planes Will Break

The airlines already use predictive maintenance technology. Now the service's materiel chief says it's a “must-do for us.”

The U.S. Air Force has started to use algorithms to predict when its aircraft will break, part of an effort to minimize the time and money they consume in the repair shop. The use of predictive analytics has been blazed by airlines, which monitor their fleets' parts in an effort to replace broken components just before — and crucially, not after — they break.

“I believe it is a must-do for us,” said Gen. Ellen Pawlikowski, the head of Air Force Materiel Command, the arm of the Air Force that oversees the maintenance of its planes. She spoke Tuesday at a Defense Writers Group breakfast in Washington. “We see this as a huge benefit.”

If the Air Force could reduce the risk of unexpected breakage — and the attendant need to fly replacement parts and repair crews around the globe — it could reduce costs and boost mission effectiveness. It could also increase the usefulness of the current fleet by reducing the number of aircraft that need to be be held in reserve as backups.

It starts with gathering data, such as the temperature of engine parts or the stresses on the airframe.

“We are trying to leverage what we already get off of airplanes, as opposed to trying to go in and put instruments in places,” Pawlikowski said. “It turns out there's quite a bit that's there, but it may not be a direct measurement. In order to measure the temperature in this one particular spot, I'm getting information somewhere else.”

Artificial intelligence and machine learning can then determine patterns.

The general said the Air Force has been learning a lot from Delta, the world's second-largest commercial airline. “Delta has demonstrated the effectiveness of predictive maintenance in dramatically reducing the number of delays to flights due to maintenance,” she said.

Over the past three years, Air Mobility Command — the arm of the Air Force that oversees all of its large cargo planes and aerial refueling tankers — has been organizing the data it collects on some of its planes. It has started using the predictive maintenance technology on its massive C-5 airlifters.

The Air Force is also using the technology on the B-1 bomber. “The B-1 is an airplane that we actually bought with a whole bunch of data that we weren't using,” Pawlikowski said. “We started to take that data in and start to analyze it....We're very excited about this because we see huge potential to improve aircraft availability and drive down the cost.”

She said she “was impressed when I saw some of the data that they were showing me.”

The Air Force Lifecycle Management Center, which reports to Pawlikowski, has been funding these trials “by finding the loose change in the seat cushions,” she said.

“As we have now shown some things ... we're seeing more and more interest in it and we're looking at increasing the investment in that to bring it further,” Pawlikowski said of the predictive maintenance.

Last September, Gen. Carlton “Dewey” Everhart, head of Air Mobility Command, stressed his desire to use predictive maintenance, but warned it would cost money to get the datafrom the companies that make the planes.

“In some cases, we'll be working this collaboratively with our industry partners,” Pawlikowski said Tuesday. “In other cases, we'll be doing it completely organically.”

Air Mobility Command is also using predictive maintenance technology on the C-130J airlifter. The latest version of the venerable Lockheed Martin cargo plane — the J model — collects reams of data as it flies. In April, the Lockheed announced it was teaming with analytics firm SAS to crunch that data.

“Everything we've been doing up to a certain point has been looking in the rear-view mirror with the data,” said Lockheed's Duane Szalwinski, a senior manager with his company's sustainment organization who specializes in analytics. “We're going to be able to look forward.”

Lockheed is working on a six-month demonstration for Air Mobility Command; officials hope to be able to predict when certain parts will break before a flight.

“If we're able to do that, it kind of changes the game in how you maintain and operate a fleet,” Szalwinski said.

The data will give military planners a wealth of information about their aircraft that could help determine the best aircraft to deploy. “All those things you now know you have insights as to what you will need at the next flight, so you act accordingly,” he said.

“Once we prove that we understand the probability of failure of these parts ... all things then become possible,” Szalwinski said. “Now it's not a matter of if, it's a matter of when. And if you know when, you can start acting accordingly. It would be a gamechanger in the way you manage a fleet.”

Lockheed also wants to use the predictive maintenance tech on the F-35 Joint Strike Fighter.

