A few weeks ago I first learned about a relatively new concept - Digital Twin. A Digital Twin is essentially a computerized companion to a real-world entity, be it an industrial physical asset like a jet engine, an individual’s health profile, or a highly complex system like a city. It’s a highly realistic, one-to-one digital model of each such specific physical entity.
Digital Twin helps bring the physical and digital worlds closer to each other. It’s intertwined with and complementary to the Internet of Things (IoT). The huge 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.
“The myriad possibilities that arise from the ability to monitor and control things in the physical world electronically have inspired a surge of innovation and enthusiasm,” said a 2015 McKinsey report on the Internet of Things. Experts estimate that the number of connected things or devices will reach 50 billion by 2020, growing to 100s of billions in the decades ahead. The economic potential of the smart solutions this makes possible is enormous, possibly reaching several trillion dollars within a decade.
The McKinsey report identified the applications areas where IoT solutions will have the biggest impact. These include:
- Individuals - monitoring and promoting improved health, wellness, fitness, personal productivity;
- Homes, offices, buildings - energy management, security, safety, automation of chores;
- Factories - production and supply-chain optimization, quality control, predictive maintenance, inventory management, health and safety;
- Outdoor worksites - equipment maintenance, optimization of custom operations, health and safety, worker productivity; and
- Cars, trucks, aircraft, ships, trains, - improved safety, condition-based maintenance, new service and business models, in-vehicle communications, entertainment.
GE is closely identified with Digital Twin, - not surprisingly given the central role played by the Industrial IoT in the company’s overall strategy. According to GE, 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 10s 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.
A key aspect of 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 thus transforming and expanding its business models, much as consumer Internet companies, - e.g., Amazon, Facebook, Google, - have done over the past decade. 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 percent increase represents billions of dollars in savings.”
In a more recent article, Parris further explained the differences in value creation between the consumer and the Industrial Internet. “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.
“For example an aircraft engine blade can experience what the aviation industry terms as spallation, in which materials begin to erode from a part. This can occur in areas like the Middle East where engines can encounter sandy conditions. As a company that has been in the jet engine business for decades with deep customer relationships, spallation is a condition we know and understand very well. In fact, we have built Digital Twins of jet engines that can model these phenomena and better predict how a blade will degrade over time so that we can advise the customer on when to bring it in for maintenance before a problem occurs. Hence, we can greatly reduce the possibility of an unplanned maintenance that can take a plane unexpectedly out of service. We can avoid the airline losing money and passengers experiencing delays.”
Intelligent personal assistants, - e.g., Apple’s Siri, Amazon’s Alexa, Google’s Assistant, - can be viewed as another major Digital Twin application. Earlier this year, a panel of global experts convened by the World Economic Forum (WEF) named Open AI Ecosystems as one of its Top Ten Emerging Technologies for 2016. “Your robot personal assistant will know when you’re stressed, tired or hungry,” notes the WEF report. “[O]ver the past several years, several pieces of emerging technology have linked together in ways that make it easier to build far more powerful, human-like digital assistants”
Such an open AI ecosystem “connects not only to our mobile devices and computers - and through them to our messages, contacts, finances, calendars and work files - but also to the thermostat in the bedroom, the scale in the bathroom, the bracelet on the wrist, even the car in the driveway. The interconnection of the Internet with the Internet of Things and your own personal data, all instantly available almost anywhere via spoken conversations with an AI, could unlock higher productivity and better health and happiness for millions of people within the next few years.”
“By pooling anonymized health data and providing personalized health advice to individuals, such systems should lead to substantial improvements in health and reductions in the costs of health care. Applications of AI to financial services could reduce unintentional errors, as well as intentional (fraudulent) ones - offering new layers of protection to an aging population.”
“The secret ingredient in this technology that has been largely lacking to date is context. Up to now, machines have been largely oblivious to the details of our work, our bodies, our lives… AI systems are gaining the ability to acquire and interpret contextual cues so that they can gain these skills… Although initially these AI assistants will not outperform the human variety, they will be useful - and roughly a thousand times less expensive.”
Digital Twin is based on some of the most powerful technology trends of the past several years, - Internet of Things, Industrial Internet, predictive modeling, Big Data and analytics and artificial intelligence. Each is a major transformative technology in its own right. Together, as Digital Twin solutions, they promise to help us bring the physical and digital worlds even closer together
Comments