The project coordinator
Project map
Russian version
English version
Write the mail
AI for airplanes?
News/ > 2019/ > AI for airplanes?/
AI for airplanes?
5 July 2019 Making the connected FMS a reality

The connected flight management system is slowly becoming a reality through software updates and an expanded use of high speed connectivity and aircraft interface devices by pilots.

A flight management system is the main navigation computer used by pilots to take off, cruise, ascend and descend and land an airplane. Flight plans are uploaded to the FMS to provide waypoints that the aircraft navigates between airports. The waypoints are routed to the autopilot, which maintains the aircraft’s heading, unless a pilot decides to hand fly the airplane instead. But the most direct path between two airports is not always the most optimal, with weather patterns and changes in headwinds and tailwinds having a significant impact on an aircraft, no matter how smart its FMS computer is. These basic elements of flying that have been a staple of the FMS since the early 2000s and the way pilots interact with their FMS will become a lot more dynamic as the concept of the connected FMS becomes more widespread.

Honeywell’s connected FMS

Avionics engineering teams at Honeywell Aerospace are researching and developing ways to further improve the concept of the connected FMS that has already been established with Honeywell’s FMS data link service. Operated by their Global Data Center, the service takes a pilot’s requested flight plan up to four hours before takeoff, and updates with the latest wind and temperature data available 30 minutes prior to takeoff.

The service also enables the FMS to recommend optimal step climbs, top of descent points and descent trajectory.

Right now, Honeywell’s cockpit systems division is researching and developing ways to advance the ability of their existing FMS to interact with EFB third party applications.

«One of our biggest investments is on the connected FMS,» Mike Ingram, vice president of cockpit systems at Honeywell Aerospace told Avionics International during a visit to their manufacturing and future research labs facility in Phoenix, Arizona. >>>
>>> «This allows for filed flight plans to easily transfer from your iPad/EFB to your avionics without needing to manually enter them. For FMSs in larger business jets, they are also going to feature more graphical flight planning in the future, allowing pilots to manipulate your flight plan on a map versus typing it in to an MCDU,» said Ingram.

Another focus area of research and development around the connected FMS is a focus on enabling the type of automation within the aircraft’s central navigation computer that can safely allow single pilot commercial airline operations. The enablement of single pilot operations became a widely discussed issue in aviation industry and regulatory circles when a provision to enable an FAA-funded study for regulating single pilot air cargo operations was opposed by the Air Line Pilots Association, which represents more than 60,000 pilots at 34 airlines.

But as all segments of aviation continue to deal with a looming pilot shortage, the concept of single pilot operations could become a reality, and a connected FMS is one of the technological keys to safely allowing it in the future.

«We’re looking at putting an increased level of automation into the FMS,» said Ingram. «Right now, the connected way of filing a flight plan, which is really the newest way to do it, is to push it from your iPad. What if its already updated and ready to go, without the need to upload anything from a tablet? This is one way to help give the industry the level of automation necessary to enable single pilot operations.»

GE Aviation-Avionica connected FMS

GE Aviation and Avionica are also in the process of obtaining FAA supplemental type certification for their version of the connected FMS, which focuses more on increasing the available interconnectivity between pilot tablet applications and the FMS itself.

The two companies formed a joint venture in 2018 with a focus on accelerating aircraft systems edge processing and wireless connectivity capabilities to allow operators to better acquire and analyze critical aircraft data.

Now, the two companies are ready to introduce the connected FMS to operators across all segments of aviation that fly aircraft equipped with GE’s flight management system. Their FMS is featured on Boeing 737s as a standalone system and on the Airbus A320, A321 and A330 in collaboration with Thales. It will also be standard on the COMAC C919 when that aircraft is ready to enter into service.

«What we’re really trying to create is a new interface to the FMS system, that allows tablet apps bi-directional access to the FMS. We also want to enable connected FMS communications with ground systems as well,» Gary Thelen, director of FMS product management at GE Aviation. >>>
>>> Thelen said GE wants to enable a new two-way link between tablet applications and embedded safety critical aircraft navigation systems that can change the isolated way in which pilots use tablets in cockpits today. For example, when a pilot today makes routing changes on a tablet after receiving updated weather, traffic or turbulence information, they must then also input those changes into the FMS by hand.

