|
Next time you safely get off an aeroplane, consider this: the internal temperature of the jet engines under the wings greatly exceeds the melting point of the material those engines are made from. Don’t panic, though, that’s how hot they are supposed to get. The reason the engines do not turn into molten blobs and fall off is because they are being carefully monitored.
To take care of that monitoring, modern jet engines have a virtual companion, a “digital twin” which resides in a computer on the ground and is fed with real-time data transmitted from the aircraft’s sensors. Algorithms, trained to spot the slightest change in performance, will alert engineers if anything starts to look amiss. Besides improving safety, the digital twin also means the engines can run for longer without being serviced, which saves money.
As my colleagues and I report this week, digital twins are beginning to pop up everywhere. Among other things, twins are monitoring the hearts of patients with arrhythmia, keeping track of Uber’s network of cabs and replicating Amazon’s extensive supply lines well enough for the online retailer to accurately forecast sales several years ahead. Twins are helping geographers predict the risk of floods and
letting carmakers shave years off the development of new models by simulating test drives. Twins are also being developed to help manage factories, companies and entire cities.
But what makes a twin a twin? After all, representations of real-world things are millennia old. Many ancient civilisations built architectural models, for example—and double-entry book-keeping, an analogue simulation of a merchant’s finances, was a 15th-century innovation. Even the ubiquitous spreadsheet can, in its way, be a sort of doppelganger.
A real digital twin, though, offers something more. Unlike their predecessors, these virtual copies operate in real time, constantly refreshed by a deluge of data from sensors and internet-connected gadgets. Recent developments in artificial intelligence (AI) have also given twins an almighty boost, giving them the ability to make predictions about their physical counterparts, and fine-tune their responses.
In the right hands they offer tremendous promise, allowing people to peer into the future, spot problems before they materialise and test wild ideas without real-world consequences. For businesses, this means better designs, streamlined operations and fewer costly blunders. For society the promise is equally tantalising: personalised health care, cities that flow and breathe more easily and, thanks to the threats exposed by climate modelling, glimpses of how the planet might dodge an environmental catastrophe. Digital twins offer an ultimate sandbox where castles can be built, tested and made real.
Elsewhere in The Economist:
Thank you for reading Simply Science. And a particular thanks to those readers who responded to last week’s newsletter on quantum computing. John Charlton, in New Zealand, laments that our article on the subject wasn’t published in time for his university paper on cyber security. We’re glad that you found it useful food for thought anyway, John. If your workplace is undergoing digital twinnification, we’d love to hear more about it. Write to us at
sciencenewsletter@economist.com.
|
