Discover the Network of Digital Twins
For Deborah Sherry, Senior Vice President and Chief Commercial Officer at GE Digital Europe, Russia & CIS, the Digital Twin is a digital replica of physical assets and systems built with artificial intelligence algorithms that allows companies to understand, predict and optimise the performance and service of individual assets. “These digital twins have the potential to improve the cycle times of critical processes in advance manufacturing and will lead to new collaboration opportunities among engineers and data scientists,” she affirms.
The 4th Industrial Revolution has led to unprecedented growth in the adoption of digital platforms across industrial organisations. “For the industrial world, this means trillions of dollars in new growth opportunities,” Sherry continues. “Digital Twins are key to driving this growth and are disrupting how the industry works as the data insights generated from them help transform industrial operations and open up new business models.
This technology sounds futuristic, but GE already has over one million digital twins operating in the field today.”
Keith Thornhill, Head of Food & Beverage, Siemens UK & Ireland, comments that the digital enterprise involves the integration of hardware, software and services programmes to record and intelligently leverage the vast quantities of data that processes can create: “Companies can take a further digitalisation step towards linking the virtual and real worlds through the simulation of machines and plants, courtesy of digital twins. The ability, for example, to respond flexibly to individual customer requirements with small batch sizes calls for the use of simulation solutions along the value chain.
“This is where the digital twin comes into its own, precisely duplicating and simulating the properties and performance features of a physical product, a product line, a process or a complete plant in the virtual world before a single screw needs to be picked up in the real world. A central data platform and high performance network components are the basis of a digital twin that can be used to map and optimise an entire plant lifecycle.”
However, there are a lot of companies that explore AI for AI’s sake, which doesn’t work in an industrial setting, cautions Sherry. “General machine learning has a place, but how do you turn it into something of value? For us, that value is utilizing that technology, as well as simulation and modelling together. We use machine learning, simulation and modelling – or a Digital Twin. Machine learning is utilized to look at this vast volume of data that’s being thrown off machines, and being collected, so we can look for patterns.
“Machine learning can tell you a part is going to break – but what do you do? Fix it now, fix it tomorrow, or wait a year to fix it? That question is worth a lot of money to industrial companies. The ability to know when a jet aircraft engine needs maintenance is critical – but the insight to know it can be repaired after normal operations, versus delaying the next flight, is an important consideration.
For this and more articles subscribe to our Industry 4.0 Digital Magazine.