By linking third party EFB applications directly with the FMS, pilots would be able to take a touchscreen flight route planning graphical mapping application and drag their flight path around an area of weather they’re trying to avoid. That update would then be automatically reflected within the FMS.

Thelen said GE is also focused on eventually integrating the connected FMS into some of air traffic management modernization initiatives being deployed under the FAA’s NextGen program in the United States and the Single European Sky ATM Research (SESAR) program in Europe.

«If you consider the future, being able to marry this with some of the SESAR and NextGen initiatives on more efficiently navigating future airspace, having the connected FMS on the aircraft very much supports those initiatives,» said Thelen.

Both the SESAR and NextGen programs have a common goal of changing the airspace structure, procedure design and air traffic control methodology to adjust for the projected doubling go air traffic growth that will occur globally over the next decade. The ATM technologies being deployed provide the opportunity for the FMS to control or participate in other navigation systems on the aircraft for new air traffic control methods. Among these new methods are time-based metering, merging and spacing, self-separation during continuous descent arrivals and/or during the final segment.

The upgrade required for GE’s connected FMS includes a software update as well as the installation of Avionica’s aircraft interface device and onboard network server. Additionally, the tablets used by pilots will have to feature applications that are developed or updated using GE’s software development kit.

Security protocols included in the development kit provide a verification method of the app that is being connected to the FMS. When the EFB is ready to connect, it populates a numeric code that the pilot must enter into the FMS that then opens up the system for a connection directly to the app. >>>
>>> «This is really a marrying of GE’s FMS and our hardware,» said Sean Reilly, vice president of business development at Avionica. «We provide the bridge to get the connectivity from the FMS through communications as well as providing connectivity to the EFB.»

That’s just one of the functions Avionica and GE are looking to introduce with their connected FMS. Reilly said pilots will really start to get more usage out of the connected FMS once they’re able to start using it in-flight and tailor it to their individual operations.

«If I take off from Miami and ATC gives me a direct route to Tampa, using the connected FMS and my connected EFB I can delete a fix, and once those fixes are deleted out of the EFB, they’re also deleted from the FMS. It minimizes flight crew workload by displaying the same information on the FMS as what’s on the EFB,» said Reilly.

Avionica is also looking to continue to leverage real time data, and higher speed connectivity links that are becoming available such as Iridium NEXT. An existing partnership that they have with Cobham combines the company’s AVIATOR 300D satcom system with Avionica’s avWIFI intelligent router, enabling operators to take advantage of SwiftBroadband Safety for SwiftBroadband cabin connectivity so that pilots can use the faster cabin connectivity normally reserved for passengers today.

Reilly said the new connected FMS technology is in the process of achieving type certification for legacy Boeing 737s that feature GE’s FMS.

«We’re providing security partitioning between all three domains on the aircraft, and enhancing the FMS, iPad, connectivity and user experience for the pilot,» said Reilly.

Gulfstream is developing future AI applications

Gulfstream is developing artificial intelligence through an expanded use of the existing data concentration network for the G500 as an upgrade for future special mission aircraft and business jets manufactured at its Savannah, Georgia facility. >>>
>>> The bulk of future development for specific artificial intelligence applications on special missions aircraft will come from partners such as L3 Technologies which is currently modifying four G550s to become the next generation electronic warfare fleet for the Royal Australian Air Force, Leda Chong, vice president of government programs at Gulfstream, said.

But the aircraft with embedded network capabilities that present opportunities for rapid upgradeability and the use of artificial intelligence and machine learning comes from Gulfstream’s business jet division, in the form of the G500/600’s data concentration network. The new network first entered service on the G500 in 2018, and has not been used yet by Gulfstream’s special missions division.

«Artificial intelligence and machine learning have really become ubiquitous in our day-to-day lexicon,» Chong said. «In the special missions space we leave that up to the primes that need to integrate the technologies on a per contract basis. We don’t go build something because we think some future customer is going to need it. We look for the technical requirements and build to those.»

Developed by GE Aviation, the data concentration network uses an Ethernet backbone and can host coding and facilitate computer language translation. It is the first time Gulfstream is using a central network that can perform smart functions and adds new capabilities by reprogramming existing remote data concentrators with software rather than adding new hardware in the form of computers and processors.

