DIGITAL CUFFLINKS they are virtual representations of a component, a device, or even an entire production line in a factory. Fed with data from sensors installed in their physical equivalent, the digital version can be used to plan maintenance, detect emerging issues, and simulate the effect of upgrades and design changes. Aircraft engines in particular are tracked by their manufacturers in this way. General Electric, Rolls-Royce and Pratt & Whitney, the three main firms involved, maintain individual engine simulations at engineering centers on the ground. These absorb real-time data from their airborne counterparts.
However, at Britain’s Cranfield University, a group of engineers hope to go further. They propose expanding the idea of digital twinning to produce what they grandly call a “conscious aircraft.” This would involve creating a digital twin of an entire aircraft by merging its various monitoring systems and interpreting the result using artificial intelligence (AI).
Today, aircraft tracking systems often work independently of one another. This means, for example, that if a sensor monitoring a valve in the fuel system indicates a problem, engineers can replace that valve, only to find that the problem persists because the real fault is in the electrical system. Ian Jennions, the technical director of the Cranfield Integrated Center for Vehicle Health Management, proposes instead a “system of reasoning” that takes an overview of individual monitoring systems.
Since it is not practical to place a sensor in every potentially fragile part of an aircraft, lest it become too heavy to take off, this will use AI trained to find faults that can be detected from broader measurements such as vibration patterns and temperature changes. Additionally, a digital twin of the entire aircraft is likely to reside on the aircraft itself, rather than relying on vast amounts of raw data being transmitted to a maintenance base for processing. That will provide faster analysis and avoid transmission bottlenecks.
All of this will allow a plane to reconfigure things like battery connections and fuel usage on the fly, so to speak. The reasoning system would also keep an eye on things like the weather the aircraft was operating in, because this can also affect wear on parts. Flying through clouds of dust, for example, can accelerate the abrasion of engine parts.
The aircraft would communicate with its pilots (assuming there were any, as some future aircraft, especially freighters, may well be drones) and also with ground engineers. Such an aircraft would be, in a sense, “aware” of how its various components performed and interacted with each other. It is this level of self-awareness that the researchers use as an excuse to describe the system as conscious, a term they say reflects a direction of travel rather than a goal.
However, that self-awareness would allow the aircraft to be booked for maintenance when needed, rather than on a fixed schedule, and to order any necessary spare parts in advance. The predictive maintenance that such a system would provide should help avoid unscheduled stopovers and repairs. Every day a passenger plane is grounded costs several hundred thousand dollars in lost revenue. Dr. Jennions believes that a conscious aircraft could reduce maintenance costs by around 30%.
Such maintenance could also be automated, at least in part. Cranfield, which started as an aeronautical school in 1946, has its own airport, hangar and Boeing 737 to experience. Researchers are exploring the use of drones equipped with optical and thermal sensors to fly around an aircraft in a hangar, looking for external anomalies. Meanwhile, small snake-like service robots could crawl into enclosed areas, such as fuel tanks, to carry out repairs.
Cranfield’s team hopes to have a digital twin of the entire aircraft up and running by 2024 and a prototype with some degree of self-awareness flying an aircraft by 2035. Whether such a system will include a sense of shame about lousy cabin service remains to be seen. . ■
To enjoy more of our mind-expanding science coverage, sign up for Simply Science, our weekly newsletter.