“The beauty of this is that the toolsets that we're developing, the models, how we clean the data, how we build the models, how we build the algorithms, all of that is not unique to a platform,” Szalwinski said.

Still, instituting predictive maintenance practices fleet-wide is not going to happen overnight, particularly as since it will take time to understand the data, Pawlikowski said.

Using this technology will require a cultural shift among maintenance crews because they'll be replacing parts before they actually fail, Pawlikowski said.

“One of the big benefits is the reduction in the amount of time the airmen on the flightline spends troubleshooting a broken part” because “we will take them off before they break,” she said.

https://www.defenseone.com/business/2018/05/us-air-force-adding-algorithms-predict-when-planes-will-break/148234/

On the same subject

  • It will be at least a decade before Canada sees any of its new frigates

    February 15, 2021 | International, Naval

    It will be at least a decade before Canada sees any of its new frigates

    New frigates are being packed with more combat capability than comparable ships of allies Murray Brewster It will be 2031, at the earliest, before the navy sees the first of its new frigates; a setback brought about partly by the fact Canada, Britain and Australia are still feeling their way around how to build the ultra-modern warship. The outgoing president of Irving Shipbuilding Inc., which is in charge of constructing combat ships for the federal government, said he anticipates steel will be cut on the first of the new generation high-end warships by mid-2024. "We have been trying to take an honest look at where we are and what it will take to build the ship," said Kevin McCoy who recently announced his retirement from the East Coast shipbuilder. The current estimate is that it will take up to seven-and-a-half years to build the surface combatant, a timeline being used by Britain's BAE Systems Inc., which is constructing the first of what's known as the Type 26 design. Both Canada and Australia are building their own variants. "Early on [in the shipbuilding process] estimates are not very good," said McCoy. "Early estimates are not very good for price; they're not very good for size; they're not not very good for duration," McCoy said. "The British ship has a seven-and-a-half year build cycle. So, we're locked in. We said our build cycle will be seven-and-a-half years as well." If they can find ways to speed up the process, they will, he said. ANALYSIS Battle of the budget: DND gears up to defend cost of new warships in the new year Serving military member sues DND over mould exposure on warship Ottawa awards $2.4B contract to finish building navy's supply ships If that timeline holds, it means the federal government's marquee shipbuilding strategy will be two decades old by the time it produces the warship it was principally set up to create. While Irving has been pumping out smaller, less complicated arctic patrol ships and Seaspan, in Vancouver, is building coast guard and science vessels, the strategy conceived by the former Conservative government was driven by the necessity of replacing the navy's current fleet of Halifax-class frigates. Originally, when the shipbuilding strategy was unveiled, it envisioned Canada receiving the first new frigate in 2017. A lot of water, wishful thinking and even money has gone under the bridge since then. Building off existing design The current Liberal government, since taking over in 2015 and embracing the strategy, has been opaque in its public estimates of the build time; suggesting, in some documents, a delivery time in mid-2020s while other more internal records have pegged the first new frigate in the 2027 timeframe. The Department of National Defence, in a statement, acknowledged some of the design and build intricacies are now better understood, and because of that; the first warship will be "approximately 2-3 years later than the previous estimate." A spokeswoman echoed McCoy's remarks about finding ways to move construction along. "We continue to look for efficiencies and are actively working with industry to accelerate the project in order to deliver this important platform to the RCN as soon as possible," said National Defence spokesperson Jessica Lamirande. One of the ways they could do that, she said, would be to construct some, less complex modules of the warship early, the way it has been in the navy's Joint Support Ship project at Seaspan's Vancouver Shipyard. $1 billion and counting: Inside Canada's troubled efforts to build new warships Industry briefing questions Ottawa's choice of guns, defence systems for new frigates McCoy, a blunt-talking former U.S. Navy admiral, suggested the expectations going to the surface combatant program were ultimately unworkable because the federal government came in expecting to do a so-called "clean sheet" design; meaning a warship built completely from scratch. It was the shipyard, he said, which ultimately inched the federal government toward building off an existing design because of the enormous risk and expense of purpose-built ships, a position the Liberals adopted in the spring of 2016. The selection of the British Type 26 design by the Liberal government has spawned criticism, a court challenge and will figure prominently in upcoming reports by the auditor general and the Parliamentary Budget Officer. Combat capability packed into ship The nub of the complaints have been that the frigate is not yet in the water and is still under construction in the United Kingdom. The defence department acknowledged that adapting the British design to Canadian expectations and desires will take a year longer than originally anticipated and is now not scheduled to be completed until late 2023, early 2024. Canada, McCoy said, can expect to pay no more $2.5 billion to $3 billion, per ship as they are produced, which is, he claimed, about what other nations would pay for a warship of similar capability. "This is a big ship, lots of capability" he said, indicating that full displacement for the new frigate will likely be about 9,400 tonnes; almost double the 4,700 tonnes of the current Halifax-class. How much will Canada's new frigates really cost? The navy is about to find out PBO pushes up cost estimate for Canada's frigate build by $8 billion McCoy said what is not generally understood amid the public concern over scheduling and cost is the fact that the Canadian version of the Type 26 will be expected to do more than its British and Australian cousins. Where those navies have different warships, performing different functions, such as air defence or anti-submarine warfare, Canada's one class of frigates will be expected to perform both because that is what the government has called for in its requirements. Dave Perry, a defence analyst and vice president of the Canadian Global Affairs Institute, has studied the program and said he was surprised at the amount of combat capability that was being packed into the new warship. "On the one hand, Canada's one [class] of ship will have more combat capability than many of the other classes of ship that our friends and allies sail with, but it also adds an additional level of complexity and challenge getting all of that gear, all of that firepower into one single floating hull and platform," he said. https://www.cbc.ca/news/politics/canada-shipbuilding-decade-frigates-1.5912961