For example, when a pilot starts the engines, the network will start the navigation lights and auxiliary power unit fuel pumps simultaneously. On previous Gulfstream aircraft, these functions would have been controlled by separate computers. That presents major weight savings opportunities as Gulfstream continues to modify existing business jets to meet special-mission requirements, Chong said.

«It is a very intelligent network, that enables increased machine-to-machine language translation capability,» Chong said. «The network can also present some cost reduction opportunities through weight savings, because the use of that type of network on the aircraft eliminates a significant number of radio racks.»

Colin Miller, senior vice president of innovation and engineering at Gulfstream, said that the flexibility of the data concentration network featured on the G500 and G600 is what will allow them to keep the aircraft’s electronics refreshed while also providing a bridge to eventually introducing artificial intelligence for health trend monitoring. >>>
>>> «If you’re going to replace your airplane every 30 years, are you willing to live with the electronics that are 30 years old? There’s a pace of development in the digital space that is much faster than probably any aircraft would be refreshed for individual owners. So how do you manage that gap? One way is by building very resilient environments that are flexible and the data concentration network sets that up for you,» said Miller.

The entire user interface featured across all 10 touchscreens on the G500/600 flight deck can be completely transformed simply by changing the code. Those changes require no replacement of hardware, only a reprogramming of the data concentrator network’s remote data concentrators.

«I can automate functions and put better and improved health trend monitoring I can put new predictive functions in, we might even have some algorithms that represent AI that are helping with pilot workload in the future,» said Miller.

Around 1,500 engineers at a facility in Savannah dedicated to research and development are evaluating the use of predictive maintenance analytics on critical aircraft parts. Miller describes one of the smart functionalities controlled by the network to include the use of self checking the speed of the opening and closing of the G500’s engine valves. The data concentration network tells each valve when to open and close, and an embedded health trend monitoring system measures how fast that is occurring.

«Artificial intelligence and machine learning become important when you want to know how far into an aircraft’s life cycle will that valve start to fail,» Miller said. «Most of AI is not actually thinking, it is pattern matching. Computers are much better at seeing patterns than humans are. An AI engine can look at how many years a part has been in service, and what’re the average number of life cycles it can endure before it will need to be replaced.»

Airlines are increasingly connecting artificial intelligence to their MRO strategies

Predictive maintenance is still in its infancy for commercial airlines, but in the future, predictive will evolve into intelligent maintenance for large-fleet commercial operators.

The use of artificial intelligence (AI) is expanding as a decision-making tool for airline maintenance teams at large fleet commercial airlines. >>>
>>> Airlines based in the U.S., Europe and Asia have been quietly adopting AI tools in the form of intelligent agents for data modeling and simulation to the use of cognitive computing. The use of AI within airline maintenance strategies is evolving into an advanced and expanded use of predictive data analytics.

A challenge exists for airline maintenance teams dealing with the large amount of data being produced by newer generation aircraft: the need for an intelligent application, bot or computer program capable of generating a specific work order task for maintenance technicians, rather than large volumes of data that they have to aggregate and analyze to produce an actionable result. In some cases, an action isn’t even taken, and a technician or engineer simply discovers a no-fault found situation.

Right now, Delta Air Lines is working on adopting artificial intelligence and machine learning into its aircraft maintenance strategy.

«We want to integrate some of the more advanced technologies such as machine learning, artificial intelligence, natural language processing and deep learning into our predictive maintenance process. With the increased digitalization of data, we want to have our technical airplane specialists focusing more on validation rather than the aggregation and analysis of maintenance data,» said James Jackson, Delta Air Lines manager of predictive technology engineering.

While Delta is not the only airline thinking about the use of artificial intelligence for maintenance, Jackson’s approach to the use of AI shows how it can be an effective tool for airline mechanics well into the future.

«If I have an alert that is a single failure mode, then why can’t I automate that and have the alert trigger out prescriptive instruction in our [maintenance information system], to send those out to maintenance to include the parts, tooling, the routing of the aircraft. That way, we have our experts focused on responding to alerts that include instances where their specialized skills are needed, rather than a single failure alert,» said Jackson.

