Have you heard of the “Digital Twin?”
This real-world, twin version and digital entity is more than just an identical replicate of a human! This computerized companion is a highly realistic, one-to-one digital model of any physical entity. Whether the subject is a a highly complex city, an industrial physical asset like a spaceship, or an individual’s health profile, the Digital Twin bridges the gap between the digital and physical worlds.
Digital twins, otherwise known as “device shadows,” are created in the same CAD and modeling software that Designers and Engineers use in the early stages of product development. The difference with a digital twin is that the model is retained for later stages of the product’s lifecycle, such as inspection and maintenance.
According to PLM expert Michael Grieves, who was among the first to use the term, the concept of the digital twin requires three elements:
- The physical product in real space
- Its digital twin in virtual space
- The information that links the two
Intertwined with and complementary to the Internet of Things, large amounts of data now collected by IoT sensors on physical objects, personal devices and smart systems make it possible to represent their near real-time status in their digital twin alter-ego.
GE aviation is poised to lead the new digital industrial era. GE is closely identified with digital twin, not surprisingly given the central role played by their IoT strategy. What GE calls the “industrial internet” enables companies “to use sensors, software, machine-to-machine learning and other technologies to gather and analyze data from physical objects or other large data streams and then use those analyses to manage operations and in some cases to offer new, value-added services.” It’s particularly valuable “in the context of industries where equipment itself or patient outcomes are at the heart of the business – where the ability to monitor equipment or monitor patient services can have significant economic impact and in some cases literally save lives.”
“A vast array of industrial machines – jet engines, power generators, pipelines, locomotives increasingly are becoming connected through the internet,” wrote Colin Parris, GE’s VP of Software Research, in a 2015 report. “With the amount of data generated by machine sensors rising exponentially, coupled with ever-more powerful big data analytics, the Industrial Internet has reached a critical tipping point. It requires industrial companies to adopt a digital mindset that embraces what the Industrial Internet can offer in new growth opportunities. Many are calling it the emergence of the data economy.”
The explosive growth of the consumer internet over the past 15 years has created many innovative applications and business models and hundreds of billions of dollars in value. At its heart, the consumer internet is based on connecting several billion people and extracting all kinds of insights from the huge amounts of data they generate. The industrial internet is similarly based on connecting tens of billions of IoT devices and analyzing the even bigger amounts of data they’re beginning to generate. GE estimates that new industrial internet applications will create at least $15 billion of new value for GE alone by 2020.
GE’s strategy is the creation of an individual digital profile or digital twin for each and every industrial machine the company makes. GE is transforming and expanding its business models, much as consumer internet companies have done over the past decade. Mr. Parris lists some examples of how Digital Twin profiles can help reduce costs and improve quality:
- “On our GE90 Engine, we have used flight data from digital twins of our engines to save tens of millions of dollars in unnecessary service overhauls per customer.”
- “Through digital twin models of our Evolution Locomotive, we are minimizing fuel consumption and emissions – generated per trip. This saves 32K gallons / locomotive and 174K tons in emissions per year.”
- “With our 6FA Turbine Combined Cycle Plant, we have used digital models of these plants is helping us achieve a >1 percent increase in efficiency that will be scalable across all plants like this. At this scale, a 1% increase represents billions of dollars in savings.”
Mr. Parris: “While consumer data typically determines what a particular person or group of people want, industrial data looks for the things we don’t want – detecting problems before they happen, saving our customers millions, even billions of dollars.”
A fleet of aircraft, for example, generates gigantic amounts of data over a year, but out all of that data, GE experts are looking for any serious issue that could require the airline to take the plane out of circulation and bring it in for maintenance. GE estimates that there are roughly 30 such bad events. Finding each of those potential needles in the vast data haystacks requires knowing what you’re looking for and where to look. You need both deep physical domain knowledge as well as deep software and analytics expertise.
Digital Twin Overview
The digital twin addresses both the historical industry weakness of poor information management and simultaneously provides the platform to fully harness the vast increase in real and near real-time data that is now economically and technically viable to capture. Whether used for monitoring, diagnostics or prognostics, sensory data will sufficiently be used for building digital twins. Thus, these Digital Twin models serve to find the root cause of issues and improve productivity.