  • 5 things you should know about the US Navy’s new frigate

    May 7, 2020 | International, Naval

    5 things you should know about the US Navy’s new frigate

    By: David B. Larter WASHINGTON — The U.S. Navy selected Fincantieri's FREMM design for its next-generation frigate, but as with most new platforms it will be a long time before the first ship hits the fleet. The contract, awarded May 30, is for up to 10 hulls constructed at Fincantieri's Marinette Marine shipyard in Wisconsin. The Navy intends to buy at least 20 frigates. Here's what we know about what the years ahead will hold: 1) The price tag. According to Assistant Secretary of the Navy for Research, Development and Acquisition James Geurts, the first hull will cost $1.281 billion, which includes the design money for both the ship and for the work needed at the shipyard to set up a production line. It also includes all the government-furnished equipment, including things such as Raytheon's AN/SPY-6-derivative radar and Lockheed Martin's Aegis Combat System. Of that $1.281 billion, $795 million will go to the shipyard. The next hulls in the buy should cost significantly less. The Navy is aiming for a price tag of $800 million in 2018 dollars, with the threshold at $950 million. But Geurts thinks he can beat both numbers. An independent cost estimate found the follow-on hulls should cost about $781 million if all 20 are built. “The study shows this ship as selected and the program as designed delivering underneath our objective cost per platform,” Geurts said on a May 30 phone call with reporters. 2) The timeline. Detailed design of the future frigate, known as FFG(X), starts right away, Geurts said, and construction will begin no later than April 2022. The first ship should be delivered in 2026 and should be operational by 2030, with final operational capability declared by 2032, Geurts said. The contract should be wrapped up — all 10 hulls — by 2035. The intention is to buy 20 hulls, though it's unclear whether Marinette will build all 20 or if the Navy will identify a second source. 3) What could go wrong? The Navy feels like it did a lot to get this ship deal right, which could be argued was important given a not-so-hot track record with programs lately. Improving the Navy's performance on lead ships, in the wake of the Ford-class debacle, has been a focus of Senate Armed Services Committee Chairman Jim Inhofe, R-Okla. Among the steps the Navy took to retire risk with FFG(X) was to adapt many of the mature systems being designed for the Flight III destroyer program, including the latest version of the Aegis Combat System and a scaled-down version of the AN/SPY-6 radar destined for Flight III. “Some of those efforts are still maturing, such as SPY-6, but from my standpoint I'm very comfortable with how that's proceeding,” said Rear Adm. Casey Moton, program executive officer of unmanned and small combatants. Bringing industry in on the process earlier will also help reduce risk in the lead ship, Moton said. “In general, even before the solicitation went out, the fact that we had industry involved in the conceptual design phase, they were there with us in the requirements; they understood the specifications; we worked with them on cost reduction. Many of the things that tend to trip up lead ships, we took proactive steps to reduce the risk there.” 