Jackson also explained how one of the primary reasons why Delta wants to adopt an intelligent maintenance strategy is a result of not only the amount of aircraft that the airline has within its fleet, but also the variety of their aircraft models as well. This is also a reflection of how and why the broader commercial airline industry is adopting AI as a decision tool for aircraft maintenance. >>>
>>> Jackson said that historically, Delta’s started to transition toward a digital and predictive-focused maintenance strategy when aircraft engines first began shipping with full authority digital engine controls and smarter sensors capable of capturing and transmitting larger amounts of data. Now, as onboard quick access recorder and data acquisition technologies make access to the rest of the airframe’s data more ubiquitous and easier, their focus is on reducing the number of human maintenance technician and engineering labor hours being used for aggregation and analysis of data, replacing those hours with automated decision making.

Delta has a five-year plan for officially adopting artificial intelligence into its predictive maintenance strategy, according to Jackson.

While Vincent Metz, Air France KLM Head of Strategy, did not explicitly discuss the use of artificial intelligence and machine learning within Air France KLM’s maintenance strategy, these are among the concepts being researched at the airline’s MRO Innovation Lab. Air France KLM uses its MRO Lab to partner with universities, manufacturers and software developers within and outside of the aviation industry to explore how they can make new ideas and concepts a reality within aviation MRO.

But the predictive maintenance strategy discussed by Metz already has the digital infrastructure — as do modern airplanes — to enable the future utilization of artificial intelligence for data mining by the Air France KLM. Developed in Air France KLM’s MRO Lab, Prognos is a predictive maintenance software designed to capture data from aircraft in-flight and on the ground across available connectivity links. That data is then stored and analyzed using algorithms that trigger alerts for components according to a pre-defined set of a parameters. Those results are then uploaded in real time to an airline’s maintenance control center, leading to a maintenance work order.

«One of the things we really focus on in our models is we need to have more length in predicting. Because if we find out 30 cycles before it fails, then suddenly what happens is maintenance that was unplanned, we can turn it into a planned one and then we save a lot of costs,» said Metz.

EasyJet is also adopting AI tools for predicting maintenance, using London-based startup Aerogility’s decision support tool set that features intelligent software agents capable of representing every aircraft in the low cost carrier’s fleet. Every aircraft, including its individual software parts and upgrades, modifications and operating profiles are represented Aerogility’s web-based application and SQL database capable of configuration and simulation output data, including analytics, schedules, and model configuration parameters. >>>
>>> The tool is used by EasyJet to automate daily maintenance planning for its fleet, including the forecasting of heavy maintenance, while simultaneously factoring in existing plans with third-party suppliers and incorporating individual fleet modification and upgrade schedules. EasyJet first started using the new tool in December 2017 and has continuously upgraded its capabilities, which now include forecasting of engine shop visits and landing gear overhauls.

On the aircraft manufacturing side of commercial aviation, Airbus has also emerged as an industry leader actively looking to introduce the increased use of artificial intelligence into airline maintenance operations. Airbus has already established Skywise as its official predictive maintenance and advanced data analytics platform. It serves as a singular access point to data analytics that combine multiple sources into one secure cloud-based platform, including work orders, spares consumption, components data, aircraft/fleet configuration, onboard sensor data and flight schedules.

Las Vegas-based Allegiant became the most recent airline to adopt a new form of this platform, Skywise Health Monitoring. which itself has AI-like capabilities. Airbus has confirmed in testing of Skywise Health Monitoring that it can analyze up to 600,000 data occurrences within 0.1 seconds. That’s an exponential improvement over Airbus’ predecessor health monitoring technology, Airman, which was capable of handling just 7,000 events with a 30-second response time.

Christian Toro, vice president of maintenance and engineering at Allegiant Air, said the airline is using the platform to provide its maintenance information system with predictive capabilities.

«Allegiant uses Skywise to predict component failures and product maintenance actions within our aircraft pneumatics/bleed systems, anti ice system, hydraulics, gears and brakes and auxiliary power unit,» said Toro.

But Airbus is now taking its approach even further, establishing a new online platform, the Airbus AI Gym, seeking to identify new and unexpected changes in the behavior of monitored systems, as well as analyze suspicious behavior for potential faults and failures more efficiently.

«We need help understanding how to (parse) … technical diagrams that have a lot of captions and annotations,» said Adam Bonnifield, VP of artificial intelligence at Airbus. «A key lesson we learned was that bringing … data together is only solving the first part of the problem. The second part of the problem is understanding how that data interoperates.» >>>
Search on the project
© 2019 State Research Institute of Aviation Systems. All rights reserved. Terms of Use.