Twins frequently appear in mythologies—throughout history and around the world—to represent contrasting ideas: good and evil, mortal and god, war and peace, sun and moon. In most cases, twins represent two sides that provide some form of balance. That’s what makes it so easy to write Gemini horoscopes.
Twins can also represent a shadow or doppelgänger—a duplicate self that does something the “real” self can’t. This is the basic principle behind applying digital twin models to an IT strategy. By providing a “real” asset with a digital twin, IT departments can spot problems before they become debilitating. In other words, the digital twin enables teams to stay one step ahead.
A digital twin is essentially a digital model of physical infrastructure—a “dynamic” digital representation of a physical asset that enables companies to better understand and predict the performance of their machines. Dimitri Volkmann of GE Digital describes digital twins as, “the combination of data and intelligence that represent the structure, context, and behaviour of a physical system of any type, offering an interface that allows one to understand past and present operation, and make predictions about the future.”
This pairing technology was originally developed by NASA with an eye on creating a digital model that would simulate how equipment behaved in space. Now, thanks to the rise of IoT, applying digital twin models is becoming increasingly widespread—both in terms of the industries embracing it and the use cases. The manufacturing and power generation industry, which relies heavily on the industrial internet, is a prime example.
Take GE: At the Minds + Machines 2016 conference, GE Vice President of Software Research Colin Parris demonstrated how—when paired with augmented reality—a digital twin could overlay the digital capabilities for servicing a steam turbine to detect wear-and-tear, identify trouble spots, and provide suggestions on how to address situations. Applying digital twin models enables GE to eliminate guesswork, predictively maintain equipment, and in doing so, proactively address issues to optimise their assets. GE has more than half a million digital twins active today.
“We see the digital twin as a key technology to fully digitise the physical world,” Volkmann said.
Eliminate the hackers
The effectiveness of the digital twins inspired GE to apply the technology in other areas, like security. In March 2017, the company announced plans to launch security products based on the same underlying principle. The technology, called “Digital Ghost,” is designed to stop cyber attacks.
Justin John, who leads the controls algorithms team at GE’s Global Research labs, described the software as “the industrial version of an immune system.” Using sensors and controls, it identifies anomalies and detects, locates, and neutralises threats—similar to how bodies respond to viruses.
“In cybersecurity, finding new ways to protect critical industrial assets from cyber threats is a never-ending job,” John said. “With Digital Ghost, we’re creating [a] brand new layer of defence and offence that will protect the brains of these cyber-physical systems and even neutralise threats.”
In this case, applying digital twin models enables GE to stay on top of vulnerabilities, and through analytics, predict and thwart cyber attacks. In a world where cyber attacks are on the rise, along with the Internet of Things (which creates additional vulnerabilities), these types of innovative predictive models are pretty exciting.
The 4-step path to digital twinning
According to an IDC Web Conference, titled, “IDC FutureScape: Worldwide Digital Transformation 2017 Predictions,” Jan 2017, companies that invest in digital twin technology by 2018 will see a 30 percent improvement in cycle times of critical processes. Enterprise and corporate IT teams can use these proxies to better understand how people interact with technology, enhance products, detect security risks, identify vulnerabilities in physical infrastructure, and drive innovation. If a particular printer is about to break down, digital twins can enable IT teams to spot those problem areas and head off repairs. Or, if a fleet of network-connected printers has an overlooked security risk, digital twins can help pinpoint it.
In an article by Forbes, SAP’s Senior Vice President of IoT, Thomas Kaiser, outlined four steps to get started in applying digital twin models:
- Integrate smart components into new or existing products.
- Connect the products or services to a central, cloud-based location with streaming, big data, and in-memory and analytics capabilities to capture sensor data and enrich it with business and contextual data.
- Constantly analyse the data to identify areas for improvements, new products, or even new business models.
- Use digital insights to create new services that transform the company—disrupt before your business is disrupted.
Like many mythological twins, applying digital twin models can enable any IT team to be more godlike—or, at least, make fewer human errors. Does this mean the original is the bad doppel? We won’t point fingers.