4) Room to grow. The Navy considered the ability to add new, energy intensive systems on to the ship later in its calculus in selecting FREMM as the FFG(X), according to service officials. During the competition, Fincantieri highlighted that it could fairly easily grow the electrical capacity of the ship, and that all the major computer and engine gear could be swapped out without cutting a hole in the ship, as is often necessary with current classes in the U.S. Navy's inventory. Rick Hunt, a retired Navy three-star admiral who is now a senior Fincantieri executive, told reporters that the company's bid was designed to meet the cost specifications while giving the Navy room to upgrade. “Be flexible in what you do right now, surge to more capacity as soon as we get that [requirement] and be able to grow the ship in lot changes should you need something even greater in the future,” Hunt said. Vice Adm. Jim Kilby, the Navy's top requirements officer, said growth will be important in Navy designs as the service seeks to move away from combating missiles with other missiles. “Understanding how fast the threat is advancing made the service-life allowance so important for us,” Kilby said May 30. “We didn't want [to] define discretely where we are going in the future, so having some margin to include things like directed energy and other systems, that's why it was so important. “We have an extensive laser [science and technology] program in the Navy, we have lasers on some of our ships now. We definitely view it as a requirement for the future as we move into a realm where our launchers are reserved for offensive weapons and our point defense systems are these rechargeable magazines that we can sustain for long periods of time.” 5) Lessons learned. The Navy acquisitions boss feels good about the process that produced the FFG(X) award and thinks it can be a model for other programs. “FFG(X) represents an evolution in the Navy's requirements and acquisition approach, which allowed the acquisition planning, requirements and technical communities along with the shipbuilders to develop requirements for the platform ahead of the release of the detailed design and construction request for proposal," Geurts said. “By integrating the requirements, acquisition planning and design phases, we were able to reduce the span time by nearly six years as compared to traditional platforms. All this was done with an intense focus on cost, acquisition and technical rigor so we got the best value for the war fighter and the taxpayer. It's the best I've seen in the Navy thus far in integrating all the teams together, and it's a model we're building on for future programs.” But it's unclear if a similar approach would work on a clean-sheet, new design the same way it worked for FFG(X), which uses already-developed technologies and a parent design. “Having all the folks in the room early in the process helped move the process along and move it along faster,” said Bryan McGrath, a retired destroyer captain who is now a consultant with The Ferrybridge Group. “The question comes when you consider how applicable duplicating such an effort would be if you were trying to do a clean-sheet design that was incorporating revolutionary technologies, untested technologies, perhaps even undeveloped technologies. That's a different story.” The FFG(X) will be a considerable step forward for the Navy in terms of capability, but isn't exactly a revolutionary platform that may require a different process to arrive at a solution, McGrath said. https://www.defensenews.com/naval/2020/05/05/5-things-you-should-know-about-the-us-navys-new-frigate/

  • Congress poised to let Pentagon start programs before budget passes

    December 11, 2023 | International, Land

    Congress poised to let Pentagon start programs before budget passes

    Air Force Secretary Frank Kendall said time wasted waiting for a budget before starting new programs "is time we’re ceding to China."

All news